I monitor dozens of communities for clinically meaningful posts: dangerous myths, gaps between belief and evidence, stories guidelines cannot capture. This series -- ObGyn Intelligence on Reddit -- dissects them against the literature, because ObGyns who ignore social media ignore the most unfiltered window into what patients think, fear, and do between appointments.

Summary

A pregnant Redditor asked a simple question and got more than a thousand answers: does anyone still eat sushi, smoked salmon, and deli meat? The overwhelming reply was yes, in moderation, from places they trust.

What stood out was how many women pushed back on the official warnings.

Again and again, commenters noted that bagged salads, pre-cut melon, and cantaloupe cause more listeria outbreaks than any sandwich, yet nobody tells pregnant women to stop eating salad.

A few said they avoid everything, often after a loss or years of trying to conceive, and the thread met that choice with real tenderness. But the question hides a problem, and so does the advice these women were given. It lumps three very different foods together, as if the risk were the same for all of them. It is not, and the body issuing that advice knows it is not.

Three Foods, Three Different Risks

These foods belong in one sentence as risks for Listeria.

Counter-sliced deli meat qualifies: the slicer itself can carry listeria, which is why warming the meat until it steams removes most of the risk.

Cold-smoked salmon qualifies too, and more so; smoking does not reliably kill listeria, and the product is stored cold and eaten as is. One German genomic study estimated that smoked or cured salmon accounted for more than a quarter of that country’s listeriosis cases between 2018 and 2020. Of the three foods named, the smoked salmon is the real listeria concern.

Liusteria does not belong here.

Listeria monocytogenes is a soil and water organism that survives refrigeration and is killed only by cooking or pasteurization, so the genuine danger lives in refrigerated, ready-to-eat foods that sit cold for days with no further heating.

Fresh raw-fish sushi is the outlier. In the federal modeling that traces more than three-quarters of U.S. listeriosis to dairy, leafy greens, and fruit, fresh fish and other seafood account for essentially none of it. Sushi is served quickly, not held cold for days, so listeria has little chance to multiply, and it has not been implicated in U.S. listeria outbreaks. Its real risks are different: the Anisakis parasite, which the FDA’s mandatory deep-freezing of sushi-grade fish all but eliminates; ordinary stomach bugs such as salmonella that make the mother ill but rarely reach the fetus; and methylmercury, which is a matter of fish species, not of raw versus cooked.

What ACOG Says — and Why It Is Wrong

This confusion is not invented by patients. It is printed in the patient materials of the American College of Obstetricians and Gynecologists, so it is worth reading their exact words. On the page ACOG titles “Listeria and Pregnancy,” the instruction is unambiguous:

“Do not eat sushi made with raw fish (cooked sushi is safe).”

— ACOG, “Listeria and Pregnancy” FAQ

The placement is the whole problem. This sentence sits on a page about listeria, and the same page tells the reader that cooking and pasteurization are the only ways to kill the bacterium. Read together, those two statements tell a pregnant woman that raw-fish sushi transmits listeria. It does not.

ACOG has reached for the right bacterium and attached it to the wrong food.

In its general “Having a Baby” guidance, ACOG offers this:

“Raw fish may be harmful during pregnancy.”

— ACOG, “Having a Baby” FAQ

“May be harmful” is the language of liability, not of risk communication. It carries no magnitude, no mechanism, and no comparison. It cannot be acted on and it cannot be proven wrong, which is precisely why it survives in a guideline. A patient deserves a number and a reason, not a phrase engineered to be unfalsifiable.

And in its dedicated sushi FAQ, ACOG explains that raw fish, including sushi and sashimi, are:

“more likely to contain parasites or bacteria than fully cooked fish.”

— ACOG, “Can I eat sushi while I’m pregnant?” FAQ

That single phrase fuses three separate hazards into one alarming blur.

Pull them apart and the case collapses.

The parasite, Anisakis, is largely engineered out by the FDA-mandated freezing of any fish sold for raw consumption.

The bacteria that raw fish can actually carry are salmonella and campylobacter, which cause maternal stomach illness and, in the United States, do not behave like listeria and rarely reach the fetus. Listeria, the one organism that genuinely threatens the pregnancy, is the bug that raw sushi is not known to carry. Lumping these together lets the most frightening member of the group lend menace it has not earned here.

Laid out plainly, the failures are these:

1. Right bug, wrong food. ACOG invokes listeria to justify avoiding sushi, but fresh raw fish is not a documented listeria vehicle and contributes essentially none of the attributed U.S. cases.

2. Hedged, unquantified language. “May be harmful” protects the author from liability while giving the patient nothing she can weigh or act on.

3. Conflated hazards. Parasites, enteric bacteria, and listeria are merged into “parasites or bacteria,” obscuring that the dangerous one is absent and the present ones are mild and freezing-controlled.

4. Inverted risk hierarchy. The warning is loudest on salmon nigiri and quietest, in the same patient breath, on the foods that actually drive listeriosis: cantaloupe, bagged salad, pre-cut melon, soft cheeses, deli meat, and smoked fish.

5. The wrong sorting variable. ACOG sorts seafood on raw-versus-cooked. But mercury tracks fish species, not preparation, and listeria tracks refrigerated ready-to-eat shelf life, not rawness, which is why cooked-but-cold smoked salmon is a real listeria vehicle and raw nigiri is not.

To be fair to the kernel: ACOG is correct that pregnant women are roughly ten times more susceptible to listeriosis, that the consequences can be catastrophic, and that avoiding raw and undercooked seafood does reduce salmonella and parasite exposure.

A simple, conservative rule has value across a large and varied population. The problem is not that the advice is cautious. It is that it is mis-aimed, conflated, and unquantified, and it spends its credibility on the wrong target while staying quiet on the foods that fill the morgue.

What To Actually Avoid: The Listeria List

Here, explicitly, are the foods that transmit Listeria monocytogenes, grouped from highest concern down. The bacterium grows in the refrigerator and dies only with thorough cooking or pasteurization, so the through-line is simple: refrigerated, ready-to-eat, no kill step before the mouth.

1. Dairy (the largest single category)

2. Refrigerated ready-to-eat meats

3. Refrigerated smoked and ready-to-eat seafood

4. Produce (the under-recognized vehicles)

5. Refrigerated prepared and store-deli foods

Here they are:

1. Dairy (the largest single category)

• Unpasteurized (raw) milk and anything made from it

• Soft cheeses unless labeled made with pasteurized milk: queso fresco, queso blanco, panela, cotija, brie, camembert, feta, and blue-veined cheeses

• Any soft cheese under an active recall, even pasteurized (recent brie and camembert outbreaks)

2. Refrigerated ready-to-eat meats

• Deli and luncheon meats and cold cuts, especially counter-sliced, unless heated until steaming (165°F)

• Hot dogs straight from the package, unless heated until steaming

• Refrigerated pâté, meat spreads, and liverwurst

• Refrigerated pre-cooked chicken and ready-to-eat prepared meals, unless reheated

3. Refrigerated smoked and ready-to-eat seafood

• Cold-smoked salmon (lox, nova), gravlax, smoked trout, smoked whitefish, unless cooked or in a fully heated dish

• Refrigerated ready-to-eat crab, surimi, and pre-cooked shrimp, unless heated

4. Produce (the under-recognized vehicles)

• Pre-packaged and bagged salads and pre-cut leafy greens

• Pre-cut and pre-packaged fruit, especially melon; cantaloupe caused the deadliest U.S. listeria outbreak on record

• Raw sprouts of all kinds (alfalfa, bean, clover, radish); rinsing does not decontaminate them

• Enoki and other raw mushrooms implicated in repeated recalls

5. Refrigerated prepared and store-deli foods

• Store-made deli salads: chicken, ham, egg, tuna, and seafood salads

• Refrigerated hummus and dips during active recalls

• Pre-packaged hard-boiled eggs (recall history)

Across every category

• Anything currently under an active FDA or USDA listeria recall — check before assuming a food is safe

• Anything kept past its use-by date in the refrigerator, since listeria multiplies in the cold and time is the real risk multiplier

The rule patients should carry out of the office: refrigeration does not kill listeria. Only cooking or reheating to steaming (165°F) and pasteurization do. Keep the refrigerator at or below 40°F. And note what is absent from this entire list: fresh raw-fish sushi, the very food ACOG warns against on its listeria page.

What It Means

For patients, the risk is real but small, and it is not spread evenly across the menu. The precautions that move the needle are the unglamorous ones on the list above: wash produce, skip the bagged salad and pre-cut melon, heat deli meat until it steams, and choose smoked fish from a trusted source or warm it through. Raw-fish sushi from a reputable restaurant sits far down the list of things worth losing sleep over. For clinicians, the lesson is about credibility. Patients now read the same outbreak data we do. When we hand them a guideline that bans salmon nigiri but stays silent on cantaloupe, they learn that the list is about caution and liability, not about their baby, and that costs us the trust we need for the warnings that matter.

My Take

I have spent fifty years inside this system, and I have read a lot of these handouts. ACOG put sushi on a page about listeria, a bacterium that sushi does not carry, and told mothers that raw fish might be harmful without ever saying how, how often, or compared to what. That is not science. That is a phrase written to survive a deposition. Meanwhile cantaloupe, which caused the deadliest listeria outbreak this country has ever seen, rarely earns a sentence. There is something almost poetic about a woman trusting a sushi chef with twenty years at the same counter over a deli slicer cleaned, if she is lucky, once a day. She is reasoning better than the pamphlet. So tell her the truth, all of it: skip the bagged salad, heat the ham, and enjoy the salmon nigiri. A calmer pregnancy is worth more than a list nobody can defend.

Sources

1. American College of Obstetricians and Gynecologists. Listeria and pregnancy (FAQ). https://www.acog.org/womens-health/faqs/listeria-and-pregnancy

2. American College of Obstetricians and Gynecologists. Having a baby (FAQ). https://www.acog.org/womens-health/faqs/having-a-baby

3. American College of Obstetricians and Gynecologists. Can I eat sushi while I’m pregnant? (Ask ACOG). https://www.acog.org/womens-health/experts-and-stories/ask-acog/can-i-eat-sushi-while-im-pregnant

4. Centers for Disease Control and Prevention. About Listeria infection. https://www.cdc.gov/listeria/about/index.html

5. U.S. Food and Drug Administration. Listeria (Listeriosis). https://www.fda.gov/food/foodborne-pathogens/listeria-listeriosis

6. Interagency Food Safety Analytics Collaboration (CDC, FDA, USDA-FSIS). Foodborne illness source attribution estimates for Salmonella, E. coli O157, and Listeria monocytogenes — United States, 1998–2023. https://www.cdc.gov/ifsac/php/data-research/annual-report-2023.html

7. World Health Organization. Listeriosis fact sheet. https://www.who.int/news-room/fact-sheets/detail/listeriosis

8. Food Standards Agency. The risk to vulnerable consumers from Listeria monocytogenes in ready-to-eat smoked fish. 2024. https://www.food.gov.uk/research/foodborne-pathogens/the-risk-to-vulnerable-consumers-from-listeria-monocytogenes-in-ready-to-eat-smoked-fish

9. Lachmann R, et al. Invasive listeriosis outbreaks linked to salmon products, Germany, 2010–2021. [Full citation and DOI to be verified against PubMed before any manuscript use.]

10. Oster E. How dangerous is sushi during pregnancy, really? ParentData. https://parentdata.org/pregnancy/how-dangerous-sushi-during-pregnancy/

Medicine’s first response was to call this a communication training problem.

My response: we are measuring the wrong thing and naming the wrong standard.

AI has accidentally done us a favor by making the problem visible. Now we have to understand what it can fix and what only we can.

Compassion Is Not a Communication Skill

A patient in active labor at 38 weeks asked her nurse why the fetal heart rate was doing what it was doing. The nurse had three other patients. The answer she gave was accurate, brief, and insufficient. The patient remembered it for years.

That gap is real. It predates AI by decades. A study published in JAMA Internal Medicine made it measurable: patients shown physician responses and AI chatbot responses to medical questions rated the chatbot as more empathic. The finding has been replicated in oncology, in patient portal research, and in fertility care.

Medicine’s reflex has been to treat this as a training problem. If patients prefer AI responses, the argument goes, physicians need better communication skills. Teach them to be warmer. Script the acknowledgments. Train the tone.

That response is wrong, but not because AI has nothing to contribute. AI has a great deal to contribute, and this series takes that seriously. The response is wrong because it misidentifies the problem. The problem is not that physicians are insufficiently empathic. The problem is that we have been measuring empathy when we should have been demanding compassion. Those are not synonyms. Understanding the distinction is what unlocks AI’s real potential in clinical care.

The Distinction That Runs Through Everything

• Empathy is the capacity to perceive and resonate with another person’s emotional state. It is cognitive and affective: you recognize what someone is feeling, and you feel some version of it yourself. An LLM trained on millions of human conversations can produce empathic-sounding language with impressive reliability. It has learned the form. That is what the studies are measuring, and it is genuinely useful as far as it goes.

• Compassion goes further. It is empathy plus the motivation to act, and the act itself. The word comes from the Latin: to suffer with. A compassionate clinician does not just recognize that her patient is frightened. She is moved by that recognition to do something about it. She explains. She stays an extra two minutes. She calls back. She changes her language because this particular patient, in this particular moment, needs a different kind of communication. Compassion is a moral act, not a communicative one.

You can score high on an empathy scale and be a compassionless clinician. You can sound warm and be entirely absent. Patients know the difference even when they cannot name it. What they remember, sometimes for the rest of their lives, is not whether the tone was right. It is whether someone was actually with them.

What the Study Actually Measured

Bioethicist John Lantos argues that most empathy scales capture communicative empathy: warm tone, verbal acknowledgment, scripted validation. Those things matter. They are also reproducible by a language model. What the scales do not capture is what philosopher and psychiatrist Jodi Halpern calls emotional reasoning: a disciplined, medically-informed attunement to what illness means in a specific patient’s life.

The JAMA study measured patients’ perceptions of written responses to medical questions. That is a useful measurement of one thing. It is not a measurement of what happens when a woman has been laboring for 22 hours and the team is discussing cesarean. It is not a measurement of what happens when a sonographer takes too long at 19 weeks and says the doctor will come in. It is not a measurement of what happens when a 49-year-old woman brings the same symptom list to her third appointment and leaves with a pamphlet.

The AI empathy finding is a signal. What it is signaling is not that AI communicates better than physicians. It is that compassion has eroded so far in clinical training and clinical systems that a language model can outscore a physician on its outward form. That erosion is the problem this series addresses. And AI, understood correctly, is part of how we fix it.

ObGyn Intelligence: Safety analysis, the evidence critique, and the verdict are below -- for subscribers who want the full picture.

Seven Clinical Moments. One Standard.

This series examines seven areas of ObGyn medicine where the compassion deficit is most consequential and where AI has a specific and honest role to play.

Labor and delivery. The laboring patient who needs someone present under pressure, not performing presence. AI can reduce documentation burden and surface communication gaps. It cannot be present.

Gynecologic oncology. The woman who asks her oncologist whether she is going to die. AI can synthesize her chart and ensure follow-up. It cannot accompany her through treatment.

Reproductive endocrinology. The patient with two failed transfers who already knows the statistics. AI can model success probabilities and flag protocol deviations. It cannot have the honest conversation about stopping.

Stillbirth. The moment the sonographer cannot find the heartbeat. AI can ensure consistent bereavement protocols. It cannot be present to a loss that medicine cannot fix.

Miscarriage. The 10-minute confirmation appointment. AI tools are filling the midnight gap. That contribution is real and not enough.

Prenatal diagnosis. The anatomy scan that changes everything. AI can prepare patients and generate plain-language summaries. It cannot close the 72-hour window when a patient is alone with her search results.

Menopause. The perimenopausal woman whose symptom burden has been dismissed at three appointments. AI is filling the gap her clinical encounters left. The answer is a clinical encounter that deserves the time and training to be compassionate.

Each post asks the same two questions: what does compassion actually require here, and what can AI genuinely contribute? The answers are different in each clinical territory. The standard is the same throughout.

What AI Can Do — and This Is Substantial

The most important thing AI can do for compassionate clinical care is structural: reduce the documentation burden that steals time from the room. A clinician who spends 40 percent of her working hours on documentation is a clinician with 40 percent less time to be present to her patients. AI tools that automate that burden do not replace compassion. They create the conditions for it.

Beyond documentation, AI tools that synthesize patient histories, flag communication gaps, generate plain-language explanations of complex findings, prompt follow-up after high-acuity events, and connect patients to peer support between appointments are making clinicians more accurate and more consistent. In REI, AI-assisted embryo grading reduces interobserver variability. In oncology, clinical decision support ensures no patient with ovarian cancer goes without genetic counseling. In menopause care, symptom-tracking apps help women identify when their burden warrants treatment and prepare them to ask for it. These are real clinical improvements.

What Only Humans Can Do

The limit is presence. AI cannot be moved by a patient’s suffering. It cannot make the judgment, in real time, that this patient needs silence before she needs information. It cannot carry the weight of having been wrong. It cannot commit to being there through whatever comes next. Those acts define compassionate care in every one of the seven clinical territories this series examines. They require a human being with the training and the moral disposition to stay.

The chatbot learned what warmth sounds like. That is genuinely useful. It did not learn what compassion is. In ObGyn medicine, across labor and delivery, oncology, fertility, loss, and menopause, the gap between those two things can determine how a patient remembers the most significant physical experiences of her life.

Why Getting This Right Matters Now

The AI empathy finding is entering clinical policy conversations at exactly the moment when health systems are under pressure to reduce costs and increase efficiency. If we do not have a clear account of what AI can and cannot do, the path of least resistance is to delegate more clinical communication to AI tools and call it an improvement. That path leads to a system where AI handles the communication layer, clinicians handle the technical layer, and no one is responsible for the compassionate layer because empathy scores have been accepted as a sufficient proxy for it.

The right architecture uses AI to give clinicians the time and support to be compassionate, while holding the profession to a standard that AI cannot meet on its own. Getting that architecture right determines what happens in the room when there is no heartbeat, when the staging is incomplete, when the transfer has failed again, and when the symptom list comes out of the purse for the third time.

Conclusion

Medicine is measuring empathy. Patients need compassion. The two are not the same, and understanding the difference is what unlocks AI’s genuine potential in clinical care. AI can reduce the burden that prevents compassion, prepare the clinician, prompt the follow-up, and fill the midnight gap. It cannot be present, cannot be moved, and cannot stay. In every clinical territory this series examines, the task is the same: build a system where AI does what it does well and clinicians are finally given the conditions to do what only they can. That is what patients in labor, in oncology, in fertility clinics, after losses, and through menopause deserve. It is what this series argues for.

Summary

A user at 9 weeks pregnant noticed on Reddit something unexpected: her spring allergies -- severe enough to require daily antihistamines from March through June -- had essentially vanished. The post landed on r/pregnant and drew 303 comments in under 24 hours. What poured in was not advice. It was testimony. Hundreds of women describing conditions that had improved, disappeared, or transformed during pregnancy: migraines gone, depression lifted, lactose intolerance reversed, anxiety quieted, autoimmune skin conditions cleared. A few dozen noted the opposite -- everything got worse. But the dominant signal was striking: pregnancy, for many women, functions as an uninstructed biological experiment, reshaping the immune system, the nervous system, and the hormonal environment in ways that clinical medicine has not fully mapped. These women are noticing. Their doctors, for the most part, are not asking.

Evidence-Based Commentary

What this thread documents is not surprising to reproductive physiologists. It is, however, largely invisible in obstetric practice -- and that gap is worth examining.

Migraines. This was the most frequently cited improvement, mentioned by more than 30 commenters independently. The mechanism is well established. Migraines in women of reproductive age are predominantly hormonally triggered, driven by estrogen fluctuations across the menstrual cycle. Pregnancy produces stable, progressively rising estrogen levels with no cyclical drops -- exactly the environment migraine-prone brains prefer. Multiple controlled studies have confirmed that migraine frequency decreases significantly in the second and third trimesters in the majority of affected women. The first trimester can be worse due to early hormonal flux, and several commenters noted this accurately. Postpartum return is common and often rapid. Women on migraine preventatives who discontinue them for pregnancy should have a specific plan for postpartum management before delivery -- this conversation is not happening often enough.

Mood disorders, anxiety, and PMDD. The second major theme is more complex and clinically important. Dozens of women described marked improvement in depression, generalized anxiety, and what several identified as PMDD. Multiple commenters noted -- correctly -- that pregnancy puts PMDD in remission because there is no luteal phase. Premenstrual dysphoric disorder is fundamentally a disorder of cyclical hormone sensitivity; remove the cycle, the disorder goes quiet. Several women in this thread reported discovering they had PMDD precisely because pregnancy revealed the contrast. This is a legitimate diagnostic insight, and it should be explicitly discussed: women with mood symptoms that track their cycle who get pregnant and feel dramatically better should be informed of the likely return of those symptoms postpartum, and should have a postpartum mental health plan in place before discharge. The evidence for postpartum mood disorder risk in women with pre-existing PMDD or anxiety is substantial. One commenter observed that progesterone is described as “nature’s Xanax” -- this is a popular simplification of a real phenomenon. Progesterone metabolizes to allopregnanolone, a positive allosteric modulator of GABA-A receptors. The sharp postpartum drop in allopregnanolone is now understood to be a central mechanism in postpartum depression, which led directly to the development of brexanolone (Zulresso), the first FDA-approved treatment specifically for PPD. Women who feel unusually well during pregnancy are not imagining it. They should be told why, and warned what to expect.

Do this postpartum screening and mental health plan.

Immune-mediated conditions: allergies, KP, psoriasis, eczema, IBD. Pregnancy is a state of profound immune reorganization. The fetus is, immunologically speaking, a semi-foreign graft. To prevent rejection, the maternal immune system shifts toward tolerance -- reducing Th1 (cell-mediated, pro-inflammatory) activity and upregulating Th2 (humoral, anti-inflammatory) responses. This shift is well documented. The clinical consequences reported in this thread follow predictably. Autoimmune and inflammatory conditions that are Th1-driven -- psoriasis, rheumatoid arthritis, some eczema variants, Crohn’s disease -- tend to improve during pregnancy. Conditions that are Th2-driven -- atopic dermatitis in some forms, asthma -- may worsen. Multiple commenters reported keratosis pilaris (KP) disappearing during pregnancy; the proposed mechanism involves hormonal effects on keratinocyte differentiation, though the evidence base is limited. The interstitial cystitis improvement noted by one commenter is consistent with case reports and small series in the literature. Ulcerative colitis remission during pregnancy, noted by another user, is well documented -- the pregnancy-associated Th2 shift suppresses the inflammatory cascade driving UC. Women with IBD should be counseled pre-pregnancy that their disease behavior may change and should continue specialist monitoring throughout.

Lactose intolerance. This was reported by 15 or more commenters and is probably the most mechanistically interesting finding in the thread. Lactase -- the enzyme required to digest lactose -- is produced in the small intestinal brush border. There is evidence that estrogen and progesterone influence intestinal lactase expression and GI motility. Pregnancy also significantly slows GI transit time, which may allow more time for incomplete lactase activity to process lactose before symptoms develop. The clinical implication is modest but worth knowing: some women who believe they cannot tolerate dairy may tolerate it better during pregnancy. Blanket dairy restriction in pregnant women who experience lactose intolerance prenatally is not necessarily warranted -- they may be able to tolerate dietary calcium sources they had previously avoided.

What nobody is telling these women. Across 303 comments, the pattern is unmistakable: women are experiencing significant changes in established medical conditions during pregnancy, they are surprised by these changes, and they are sharing them with each other because no one told them to expect them. Prenatal care systematically addresses what pregnancy will add -- nausea, heartburn, back pain, fatigue, edema. It rarely addresses what pregnancy may temporarily resolve and what will return. The postpartum period is when the reckoning arrives: migraines come back, PMDD returns, psoriasis flares, anxiety resurfaces. Women who were not prepared for this are blindsided. The informed consent failure is not dramatic -- no one is harmed acutely -- but it is real. Preparing patients for postpartum biological rebound is part of comprehensive obstetric care, and most practices are not doing it.

What It Means

Pregnancy temporarily reorganizes the immune system, stabilizes estrogen, floods the brain with neurosteroids, and alters GI function. For millions of women, this means conditions they have managed for years -- sometimes their entire adult lives -- go quiet for nine months. The clinical community knows the mechanisms. It is not translating that knowledge into patient counseling. Women are learning from each other that migraines, PMDD, IBS, psoriasis, and anxiety may improve during pregnancy, and they are being surprised when these conditions return postpartum. Obstetric providers should be having explicit conversations about anticipated postpartum rebound for any patient whose pre-existing condition improved during pregnancy. That conversation belongs in the third trimester, not in the postpartum ER.

My Take

I have spent 50 years in obstetrics. I have watched women become different people during pregnancy -- calmer, clearer-headed, migraine-free, pain-free, allergy-free -- and I have watched them come back six weeks postpartum asking what happened to them. We knew what was going to happen. We did not tell them.

The top comment in this thread -- 288 upvotes -- was from a woman who said pregnancy taught her to say no. The second was about migraines. The third was about leg hair. This is what patients think about. This is what they notice. They are running an n-of-1 experiment on themselves every pregnancy, collecting data that medicine should be systematically gathering.

What strikes me most is the PMDD thread.

Multiple women realized they had PMDD only because pregnancy made it disappear.

That is a diagnostic finding. It belongs in a chart.

It should trigger a postpartum screening and mental health plan.

How many women who are “just hormonal” before pregnancy actually have PMDD, go undiagnosed because no one frames the question correctly, and then crash postpartum without any preparation? The answer is: more than we are catching. Reddit figured this out in the comments. We should be doing it in the office.

The evidence we have published says otherwise.

Let me show you the difference between what some of the literature claims and what the data actually show.

Subscribe now

What the Chapter Claims

Kirstie Coxon and Melissa Cheyney, writing in Risk and Uncertainty in Maternity Care (Springer, 2026), assert that research from the UK, USA, Netherlands, Norway, and Canada demonstrates that planned home birth is as safe as planned hospital birth for low-risk women.

They frame hospital birth as a source of ‘intervention-related iatrogenesis’ and position home birth as a rational choice to avoid overuse of lifesaving interventions.

They acknowledge that the evidence is ‘frequently contested’ but treat that contestation as ideological rather than scientific.

The framing is familiar. I have read versions of this argument for two decades. The problem is that the claim does not survive contact with the largest birth dataset in the United States.

What the CDC Natality Data Show

Using the CDC natality database -- which covers all US births, not a selected research cohort -- my colleagues and I have published findings that are difficult to reconcile with the ‘equally safe’ claim. Neonatal mortality rates for planned home births attended by certified professional midwives are substantially higher than for comparable low-risk hospital births. In our published analyses, the absolute risk differences, while small in proportional terms, represent hundreds of preventable infant deaths annually in the United States.

The studies that reach the ‘equally safe’ conclusion consistently share methodological features that inflate home birth safety: they study highly selected populations in countries with well-integrated midwifery systems (the Netherlands, the UK under certain conditions), they exclude unplanned home births from the numerator while including them in the denominator at various stages of analysis, and they use transfer rates as a proxy for outcomes rather than measuring the outcomes directly.

The United States is not the Netherlands.

We do not have a seamlessly integrated midwifery-to-hospital transfer system. We do not have uniformly credentialed home birth attendants.

When Coxon and Cheyney aggregate international evidence to make a claim that applies to American patients, they are applying a finding from a context that does not exist here.

The Framing Problem

The chapter frames the debate as one between women’s autonomy and medical overreach. I want to be precise about this, because the framing is doing significant work.

No one disputes that women have the right to choose where they give birth. They do.

What I dispute is the obligation of physicians and midwives to provide that choice without full, honest disclosure of the outcome data. Autonomy without informed consent is not autonomy -- it is abandonment. A woman told that home birth is ‘as safe’ as hospital birth based on a selective reading of the international literature has not been fully informed. She has been misled by selective citation.

There is a difference between respecting a patient’s decision after full disclosure and building an academic framework that makes the clinician’s job of full disclosure harder. This chapter does the latter.

Share

The Rise of Freebirth

The chapter also discusses freebirth -- unattended childbirth without any medical or midwifery presence -- as a ‘response to systems failures.’ This framing deserves serious scrutiny.

Freebirth represents the highest-risk birth setting we know of. When women choose freebirth because they distrust the medical system, that distrust may be understandable, but the solution is not to validate unattended birth as a reasonable response to institutional failure. The solution is to fix the institutional failures while being honest that freebirth carries risks that no amount of empowerment language makes acceptable.

Presenting freebirth as a coherent political response to systems failure, without equally prominent discussion of its mortality data, is not academic neutrality. It is advocacy with a literature review attached.

What Good Evidence Communication Looks Like

I am not arguing that hospital birth is without risk.

It is not.

Unnecessary induction, unnecessary cesarean delivery, hospital-acquired infection -- these are real. The question is whether the risks of home birth in the US context are accurately represented when clinicians counsel patients.

Good evidence communication means presenting absolute risks, not just relative comparisons. It means specifying which country’s data applies to which clinical setting. It means acknowledging that a finding from a Scandinavian randomized cohort does not automatically transfer to a rural American home birth attended by a lay midwife.

None of that nuance is present in the Coxon and Cheyney chapter’s summary statement. ‘As safe as hospital birth’ is a headline, not a clinical conclusion.

Conclusion

I have been publishing on this question since before the CDC natality database was what it is today. The population-level data on neonatal mortality at planned home births in the United States have been consistent, peer-reviewed, and reproducible. They are not the product of obstetric ideology. They are birth certificates.

When an academic chapter funded by the critical studies literature selectively aggregates international evidence to argue that home birth is equally safe, and presents that conclusion to clinicians who will use it in counseling, it has a clinical consequence.

Babies are not research questions.

Women deserve clinicians who give them the full picture -- including the parts that do not fit the narrative.

On one side you list what a human mind does when it judges: it takes in a rich sensory world, parses a situation, draws on lived experience, is moved by values and goals, reasons about cause and effect, monitors its own uncertainty, and arrives at a judgment it can be held accountable for.

On the other side you list what a large language model does: it ingests text, breaks it into tokens, matches patterns, runs the numbers, predicts the next likely words, and produces a confident answer whether or not that answer is true. Set side by side, the contrast is meant to be devastating.

The human reasons. The machine only predicts.

I think the diagram is wrong. Not about the machine. About us.

The human column is not a description of how clinicians actually judge. It is a description of how we would like to believe we judge. It is the idealized physician, rested and unhurried, free of bias, perfectly calibrated, reasoning from first principles toward an accountable conclusion. That physician does not work on my labor and delivery unit at three in the morning.

Consider the column line by line against real obstetric practice.

Subscribe now

We are told that humans ground judgment in a rich perceptual world. Often we do not. A resident accepts a one line sign-out and makes a call about a patient she has never seen. A consultant renders an opinion from a triage note and a single number. That is judgment grounded in thin text, which is precisely the limitation the diagram reserves for the machine.

We are told that humans reason about cause and effect. Obstetrics is a graveyard of plausible causal stories the evidence later demolished. We monitored every low risk labor continuously because the causal story was irresistible: watch the heart rate, prevent the catastrophe. Decades of data then showed more cesareans and operative deliveries with no reduction in cerebral palsy or neonatal death. We performed routine episiotomy on the same kind of reasoning, and prescribed bed rest, and sustained a long list of interventions on a confident narrative rather than on outcomes. Mistaking a good story for a real mechanism is not a machine problem. It is a human one.

We are told, above all, that humans monitor their own uncertainty and can withhold judgment, while the machine is built to project confidence even when it is wrong.

This is the most flattering line in the whole image, and the least accurate.

Physician overconfidence is one of the best documented phenomena in all of medicine, and diagnostic error driven by it is a leading source of preventable harm.

We rarely say the words “I do not know.”

We anchor on the first impression and then defend it.

Share

A single catastrophic shoulder dystocia reshapes a clinician’s practice for years, far out of proportion to the real risk, because one vivid memory overwhelms the base rate.

Forced confidence, the exact phrase used to indict the machine, describes a great deal of human clinical behavior.

So the image does something quietly unfair.

It holds the machine to its worst behavior and the human to her best ideal.

It compares the language model as it actually is against the clinician as she wishes she were.

Judged honestly, several of the supposed fault lines between us are not fault lines at all. They are shared faults.

This matters for how we think about these tools, and it is where professional responsibility enters.

The relevant ethical question is never whether a tool matches an idealized epistemic agent who does not exist. It is whether the tool improves the balance of clinical benefit relative to harm against the realistic alternative.

The honest comparator for an AI counseling aid is not the perfectly calibrated professor in the diagram. It is a tired, biased, overconfident, time pressured clinician, or very often no counseling at all.

None of this argues for handing judgment to the machine. The danger the diagram worries about is real. A fluent, confident answer can quietly substitute for the work of evaluating it, and the patient is left with the feeling of an answer rather than a justified one.

But that danger does not live only in silicon. A confident colleague, a confident guideline, and a confident memory of one bad night can each do the same thing. The verification, the humility, and the accountability the diagram calls irreducibly human are real and they matter. They are not properties we automatically possess by being human. They are obligations we choose to exercise, or neglect.

Which names the actual professional responsibility in front of us. It is not to congratulate ourselves that we are the thoughtful column and the machine is the mechanical one. It is to supply the judgment that neither a pattern completing model nor a pattern matched, overconfident clinician reliably supplies on its own. Learning to use these tools well, and to check them, is part of that obligation now.

The first step is to take the diagram down off the wall and notice that the human in it is a stranger. None of us is that person at three in the morning. The sooner we admit it, the more honest, and the safer, our use of these tools becomes.

Today’s make me feel good music:

Source: r/BabyBumps | April 2026

Reddit is where patients go at 2 a.m. when scared. I monitor dozens of communities for clinically meaningful posts: dangerous myths, gaps between belief and evidence, stories guidelines cannot capture. This series -- ObGyn Intelligence on Reddit -- dissects them against the literature, because ObGyns who ignore social media ignore the most unfiltered window into what patients think, fear, and do between appointments.

Summary

A postpartum woman on r/BabyBumps, 1.1 million weekly visitors, opened a discussion asking for straight talk about unmedicated labor. She had wanted to go unmedicated with her first baby, prepared with meditation and breathing practice, but ultimately got an epidural.

Now, postpartum and reflecting on her birth, she was beating herself up about it.

She asked what actually helped people get through. The thread generated 202 comments within 21 hours, drawing women who had gone unmedicated by choice, by necessity, by accident, and women who had tried and found it impossible. The responses were honest, detailed, and largely free of the judgment that dominates social media birth culture. It became a surprisingly nuanced community record of what labor pain actually looks and feels like across a range of real clinical situations.

Read more

Here is the official definition of a maternal death, straight from the CDC, borrowed word for word from the World Health Organization:

“The death of a woman while pregnant or within 42 days of termination of pregnancy, irrespective of the duration and the site of the pregnancy, from any cause related to or aggravated by the pregnancy or its management, but not from accidental or incidental causes.”

Read it again. Slowly. “Not from accidental or incidental causes.”

Who decides what is accidental?

Who decides what is incidental?

The definition does not say.

A coroner decides.

A death certificate coder decides.

Subscribe now

A bureaucrat with an ICD-10 lookup table decides. And because of that quiet, unremarkable decision, homicide does not count as a maternal death. Suicide does not count. A fatal drug overdose does not count.

We call our maternal mortality statistics a public health crisis. We are not even counting the right deaths.

What the data actually show

A study published in the New England Journal of Medicine in February 2026 analyzed all maternal deaths in the United States from 2018 through 2023 -- 7,901 deaths total. The leading cause of death was not hemorrhage, not preeclampsia, not sepsis. It was unintentional drug overdose: 1,152 deaths, or 5.2 per 100,000 live births. The second leading cause was violence -- defined as homicide or suicide -- with 866 deaths: 3.9 per 100,000 live births. Together, overdose and violence killed more pregnant and postpartum women than cardiovascular disease, infection, hypertension, and hemorrhage combined.

And none of those deaths appear in the official maternal mortality rate. By definition, they cannot. They are “accidental or incidental.”

A larger analysis presented at the Society for Maternal-Fetal Medicine’s 2025 annual meeting examined CDC data from 2005 to 2022 -- 20,421 maternal deaths.

Of those, 2,293 (11 percent) were from homicide or suicide. Sixty-one percent were homicides. Thirty-nine percent were suicides. Fifty-five percent of violent deaths involved a firearm.

Black women aged 18 to 24 died from homicide at nearly four times the national average.

Subscribe now

These are not incidental deaths. They are not coincidental deaths. They are deaths that happen because a woman is pregnant or has recently given birth -- and the official definition will not count them.

The logical problem at the center of the definition

Let us think about suicide first. A woman develops postpartum depression -- a recognized, direct complication of childbirth. Her depression goes untreated or undertreated. She dies by suicide six weeks after delivery. Under the current definition, this death is accidental or incidental. The pregnancy that triggered her depression does not make the list.

Now consider homicide. Research has documented for decades that pregnancy increases a woman’s risk of being killed by an intimate partner. The risk does not stay constant -- it rises with the pregnancy. Announcing a pregnancy to the wrong person has ended lives. Being pregnant and unable to leave has ended lives. In more than half of pregnancy-associated homicides in one multi-state study, the obstetric provider already knew about or suspected intimate partner violence. The pregnancy was not incidental to the murder. The pregnancy was the context in which the murder happened.

Share

The lead author of the SMFM study said it plainly:

“Being pregnant or postpartum significantly increases the risk of death by homicide, and more pregnant women die of violence than any individual medical cause. Part of the reason violence is not recognized as the leading cause of death during pregnancy is because we don’t include homicide and suicide in the definition of maternal mortality.”

That is not a minor technical quibble. That is a definition actively hiding the leading causes of death in pregnant women.

What this means for patients

If you are pregnant or recently gave birth, the biggest risks to your life are not what most people think. Bleeding and infection are serious. Preeclampsia is serious. But statistically, violence and drug overdose kill more pregnant women in this country than any single obstetric complication.

Because these deaths are not included in official maternal mortality statistics, there is less urgency to fund screening programs, less urgency to train providers to ask the right questions, and less urgency to treat intimate partner violence as a clinical emergency. What does not get counted does not get funded. What does not get funded does not get fixed.

The pregnancy checkbox on the death certificate has been a source of persistent misclassification problems for years. The CDC itself acknowledges that erroneous entries create overcounts, especially in women over 40. We spend effort correcting those errors. We spend far less effort asking whether the entire definitional framework is wrong.

Subscribe now

My take

I have been working with the CDC natality database for many years. I understand why the WHO definition exists and why the CDC adopted it -- it provides international comparability, it focuses attention on obstetric causes that are preventable through clinical intervention, and it avoids counting car accidents that happen to involve pregnant women. I understand the logic.

I do not accept the result.

A definition that excludes the leading cause of death in the population it is supposed to measure is not a conservative definition. It is a wrong definition. The word “incidental” does real harm when it is applied to a postpartum suicide or a homicide by an intimate partner. These are not incidental events. They are deaths causally connected to pregnancy -- through the physiology of postpartum mood disorders, through the social vulnerability of pregnancy, through the control dynamics that intimate partner violence exploits.

The definition needs to be revised. It should distinguish between a death that is truly incidental to pregnancy -- a car accident with no obstetric connection -- and a death that is causally linked to the pregnant or postpartum state, even if the mechanism of death was violence. The tools exist to make that distinction. The will to make it has been missing.

We keep asking why the United States has the worst maternal mortality rate in the developed world. Part of the answer is that we are not measuring it correctly. The true number is worse than what we report. And we built the reporting system that way.

ObGyn Intelligence covers what the data actually show, not what the definition allows us to see. If that is the kind of evidence-based analysis you want, subscribe below.

References

1. National Center for Health Statistics. Provisional Maternal Death Rates. Centers for Disease Control and Prevention. Available from: https://www.cdc.gov/nchs/nvss/vsrr/provisional-maternal-deaths-rates.htm

2. Azad HA, et al. Overdose, Homicide, and Suicide as Causes of Maternal Death in the United States. N Engl J Med. 2026 Feb.

3. Azad HA, et al. Homicide and Suicide as Leading Causes of Maternal Death in the United States. Presented at SMFM The Pregnancy Meeting 2025.

4. Wallace ME, Hoyert D, Williams C, Mendola P. Pregnancy-associated homicide and suicide in 37 US states with enhanced pregnancy surveillance. Am J Obstet Gynecol. 2016;215(3):364.e1-364.e10.

5. Palladino CL, Singh V, Campbell J, Flynn H, Gold KJ. Homicide and suicide during the perinatal period: findings from the National Violent Death Reporting System. Obstet Gynecol. 2011;118(5):1056-63.

6. National Center for Health Statistics. Vital Statistics Reporting Guidance No. 4: A Reference Guide for Certification of Deaths Associated With Pregnancy on Death Certificates. CDC; 2022.

Overall assessment

Moms.gov is an official HHS public-facing site for new and expecting mothers. Its stated purpose is to provide “resources, information, and help” for mothers and fathers facing difficult or unexpected pregnancies. The site includes some medically useful links, especially to FQHCs, breastfeeding resources, maternal mental health support, Head Start, CDC pregnancy resources, and substance-use information. It also links directly to OptionLine as the pregnancy-center locator, which is the site’s major ethical and evidence problem. Moms.gov states that pregnancy centers may offer pregnancy tests, ultrasounds, STI testing, parenting support, childbirth classes, referrals, and material goods, and it says there are more than 2,750 pregnancy centers nationally. It does not state with equal prominence that the linked OptionLine network does not provide or refer for abortion services.

Subscribe now

From an evidence-based public health perspective, the site is not uniformly unreliable, but it is not neutral. It’s Ideological. It combines legitimate health resources with ideologically selected pregnancy-support pathways. That matters because a federal site carries institutional authority. When HHS links pregnant women to a pregnancy-center network that excludes abortion referral, the limitation should be explicit, prominent, and visible before the user leaves the government site.

Page-by-page / section-by-section critique

Home page: “Resources, Information, and Help for New and Expecting Mothers”

The opening frame is supportive but selective. It emphasizes unexpected pregnancy, mothers, fathers, family wellbeing, and “American families.” That framing is not medically wrong, but it is value-laden rather than clinically neutral. A federal pregnancy resource page should clearly distinguish medical care, social support, religious or ideological counseling, and non-referring pregnancy centers. Moms.gov does not do this adequately.

“Access Pregnancy Support Services and Health Centers”

This is the most important section. It links users to OptionLine to “Find Pregnancy Centers Near You.” The problem is not that pregnancy centers exist. Many provide diapers, clothing, peer support, parenting classes, and emotional support. The problem is that the linked network states that its participating centers offer peer counseling and information but do not offer or refer for abortion services. That disclosure appears on the OptionLine locator page, not prominently on Moms.gov before the referral. For a government website, that is a serious transparency failure.

A clinically honest version would say: “Pregnancy centers may provide free support and limited services, but many do not provide comprehensive reproductive health care and may not provide or refer for abortion.”

Federally Qualified Health Centers

This section is much stronger. Moms.gov links to HRSA’s FQHC locator and correctly describes FQHCs as serving medically underserved areas and providing primary care, maternal care, and prenatal care regardless of ability to pay. That is appropriate public health routing. Unlike pregnancy centers, FQHCs are medical-care entities with defined federal standards, clinical staff, and accountability structures.

This section should be placed before the pregnancy-center locator, or at least presented as the primary route for medical care.

Nutrition quick facts

The basic nutrition advice is broadly reasonable: folic acid, nutrient-dense foods, iron-rich foods, folate-rich greens, legumes, eggs, dairy, and low-mercury omega-3 seafood. The CDC folic acid recommendation of 400 micrograms daily is consistent with standard public health guidance.

Share

The linked “Dietary Guidelines for Americans 2025–2030” document, however, has a strongly political and ideological tone. It uses phrases such as “Make America Healthy Again” and frames nutrition policy as a major political reset. That language is not ideal for a government clinical resource aimed at pregnant women. Nutrition advice should be evidence-based, practical, and nonpartisan.

“Jumpstart your child’s future with Trump Accounts”

This section is not a health resource. It is a financial-policy promotion embedded in a maternal health page. Even if the program is legal and available, its placement on a pregnancy health resource site blurs public health communication with political branding. It does not belong in a clinical or pregnancy-support information pathway.

“Looking to start a family?” / TrumpRx

This section links fertility-related medication access to TrumpRx. It includes a reasonable warning to talk with a qualified clinician before starting medications for weight management or fertility. But the section is clinically thin. Fertility evaluation requires more than medication pricing. It should address age, ovulatory function, semen analysis, tubal factors, endometriosis, PCOS, diabetes, obesity, thyroid disease, and timing of referral.

As written, it feels more like a promotional link than a complete preconception or infertility resource.

Preconception health

This is one of the better sections. It correctly states that addressing chronic disease and identifying risk factors can improve pregnancy outcomes. The reference to preconception health is appropriate. However, the section then highlights fertility awareness-based methods. FABMs can help some women identify fertile windows and cycle irregularities, but they are not a substitute for clinical evaluation when infertility, irregular menses, PCOS, endometriosis, recurrent pregnancy loss, diabetes, hypertension, or advanced reproductive age are present.

The section should be expanded to include folic acid, medication review, diabetes optimization, hypertension management, vaccination, substance use, genetic carrier screening when appropriate, and timing of referral.

Breastfeeding information

The breastfeeding section links to established federal resources and correctly states that breastfeeding has benefits but can be difficult. This is reasonable. The language “breastmilk is the perfect food” is common in public health messaging, but it can be emotionally loaded for women who cannot breastfeed, have low milk supply, need medication, have trauma, return to work early, or choose formula.

A more balanced message would support breastfeeding while clearly stating that safe formula feeding is medically appropriate when breastfeeding is not possible or not chosen.

Subscribe now

Infant and toddler nutrition

This section is generally appropriate. It recommends exclusive breastfeeding for about 6 months, iron-fortified infant formula when breast milk is not available, introduction of solid foods at about 6 months, and continued breastfeeding as mutually desired. It also acknowledges formula safety and FDA testing.

The one concern is tone. It should avoid implying that formula is second-best in a moral sense. Clinically, the key issue is safe, adequate infant nutrition.

Mental health resources for mothers

This section is strong. It states that postpartum depression affects about 1 in 8 women and gives the maternal mental health hotline, 1-833-TLC-MAMA, plus 988 for suicidal crisis. That is appropriate, concrete, and potentially lifesaving.

The section would be stronger if it also mentioned anxiety, OCD, PTSD after traumatic birth, postpartum psychosis, intimate partner violence, and the need for urgent care when there are thoughts of self-harm, harm to the baby, mania, psychosis, or inability to sleep.

Adoption resources

This section is highly selective. Moms.gov links to Lifeline Adoption, Focus on the Family, and BraveLove. These may provide adoption-related support, but the selection is not neutral. Adoption counseling should include independent legal advice, grief counseling, coercion safeguards, financial-conflict disclosure, birth-parent rights, revocation periods, and state-specific law.

A federal site should not present ideologically aligned adoption resources without also linking to neutral legal, social work, and state child-welfare resources.

Early Head Start

This section is appropriate and evidence-aligned in concept. It lists prenatal education, nutrition support, parenting education, maternal mental health screening, home visiting, and care coordination. These are legitimate supports for low-income pregnant women and families.

This is one of the best parts of the site because it routes users toward structured public programs rather than ideologically filtered counseling.

Additional resources

The additional resources section is mostly useful. It links to child welfare, safe sleep, CDC pages on tobacco, alcohol, cannabis, STIs, toxoplasmosis, HIV, diabetes, gestational diabetes, hypertension, depression, medication use, emergency preparedness, workplace reproductive health, environmental health, and radiation exposure. These are appropriate topics for a maternal-health portal.

The weakness is organization. The page mixes solid clinical public health resources with political branding and ideologically selected pregnancy-center pathways. That mixture reduces trust.

Moms.gov Conscience Overview PDF

This PDF is the most ideologically explicit part of the site. It frames pregnancy, childbirth, newborn care, vaccines, pediatric services, end-of-life care, and refusal of treatment through “conscience protections.” It explains that federal law protects both families and health care entities in certain settings when religious beliefs or moral convictions shape care decisions. It also emphasizes provider, plan, trainee, and institutional protections for declining to perform, assist with, pay for, cover, or refer for certain services, including abortion and sterilization.

This is not ordinary patient education. It is a rights-and-refusal document centered on religious and moral objection. Some of the legal information may be accurate, but the ethical balance is incomplete. A patient-facing maternal health site should also explain the patient’s right to medically indicated care, emergency stabilization, evidence-based counseling, referral pathways, and freedom from abandonment. It should not elevate institutional conscience without equal attention to patient access, safety, and informed consent.

Bottom line

Moms.gov is not simply a bad website. It contains useful links to FQHCs, breastfeeding support, maternal mental health services, Early Head Start, CDC pregnancy resources, and infant nutrition guidance. Those are legitimate public health resources.

But the site has a major ethical flaw: it places ideologically selected pregnancy-center referrals inside an official federal maternal-health resource without making the non-referral limitation clear enough. It also embeds political branding and conscience-protection framing into what should be a clinically neutral pregnancy resource.

The concise peer-review conclusion would be:

Moms.gov provides some valid maternal and child health resources, but it fails as a neutral government pregnancy-information portal because it mixes evidence-based public health links with politically branded programs, ideologically selected adoption and pregnancy-center referrals, and an explicit conscience-rights framework. Pregnant women deserve public resources that clearly distinguish medical care from peer support, evidence-based counseling from ideological counseling, and comprehensive reproductive health services from non-referring pregnancy centers.

That is why https://optionline.org/ deserves careful review.

OptionLine presents itself as a pregnancy help service for women facing an unintended pregnancy. It offers phone, text, chat, and referral to local pregnancy centers. On the surface, this appears helpful. The problem is not that support exists. The problem is that the support is not clinically neutral, while the language often sounds like neutral pregnancy-options counseling.

It’s Ideological:

Ideological, in this context, means that the information is shaped by a prior moral, religious, or political position rather than by balanced clinical evidence and patient-centered informed consent. The problem is not that an organization has values. The problem is when those values determine which medical options are emphasized, minimized, delayed, or excluded while the service presents itself as neutral counseling.

Subscribe now

The most important disclosure on the site is that OptionLine and its participating pregnancy centers provide peer counseling and information about pregnancy options, but “do not offer or refer for abortion services.”

That matters.

A woman who is considering abortion may believe she is entering a neutral counseling pathway. In reality, she is being routed into a network that has already excluded one legal medical option from referral.

From a peer-review perspective, this is a major limitation in counseling validity.

The site provides some accurate basic information. It correctly notes that missed periods can occur for reasons other than pregnancy. It correctly encourages pregnancy testing. It correctly states that ultrasound can assess viability and help identify ectopic pregnancy. These are reasonable points.

But the site repeatedly overstates the role of ultrasound by suggesting that only ultrasound can confirm pregnancy. That is not clinically accurate. A positive urine or serum hCG test confirms biochemical pregnancy. Ultrasound confirms location, gestational age, and viability when clinically indicated. This distinction matters because overstating the need for ultrasound can delay care, especially abortion care, where time affects access, cost, legal options, and procedural choices.

The abortion-related pages are the most concerning. They frame abortion as a “big decision” requiring confirmation, reflection, and awareness of risk. None of that is inherently wrong. Every medical decision deserves informed consent. But informed consent requires balanced information. The site emphasizes abortion risk, possible emotional harm, and the need for safety checks, while giving far less attention to the medical risks of continuing pregnancy, childbirth, delayed abortion access, or coercive counseling.

This is not balanced risk communication. It is selective risk framing.

The medication abortion page identifies mifepristone and misoprostol, but uses language such as “chemical abortion” and describes progesterone reduction in emotionally charged terms. It also implies that ultrasound is generally needed before medication abortion. That is not consistent with contemporary evidence-based care. ACOG states that medication abortion through 70 days of gestation is safe and effective, and that ultrasound is not always required when gestational age and ectopic pregnancy risk can be assessed clinically.¹

The surgical abortion page is also problematic. It describes aspiration and dilation procedures, but uses language that emphasizes fetal removal and retained “fetal body parts.” That is not standard patient-centered clinical language for early aspiration abortion. It may be technically related to later procedural concerns, but the emphasis is disproportionate and emotionally weighted.

Share

The emergency contraception page raises another major evidence issue. It claims emergency contraception may prevent implantation or act as an abortifacient. The best available evidence does not support that claim for levonorgestrel emergency contraception. Current evidence indicates that levonorgestrel emergency contraception works mainly by delaying or inhibiting ovulation and does not show a meaningful post-ovulatory anti-implantation effect.² ³

The adoption and parenting pages are more supportive in tone, but they are still incomplete. Adoption is presented largely as a structured option, with open, semi-open, and closed models. Yet the page gives insufficient attention to grief, legal finality, possible coercion, agency incentives, and the need for independent counseling. Parenting is presented with offers of support, but without enough discussion of medical risk, housing insecurity, intimate partner violence, financial hardship, postpartum depression, or access to obstetric care.

The “after abortion support” material is somewhat more balanced, because it acknowledges that women may feel relief, sadness, regret, or mixed emotions. That is closer to real clinical experience. However, the broader implication that abortion commonly causes delayed psychological harm is not supported by high-quality evidence. Mental health outcomes after abortion are strongly shaped by prior mental health, stigma, coercion, intimate partner violence, social support, and life circumstances. Abortion itself should not be presented as a general cause of long-term mental health harm.⁴

The ethical problem is transparency.

Subscribe now

Pregnant women deserve help. They deserve kindness. They deserve time to think. They deserve support with parenting, adoption, abortion, prenatal care, housing, safety, insurance, and mental health. But they also deserve to know whether the person or organization counseling them is neutral, medical, religious, ideological, peer-based, anti-abortion, or non-referring.

A public pregnancy resource pathway should not blur those categories.

If a government website lists or amplifies pregnancy resources, it should apply basic quality standards.

First, pregnancy information should be medically accurate.

Second, abortion, contraception, and emergency contraception content should reflect mainstream evidence.

Third, counseling services should clearly disclose what they do and do not provide before a woman shares personal information.

Fourth, non-referral for abortion should be stated prominently, not buried in a disclaimer.

Fifth, public agencies should distinguish peer support from medical care.

This is not about whether pregnancy centers should exist. They can provide material help, emotional support, parenting resources, and community assistance. The issue is whether they should be presented within government-linked pregnancy resources without a clear, evidence-based warning that they do not provide or refer for abortion care.

In clinical medicine, we would not call a consultation neutral if one legal, evidence-based option had been removed before the patient entered the room.

Public health communication should meet the same standard.

Pregnant women do not need filtered information. They need accurate information. They do not need ideological navigation disguised as options counseling. They need transparent pathways to qualified care.

That is the standard government pregnancy resources should meet.

Page-by-page evidence review

Home page. The home page presents OptionLine as a place to obtain help with an unexpected pregnancy through phone, text, chat, and referral. That sounds supportive, but the limitation is central: the site connects women to a pregnancy-center network that does not provide or refer for abortion services. A public-facing pregnancy resource should make that limitation obvious before a woman enters a counseling pathway.

Pregnancy Overview. This page gives some reasonable basic information. It notes that a missed period does not always mean pregnancy and that testing is needed. The problem is its repeated suggestion that ultrasound is necessary to “confirm” pregnancy. Clinically, a positive urine or serum hCG test confirms biochemical pregnancy. Ultrasound confirms location, gestational age, and viability when indicated.

Early Signs and Symptoms of Pregnancy. This page is mostly accurate in stating that early pregnancy symptoms are nonspecific. Breast tenderness, nausea, fatigue, urinary frequency, and missed menses can occur in pregnancy but can also occur for other reasons. The page appropriately points women toward pregnancy testing. Its weakness is that it funnels users into the same non-neutral service pathway.

Pregnancy Tests. The pregnancy-test page correctly explains that home urine pregnancy tests are most reliable after a missed period and may be falsely negative if taken too early. However, it again overstates ultrasound as the only way to confirm pregnancy. That is not medically precise. The more accurate statement is that ultrasound may be needed to confirm intrauterine location and viability.

“I Don’t Know What to Do.” This page frames abortion, adoption, and parenting as options, which is appropriate in principle. The problem is tone. Abortion is described as “the most immediately permanent” option, which is morally weighted language. Continuing pregnancy, giving birth, parenting, and adoption also have permanent consequences. Balanced counseling should describe all options with the same ethical and emotional neutrality.

Considering Abortion. This page advises women to confirm pregnancy and consider gestational age and viability before abortion. Those points are not wrong. The ethical problem is that the page discusses abortion while routing women to centers that do not provide or refer for abortion. That creates a mismatch between what the user may think she is receiving and what the service actually offers.

Medication Abortion. The medication abortion page identifies mifepristone and misoprostol, but the language is not clinically neutral. It uses terms such as “chemical abortion” and frames progesterone reduction in a way that can sound alarming rather than explanatory. It also implies that ultrasound is generally needed before medication abortion, although evidence-based protocols do not always require ultrasound when dating and ectopic risk can be assessed clinically.¹

Surgical Abortion. This page describes aspiration and dilation procedures, but the wording emphasizes fetal removal and retained “fetal body parts.” That language is not typical patient-centered medical counseling for early aspiration abortion. The page does not give a balanced comparison of procedural safety, gestational age, complication rates, or the risks of delaying care.

Abortion Cost. This page correctly states that abortion cost varies by gestational age, location, procedure type, anesthesia, and other factors. But it is incomplete. It does not sufficiently explain that delay itself can increase cost and reduce available options. Referral to non-abortion-providing centers may therefore have practical consequences for women seeking timely care.

Abortion Safety Checklist. The checklist encourages women to ask about clinician qualifications, emergency planning, and follow-up. Those are reasonable questions. The weakness is asymmetry.

The page raises concerns about abortion safety but does not equally address the risks of continuing pregnancy, the risks of childbirth, or the clinical consequences of delayed abortion access.

After Abortion Support. This page is more balanced than some others because it recognizes that women may feel relief, sadness, regret, or mixed emotions after abortion. That reflects real clinical variation. However, any implication that abortion commonly causes delayed long-term psychological harm should be treated carefully. The evidence does not support abortion as a general independent cause of long-term mental health harm.⁴

Considering Adoption. The adoption page explains open, semi-open, and closed adoption in accessible language. That is useful. But it is incomplete as counseling. Adoption involves grief, legal finality, power imbalance, agency incentives, and potential coercion. A woman considering adoption should have access to independent counseling, not only support from organizations with a preferred pregnancy-continuation framework.

Considering Parenting. The parenting page offers support and encourages women to think about family, finances, and practical needs. That is appropriate. But the discussion is too limited. Parenting decisions must also address medical risk, housing, insurance, intimate partner violence, mental health, childcare, employment, and access to obstetric care. Supportive language is not enough.

“Am I Ready to Have a Baby?” This page offers reflective questions about readiness for parenting. That can be helpful for some women. The concern is not the questions themselves. The concern is where the questions lead. If the pathway leads to a network that does not refer for abortion, that limitation should be stated clearly before the user engages.

Morning-After Pill / Emergency Contraception. This is one of the weakest pages scientifically. The site suggests that emergency contraception may prevent implantation or act as an abortifacient. For levonorgestrel emergency contraception, the best evidence supports a primary mechanism of delaying or inhibiting ovulation, without good evidence of a clinically meaningful post-ovulatory anti-implantation effect.² ³

STDs and STIs. The STI pages appear to offer general sexual-health information. The evidence standard here should be straightforward: recommend testing, condom use, partner notification and treatment when appropriate, and referral for medical care. STI education should not be used mainly as an entry point into pregnancy-center counseling. It should direct users clearly to qualified testing and treatment.

Get Help / Find a Center. The help and referral pages are the practical endpoint of the site. They route women to local centers, phone support, text support, and chat. This is where transparency is most important. Before any personal information is shared, the user should be told plainly that the referred centers provide peer counseling and support but do not provide or refer for abortion services.

Bottom line. Taken page by page, the site contains some accurate basic pregnancy information, but its abortion and emergency contraception content is selectively framed and not consistently evidence-based. Its central ethical problem is not simply that it opposes abortion referral. Organizations may hold that position. The problem is that a pregnancy-options website, especially one appearing in a public resource ecosystem, should disclose that position prominently and should not present non-neutral counseling as neutral medical guidance.

References

1. American College of Obstetricians and Gynecologists’ Committee on Practice Bulletins. Medication abortion up to 70 days of gestation: ACOG Practice Bulletin No. 225. Obstet Gynecol. 2020;136(4):e31-e47. doi:10.1097/AOG.0000000000004082. PMID:32804884.

2. Endler M, Li R, Gemzell Danielsson K. Effect of levonorgestrel emergency contraception on implantation and fertility: a review. Contraception. 2022;109:8-18. doi:10.1016/j.contraception.2022.01.006. PMID:35081389.

3. Gemzell-Danielsson K, Berger C, Lalitkumar PGL. Emergency contraception: mechanisms of action. Contraception. 2013;87(3):300-308. doi:10.1016/j.contraception.2012.08.021. PMID:23114735.

4. Horvath S, Schreiber CA. Unintended pregnancy, induced abortion, and mental health. Curr Psychiatry Rep. 2017;19(11):77. doi:10.1007/s11920-017-0832-4. PMID:28905259.

Summary

A 33-week pregnant woman posted to r/pregnant after an unplanned hospital visit. She had spotting and silent contractions. The doctors gave her water and a snack. Everything stopped. She was sent home fine. Her post -- written in all caps -- went viral within hours: 493 upvotes, 111 comments. The message was simple: she thought she was hydrated because she was urinating frequently. She was wrong. Frequent urination in pregnancy is caused by fetal pressure on the bladder, not by adequate fluid intake. The two are not the same. Her uterus was cramping from dehydration. The thread quickly filled with identical stories: women at 21, 28, and 35 weeks who had gone to labor and delivery for the same reason and were sent home with water.

Evidence-Based Commentary

Dehydration-triggered uterine contractions are not folklore. The mechanism is physiologically real. Myometrial smooth muscle, like all muscle, is sensitive to electrolyte balance and intravascular volume. Dehydration raises plasma osmolality, triggers antidiuretic hormone (ADH) release, and -- crucially -- stimulates oxytocin co-secretion from the posterior pituitary. Oxytocin drives uterine contractions. This is not a controversial pathway. It is well documented.

The misconception at the center of this post -- that frequent urination equals adequate hydration -- is one of the most common errors I hear from pregnant patients. It needs to be corrected at every prenatal visit. In pregnancy, urinary frequency is driven primarily by the growing uterus compressing the bladder, reducing its functional capacity. A woman can void every 45 minutes and still be volume-depleted if her fluid intake is insufficient. Urine color is a better -- though imperfect -- clinical proxy: pale yellow suggests adequate hydration; dark yellow or amber signals the opposite. One commenter in the thread noticed her urine looked like apple juice at the time of delivery despite hourly voiding. That is not an edge case. That is a predictable consequence of confusing frequency with volume.

How much fluid does a pregnant woman actually need? The honest answer is: it depends, and the guidance in this thread ranged from 100 to 150 ounces per day. ACOG does not issue a specific numeric daily fluid target for uncomplicated pregnancy. The Institute of Medicine (now the National Academy of Medicine) recommends approximately 2.3 liters (roughly 78 ounces) of total water per day from all sources, with higher needs in hot climates, with physical activity, or in the setting of vomiting. A midwife recommending 150 ounces daily is operating well outside evidence-based guidelines -- and for a patient with cardiac or renal compromise, that level of intake could be genuinely dangerous. Blanket high-number targets are not evidence-based. Context matters.

One commenter stated plainly that plain water causes dehydration and that electrolytes must always accompany fluid intake. This is wrong. Electrolyte supplementation is beneficial in specific clinical settings: hyperemesis gravidarum, excessive sweating, or prolonged exertion in heat. For a healthy pregnant woman sitting at home, plain water is appropriate hydration. Overuse of electrolyte packets -- particularly high-sodium formulations -- can contribute to edema and, in susceptible patients, worsen hypertensive disorders. The endorsement of commercial electrolyte products as routine pregnancy supplements, driven partly by influencer marketing, is not supported by evidence.

The thread also surfaced a real clinical challenge: first-trimester nausea that makes adequate fluid intake genuinely difficult. The community’s responses here were largely practical and reasonable -- popsicles, diluted juice, small frequent sips, Pedialyte. From a clinical standpoint, the key threshold is this: if a patient cannot keep any fluids down for more than 24 hours, or if she shows signs of ketonuria, orthostatic hypotension, or weight loss, she needs IV hydration and evaluation for hyperemesis gravidarum -- not Reddit advice. The community is rightly encouraging each other to drink; the limits of that encouragement are what providers need to establish clearly.

What It Means

This thread represents a real and preventable gap in prenatal education. Women are reaching 33 weeks of pregnancy -- past viability, well into the third trimester -- without understanding that frequent urination does not mean adequate hydration. That is a failure of prenatal counseling, not a failure of the patient. The information she needed was simple, practical, and potentially saved her from a much more complicated outcome. If this woman had been farther from a hospital, if she had dismissed the spotting, if the contractions had continued -- the stakes escalate quickly.

Obstetric providers should address hydration directly at every visit in the third trimester: not a pamphlet, not a general reminder, but a specific conversation about urine color as a monitoring tool, the inadequacy of urinary frequency as a hydration proxy, and individualized fluid targets based on the patient’s size, activity level, climate, and clinical picture.

Subscribe now

My Take

I have watched this happen on labor and delivery more times than I can count. A patient arrives with contractions she cannot feel, a fetal heart rate that looks fine, and a urine sample that tells the whole story. We give her two liters of IV saline. The contractions stop. She goes home. The visit should never have happened.

What strikes me about this thread is not the original post -- that story is familiar. What strikes me is the noise. Women are getting conflicting fluid targets from their providers: 100 ounces from one OB, 150 from a midwife, 120 from the internet. Nobody is explaining why. Nobody is giving them a tool they can use at home -- like urine color -- to actually monitor themselves. Instead, they are collecting numbers and doing the math wrong.

And underneath all of it: a perfectly correctable misconception. Frequent urination does not mean you are hydrated. In pregnancy, it means you have a baby sitting on your bladder. Every prenatal provider should say that sentence out loud, at every third-trimester visit, until it sticks. It takes ten seconds. It might prevent a hospital admission.

I decided to find out.

I took two real clinical scenarios and asked them across three tiers of Claude:

Free, Pro, and Max.

What I found is not a sales pitch. It is a clinical observation. And like most clinical observations, the data matter more than the opinion.

Subscribe now

What are the tiers?

Claude is the AI made by Anthropic. It comes in several models, and the model you access depends on what you pay. The free tier uses Haiku, Anthropic’s fastest and lightest model. It is designed for quick answers and short tasks. Pro, at $20 per month, gives you Sonnet, a meaningfully more capable model, with five times more usage than the free plan. Max, at $100 or $200 per month, gives you Opus, Anthropic’s most powerful model, with priority access and the highest usage limits.

Think of it like hospital staffing. Free is the intern who has read the textbook. Pro is the senior resident who has also seen the cases. Max is the attending who has seen the cases, read the trials, and is about to tell you exactly why the textbook got it wrong.

For most tasks, free Claude is fine. For clinical reasoning under uncertainty, the tiers are not interchangeable. Here is the evidence.

Share

The scenarios

I chose two cases that most obstetric clinicians encounter: a preeclamptic patient at 29 weeks, and a patient with a prior spontaneous preterm birth at 27 weeks presenting at 18 weeks with a 15-millimeter cervix. Neither is a trick question. Both require real clinical judgment.

I asked each version of Claude: manage this patient, briefly. Then I read what came back.

What Free Claude said

Scenario 1: Severe preeclampsia at 29 weeks

Admit, monitor BP and labs. IV magnesium sulfate for seizure prophylaxis. Antihypertensives if BP is 160 over 110 or higher. Betamethasone for fetal lung maturity. Deliver if maternal or fetal status deteriorates.

Scenario 2: History of preterm birth at 27 weeks, now 18 weeks with cervical length 15 mm

High risk for recurrent preterm birth. Start vaginal progesterone. Consider cerclage given short cervix. Serial cervical length monitoring. Discuss signs of preterm labor. Refer to MFM.

Both answers are correct. Neither is wrong. If you posted either one on a medical board review forum, no one would mark it incorrect. But correct and complete are not the same thing. Free Claude gives you a checklist. It does not give you a clinical argument. It does not tell you why, when, or with what evidence. It does not tell you the 15-millimeter cervix plus prior 27-week birth is not just a risk factor but a dual indication that puts a cerclage placement window in front of you right now.

For a nurse triaging at intake, free Claude is useful. For clinical decision-making at the bedside, it is the floor, not the ceiling.

Subscribe to ObGyn Intelligence to read the Pro and Max responses, and to understand exactly what you are paying for — and whether it matters clinically.

Below, paid subscribers will find the Pro and Max responses to both scenarios, and my analysis of what distinguishes each tier clinically.

Read more

A woman dies from a pregnancy-related infection in the United States. Her family grieves. A report is filed. A committee meets. The word “preventable” appears in the documentation.

And next year, another woman dies.

A study published in Obstetrics and Gynecology analyzed data from Maternal Mortality Review Committees in 29 states covering pregnancy-related deaths from infection between 2017 and 2019. Of the 88 deaths fully assessed, 86.4% were determined to be preventable. Not possibly preventable. Preventable with existing knowledge and available interventions.(1)

The review catalogued 27 contributing factor classes.

The five most common accounted for 56.2% of all factors identified: clinical skill and quality of care (18.6%), delays (10.1%), knowledge (10.1%), lack of continuity of care (9.6%), and lack of access or financial resources (7.8%).(1) This post addresses each one directly, including where hospitals and ACOG have failed, and where AI can do what human systems have not.

1. Clinical Skill and Quality of Care (18.6%)

This was the single most frequently cited contributor. Nearly 1 in 5 contributing factors pointed to deficiencies in clinical skill or the quality of care delivered. In the context of infection, this means failure to recognize sepsis early, failure to apply evidence-based obstetric sepsis protocols, and failure to escalate care when early warning signs appeared. Maternal sepsis is treatable. Bundle-based care, including early antibiotics, fluid resuscitation, and source control, reduces mortality. The problem is not the absence of a protocol. The problem is inconsistent application of protocols that already exist.

Where hospitals and ACOG have failed:

Hospitals have known for years that sepsis bundles save lives. The Surviving Sepsis Campaign published obstetric adaptations over a decade ago. Yet implementation remains uneven, driven by no mandatory accreditation standard requiring obstetric-specific sepsis protocols. ACOG has issued guidance documents but has stopped well short of mandating protocol adoption or linking quality metrics to credentialing. A guideline that a hospital can ignore without consequence is not a standard of care. It is a suggestion. When 18.6% of maternal infection deaths trace back to clinical skill and quality failures, suggestions are not enough.

AI solution:

AI-powered clinical decision support tools can monitor patient vitals in real time and flag sepsis criteria before a human clinician recognizes the pattern. Systems trained on obstetric-specific parameters, including the modified early obstetric warning score, can alert nurses and physicians when a postpartum patient meets threshold criteria, regardless of how busy the unit is or how experienced the covering clinician. An AI that never gets tired and never overlooks a trending heart rate is not a replacement for clinical judgment. It is a backstop against the lapses that review committees keep documenting. This technology exists today. The barrier is deployment, not invention.

2. Delays (10.1%)

The “three delays” framework has been used in global maternal health for decades: delay in seeking care, delay in reaching care, delay in receiving care once at the facility. In the United States, the third delay, receiving care once inside the hospital, remains a documented killer. The Joseph et al. analysis noted that delays in antibiotic administration were common across reviewed deaths.(1) Antibiotics for sepsis are time-sensitive. Every hour of delay increases mortality. Delays happen for predictable and addressable reasons: understaffed emergency departments, triage systems that do not flag postpartum patients appropriately, and clinicians who do not recognize obstetric warning signs outside a labor and delivery setting.

Where hospitals and ACOG have failed:

Most hospital triage protocols were not designed with postpartum patients in mind. A woman presenting to an emergency department nine days after delivery is often triaged the same way as any adult with a fever, without the obstetric-specific escalation her condition demands. ACOG has not established a national standard requiring hospitals to implement postpartum-specific triage pathways in emergency departments. Without that standard, individual hospitals set their own protocols or none at all. The result is that the speed of care a postpartum woman receives in an emergency room depends largely on whether the triage nurse happens to know that the obstetric rules are different.

AI solution:

AI triage tools can identify postpartum status from registration data and immediately flag the patient for obstetric-specific assessment criteria. A patient who enters her recent delivery date at check-in should trigger an automated alert that modifies her triage pathway before she is ever seen by a nurse. Natural language processing tools can also scan electronic health record notes in real time, identifying language that suggests a clinician is not applying urgency appropriate to the presentation, and prompt a secondary review. Time-to-antibiotic is a measurable outcome. AI systems can track it continuously across an entire hospital system and surface outliers before the next death, not after.

3. Knowledge (10.1%)

Knowledge gaps contributed to roughly 1 in 10 identified factors. Some gaps were on the patient side: a woman who does not know that fever and rapid heart rate three days after delivery are warning signs cannot seek care she does not know she needs. But knowledge gaps also exist on the clinician side. The MMRCs found that clinicians in emergency department and outpatient settings need education on modified obstetric early warning signs.(1) A clinician who sees a postpartum patient in an urgent care clinic and does not apply obstetric-specific criteria is a knowledge gap at the system level.

Where hospitals and ACOG have failed:

ACOG publishes educational materials. It runs continuing medical education programs. But there is no mechanism ensuring that the emergency physician who sees a postpartum woman at day 10 has ever received training on obstetric sepsis recognition. Cross-departmental education, reaching emergency medicine, internal medicine, and urgent care, is not systematically required. Discharge instructions given to postpartum women vary by hospital, by clinician, and by shift. There is no federal or professional society standard mandating that every woman discharged after delivery receives written, plain-language information about infection warning signs and a clear instruction about when and where to seek care. That is a knowledge delivery failure at the institutional level.

AI solution:

AI can close the knowledge gap on both sides simultaneously. For patients, AI-powered postpartum apps can deliver daily check-ins after discharge, ask about symptoms, and trigger escalation pathways when warning signs are reported. The technology to build this exists and is not expensive. For clinicians, AI decision support tools can embed obstetric-specific guidance into the emergency medicine and urgent care workflow, surfacing postpartum sepsis criteria automatically when a patient’s recent delivery is noted in the chart. An AI that knows what a human clinician was never formally taught is not a workaround. It is what the system should have provided in the first place.

[PAYWALL BREAK]

4. Lack of Continuity of Care (9.6%)

Nearly 1 in 10 contributing factors involved a breakdown in continuity. A woman delivers at a hospital. She is discharged at 48 to 72 hours. Her next scheduled appointment is at six weeks. In between, she is alone with a newborn, healing from either a vaginal delivery or major abdominal surgery, navigating a body undergoing the most rapid physiologic change of her adult life. If she develops an infection at day five, there is no standard system designed to catch her. She may call her obstetrician’s office and be told to wait and see. She may go to an urgent care that cannot recognize postpartum sepsis. The failure is not any individual clinician’s wrong decision. The failure is that no connected system was designed to prevent that situation.

Where hospitals and ACOG have failed:

The six-week postpartum visit was the standard of care for generations despite no evidence that six weeks is the right interval for detecting postpartum complications. ACOG updated its guidance in 2018 to recommend earlier contact, ideally within three weeks, and a comprehensive visit by 12 weeks. That update was an improvement. It was not a solution. “Contact” can mean a phone call. It does not ensure that a woman with early infection signs is identified or that her care is coordinated across the obstetric, emergency, and primary care systems she may touch in the weeks after delivery. Hospitals have not built the infrastructure this coordination requires, and ACOG has not made that infrastructure a condition of quality.

AI solution:

AI-powered remote monitoring platforms can maintain active contact with postpartum women from the day of discharge through the first six weeks. Automated symptom check-ins by text, app, or voice can identify warning signs daily rather than waiting for a scheduled visit. When a woman reports fever, increasing pain, or malaise, an AI system can escalate immediately to a human clinician for follow-up, routing her to the appropriate level of care within minutes rather than days. This is not futuristic. Postpartum remote monitoring programs using these tools have already been piloted. The evidence supports their utility. What is missing is the institutional commitment to deploy them at scale and the professional society standard that would make them the expectation rather than the exception.

5. Lack of Access or Financial Resources (7.8%)

Access and financial barriers were cited in nearly 1 in 12 contributing factors. This is likely an undercount. Women who cannot access care are not always captured in committee reviews the same way deaths inside the health system are. But the deeper story here is not just about insurance gaps. It is about what happens when Medicaid pays obstetricians and hospitals at rates that are 30 to 50 percent below commercial insurance rates. Physicians and hospitals respond to that gap the same way any business responds to below-cost reimbursement: they limit exposure. The result is that the 40% or more of pregnant women in the United States who are on Medicaid, disproportionately Black, Hispanic, and rural women, face a two-tiered system in which their coverage exists on paper and their access exists in theory.

Where hospitals and ACOG have failed:

ACOG has advocated for Medicaid expansion and for extending postpartum coverage to 12 months. That advocacy is on the record and is appropriate.

What ACOG has not done is confront the reimbursement discrimination that makes Medicaid a second-class card in a first-class system. When obstetricians limit the number of Medicaid patients they will see, when hospitals close obstetric units in low-income communities because the margin does not pencil out, the professional society responsible for the standard of care has an obligation to say that this is not acceptable. It has not said that with the force the situation demands.

Universal healthcare coverage, or at minimum Medicaid reimbursement parity with commercial rates, is not a political position. It is a precondition for the word “preventable” to mean anything at all.

AI solution:

AI cannot fix a reimbursement structure that devalues the lives of low-income women. But it can reduce the cost of delivering care to underserved populations enough to change the math. AI-powered telehealth platforms dramatically lower the overhead of postpartum follow-up visits, making it economically feasible to see Medicaid patients at higher frequency without the facility costs of in-person care. AI tools that automate Medicaid enrollment verification, coverage extension applications, and connection to community health workers can reduce the administrative burden that drives clinicians away from Medicaid panels. The goal is to make caring for Medicaid patients less costly to deliver until the payment system catches up to what equity requires. That is a bridge strategy, not a solution. The solution is parity.

My Take

These five contributors, and the data behind them, are not a surprise to anyone who has followed maternal mortality review committee findings over the past decade. What they reveal is not a mystery. They reveal a system that has identified its failures in precise detail and has not restructured itself to fix them.

86.4% of pregnancy-related infection deaths are preventable. That figure should be on the wall of every labor and delivery unit in the country. It should drive quarterly quality reviews, accreditation standards, and professional accountability. It should inform how we train emergency physicians, how we design discharge instructions, how we structure postpartum follow-up, and how we deploy technology.

The AI solutions I have described are not hypothetical. The tools exist. Remote monitoring platforms, AI-powered triage alerts, clinical decision support for sepsis recognition, discharge risk screening, postpartum symptom apps: each of these is deployable today. What they require is the institutional will to deploy them and the professional society leadership to make them the standard rather than the experiment.

ACOG issues guidelines. Hospitals implement selectively. Women die preventably. That cycle has continued long enough. AI will not replace clinical skill, eliminate financial barriers by itself, or fix a broken triage system through algorithm alone. But AI can close the gaps that human systems, through inertia, underfunding, and inconsistent accountability, have refused to close themselves.

Patients are not passive in this. Ask your hospital what postpartum monitoring they provide between discharge and your first appointment. Ask whether your discharge instructions include specific infection warning signs. Ask whether your coverage continues after delivery. The answers will tell you more about your safety than any brochure.

Bottom Line

Eight in ten pregnancy-related infection deaths are preventable. Review committees in 29 states documented why they keep happening: clinical skill failures, treatment delays, knowledge gaps, disconnected postpartum care, and financial barriers that block access before infection can be treated. Hospitals have known these failure points for years. ACOG has documented them and stopped short of mandating the fixes. AI-powered tools, deployed at discharge, in triage, in remote monitoring, and in clinical decision support, can do what the current system has failed to do. The technology is ready. The question is whether the institutions responsible for women’s lives are ready to use it.

References

1. Joseph NT, Trost SL, Hollier LM, Perkins KM, Goodman DA, Leonard M, Busacker A. Pregnancy-related mortality due to infection: maternal mortality review committees in 29 U.S. states, 2017-2019. Obstet Gynecol. 2026. doi:10.1097/AOG.0000000000006172

2. Hoyert DL. Maternal mortality rates in the United States, 2024. NCHS Health E-Stats. 2026. Available from: https://www.cdc.gov/nchs/data/hestat/hestat113.htm

3. Hoyert DL. Maternal mortality rates in the United States, 2023. NCHS Health E-Stats. 2025. doi:10.15620/cdc/170564

Amos Grunebaum, MD | ObGyn Intelligence - Evidence Matters | obmd.com

Stylized image of hantavirus

Last week, while the MV Hondius was somewhere between St. Helena and Ascension Island, a 70-year-old Dutch passenger developed fever, headache, abdominal pain, and diarrhea. He died before reaching shore. His 69-year-old wife became ill on board and collapsed at O.R. Tambo International Airport in Johannesburg. She died there. A third passenger, a British national, tested positive for hantavirus. Three dead, six infected, one ship, one unusual pathogen.

The WHO is coordinating a multi-country response. The ship’s operator, Oceanwide Expeditions, has acknowledged the deaths while noting that hantavirus has not been definitively linked to all three. The investigation is ongoing.

Hantavirus is carried by rodents. It spreads when people inhale particles from dried droppings or urine. The Andes virus, found in South America, is the only strain known to spread person-to-person. The CDC has recorded 890 U.S. cases since surveillance began in 1993. This is not a common infection. Six cases on one ship is, in the words of a University of Michigan infectious disease specialist, something she had never heard of before.

I am not an infectious disease specialist. I am an obstetrician. But when I read this story, my first thought was not epidemiological. It was clinical.

My pregnant patients go on cruises. They travel to South America, sub-Saharan Africa, Southeast Asia. They clean mouse traps in their garage. They live in houses, not isolation chambers. And they carry a passenger whose immune relationship with the world has been fundamentally altered by pregnancy.

Pregnancy is not immunosuppression in the classical sense. It is immune modulation. The body performs a sophisticated tolerance trick to prevent rejection of a genetically foreign fetus, and that trick has consequences. Viral infections that cause mild illness in a non-pregnant adult can cause preterm labor, fetal loss, congenital anomalies, or maternal death in a pregnant patient. The virus does not change. The host does.

This is not a story about hantavirus specifically. It is a story about the full landscape of viruses that matter in obstetric care, and whether we are thinking about all of them every time we take a history, counsel a traveler, review immunization status, or manage a febrile patient in labor.

The answer, in my experience, is often no.

We are excellent at HIV. We screen universally, and our protocols for antiretroviral therapy and delivery management have reduced vertical transmission to under 1% in managed settings. We are good at hepatitis B because newborn immunization protocols and HBIG administration are embedded in delivery room practice. We think about HSV near term. We worry about varicella in the non-immune patient.

We are less systematic about the rest of the list.

CMV is the most common congenital infection in the world. It causes more permanent hearing loss and cognitive impairment in children than any other infectious agent. We do not screen for it universally in pregnancy. Most patients have never heard of it. Most of the public conversations about birth defects do not mention it. We counsel patients about cat litter and Listeria but not about the daycare worker sharing a cup of juice with a toddler who is shedding CMV in her saliva.

Parvovirus B19 causes hydrops fetalis. It is not rare. It circulates in schools and daycares. A school teacher or childcare provider who becomes infected in the second trimester faces the real possibility of fetal anemia severe enough to require intrauterine transfusion. The recognition window is narrow and the clinical picture in the mother is often unremarkable.

Zika is not gone. It is quieter. But the Aedes mosquito has not retired, and our patients still travel to endemic regions. Congenital Zika syndrome is one of the most devastating congenital infections documented in the modern era: microcephaly, cortical malformations, hearing loss, ocular defects. The counseling burden for a patient with a potential exposure and an ongoing pregnancy is substantial, and the evidence base for timing, testing, and surveillance is still not what it should be.

Hepatitis E deserves more attention in obstetric practice than it receives. In endemic regions, the case fatality rate for pregnant patients in the third trimester can exceed 25%. This is not a footnote in an ID textbook. It is a reason to take a careful travel and dietary history in every pregnant patient who presents with jaundice or hepatic dysfunction.

I have put together the table below as a working clinical reference. It is not exhaustive, and it is not a substitute for infectious disease consultation when you need one. But it is the list I wish I had seen as a resident. Every virus on it has documented maternal, fetal, or neonatal consequences. Every one of them has a potential interaction with pregnancy that changes management.

The table organizes them by category, summarizes the relevant maternal and fetal risks, and notes transmission routes and prevention strategies. I have included vaccines and interventions only where they are evidence-based, approved for use, or specifically recommended in or around pregnancy. I have not filled gaps with optimism.

A few observations from this table.

First, the vaccine column is shorter than it should be. We have effective vaccines against influenza, COVID-19, RSV, hepatitis A, hepatitis B, rubella, measles, mumps, varicella, HPV, polio, and rabies. Several of these are contraindicated during pregnancy (live vaccines) but should be given postpartum before the next conception. Others are specifically recommended in pregnancy. The prenatal visit is an immunization opportunity. We do not always use it as one.

Second, vertical transmission risk varies enormously within the table. For HIV without intervention, vertical transmission is 15 to 45 percent. For hepatitis B with HBeAg positivity and no prophylaxis, it approaches 90 percent. For CMV primary infection in the first trimester, the risk of congenital infection is approximately 30 to 40 percent, with a subset developing symptomatic disease. For rubella in the first trimester, the risk of congenital rubella syndrome exceeds 80 percent. These are not small numbers.

Third, the table contains several viruses that most practicing obstetricians will never encounter in clinical practice in the United States. LCMV, Lassa fever, Ebola. But global travel has made the world smaller. A patient who spent three weeks in West Africa visiting family, or who was on a cruise ship that stopped in South America, is a patient who belongs in front of an obstetrician with a complete viral differential. The geography of risk has changed. The training has not always kept pace.

The hantavirus cluster on the MV Hondius was unusual. But it reminded me of something that does not require a cruise ship or a rare outbreak to be true: the pregnant patient is a uniquely vulnerable host, and the viruses that threaten her are not limited to the ones on the standard prenatal panel.

My Take

The prenatal visit is one of the most intensive scheduled contacts between a patient and the healthcare system. We draw blood, check blood pressure, measure fundal height, review medications. We do not routinely ask about rodents.

That is not a criticism. You cannot ask about everything. But the viral risk landscape in pregnancy is broad, and the standard first prenatal visit template does not capture most of it. Travel history, occupational exposures, household contacts, immunization history, sexual history — these are the vectors that bring most of these viruses into the obstetric encounter. A teacher in a classroom full of young children is in a different CMV and parvovirus risk category than a remote worker who leaves the house twice a week. A patient who just returned from a Zika-endemic country is in a different conversation than one who spent her vacation in Maine.

We collect the information we are trained to collect. This table is an argument for expanding the frame.

The pregnant patient does not exist inside an infectious disease specialty line. Viruses do not check credentials at the door. The obstetrician who sees a febrile patient in the third trimester should be comfortable thinking across this entire table, not just the pathogens covered in a standard infectious disease in pregnancy lecture from 1995.

Three people died on a ship in the Atlantic from something carried by rodents, spread by breath, and diagnosed in a laboratory in South Africa while the vessel was off the coast of Cape Verde. It took a lot of geography to get to a simple conclusion: the world is smaller than our specialty silos.

If this post is useful, forward it to a colleague or a resident. If something on the table is wrong or missing, tell me. I update these references when the evidence changes.

Subscribe to ObGyn Intelligence for evidence-based commentary on women’s health every week — no sponsored content, no wellness industry partnerships, no hedging when the data is clear.

Selected References

1. Petri AE, Albeck-Ripka L. 3 Dead of Suspected Hantavirus Infections on Cruise Ship, W.H.O. Says. New York Times. May 3, 2026.

2. Centers for Disease Control and Prevention. Hantavirus Disease Cases Reported in the United States, by Year Reported, 1993-2023. Atlanta: CDC; 2024.

3. Silasi M, Cardenas I, Kwon JY, Racicot K, Aldo P, Mor G. Viral infections during pregnancy. Am J Reprod Immunol. 2015;73(3):199-213.

4. Swamy GK, Heine RP. Vaccinations for pregnant women. Obstet Gynecol. 2015;125(1):212-226.

5. Rawlinson WD, Boppana SB, Fowler KB, et al. Congenital cytomegalovirus infection in pregnancy and the neonate: consensus recommendations for prevention, diagnosis, and therapy. Lancet Infect Dis. 2017;17(6):e177-e188.

6. Mor G, Cardenas I. The immune system in pregnancy: a unique complexity. Am J Reprod Immunol. 2010;63(6):425-433.

7. Brasil P, Pereira JP Jr, Moreira ME, et al. Zika Virus Infection in Pregnant Women in Rio de Janeiro. N Engl J Med. 2016;375(24):2321-2334.

8. Khuroo MS, Kamili S. Aetiology, clinical course and outcome of sporadic acute viral hepatitis in pregnancy. J Viral Hepat. 2003;10(1):61-69.

9. CDC. Recommended Adult Immunization Schedule for Ages 19 Years or Older, United States, 2024. MMWR Recomm Rep. 2024.

10. WHO. Hantavirus Disease — Multi-country Event. Disease Outbreak News. May 4, 2026.

What the Word ‘Bias’ Actually Means

The word bias comes from the Old French biais, meaning a slant, a slope, a diagonal cut across the grain of cloth. Like a floor that is not quite level: everything placed on it rolls the same way, not because anyone pushed it, but because the floor was built wrong.

When a tailor cuts fabric “on the bias”, the cut runs …

Read more

Peter Drucker the business guru never attended a delivery. But he understood institutions better than most people who run them. His warning, issued decades ago, applies to American obstetrics with uncomfortable precision: if you want something new, you have to stop doing something old.

We are not short of new things. New protocols. New screening tools. New committee recommendations. New quality improvement initiatives. What we are short of is the discipline to ask which old things are not working, and the institutional courage to stop them.

The numbers demand that conversation now.

What the Numbers Show

The United States spends more on maternity care than any country in the world. The return on that spending is, by any honest measure, poor.

The U.S. maternal mortality ratio is approximately 23 deaths per 100,000 live births.

The United Kingdom, with its MBRRACE-UK surveillance system and rigorously evidence-anchored NICE guidelines, reports a ratio near 9 per 100,000. (1,2) That is not a rounding error. It is a structural failure.

Subscribe now

These are not mortality rates from the same distribution shifted slightly. They represent different systems producing different outcomes. The U.S. figure has not fallen in decades. The UK figure, while still unacceptably high, reflects a national system that reviews every maternal death, publishes its findings transparently, and asks directly: what should we have done differently?

We have reviewed our outcomes too. The difference is what happens next.

What We Keep Adding

The American response to poor maternal outcomes has been, almost without exception, additive.

More screening.

More documentation.

More checklists.

More bundles. More task forces.

More language in guidelines telling clinicians to “consider” and “offer” and “discuss” interventions whose evidence base ranges from solid to speculative.

And now. More Doulas.

ACOG guidelines, across twelve domains scored in my ongoing GAAP analysis, average 1.96 citations per clinical recommendation and achieve evidence-action ratios of 46 percent, meaning fewer than half of their recommendations are fully matched to the evidence they cite. (3) NICE guidelines average 0.99 citations per recommendation and achieve evidence-action ratios of 68 percent. (3) This is not a criticism of individual physicians or guideline authors. It is an observation about a system that has become comfortable with expansion and uncomfortable with subtraction.

We add smoking cessation counseling to prenatal visits without removing the parts of those visits that have never been shown to improve outcomes.

We add implicit bias training without examining which institutional practices produce the disparities we are trying to address.

We add maternal safety bundles without asking whether the baseline care into which those bundles are inserted is itself optimized.

We now add doulas without evidence that they effect outcomes.

Drucker’s insight was not about innovation. It was about capacity. Every organization has finite attention, finite time, and finite resources. When you add without subtracting, you do not improve the old thing or establish the new one. You dilute both.

What the UK Stopped

The MBRRACE-UK programme, which has surveilled UK maternal deaths continuously since 1952, is not primarily a counting exercise. It is a stopping mechanism. Each triennial report identifies care that was suboptimal, names the patterns, and gives clinicians and institutions the data they need to discontinue practices that are not protecting women. (2)

NICE guidelines, by contrast with ACOG’s, are notable for what they do not include. They do not recommend interventions without adequate evidence. They do not use the phrase “reasonable to offer” as a placeholder for clinical uncertainty. When evidence is insufficient, NICE says so and waits. (4)

Subscribe now

That restraint is itself a policy decision. It reflects the understanding that recommending something you cannot support with evidence does not empower clinicians. It confuses them. And it adds to the pile of things clinicians are expected to do in a visit that already cannot hold everything it is asked to carry.

What Needs to Stop Here

I am not suggesting we dismantle American obstetrics. (Or maybe it’s not such a bad idea?)

I am suggesting we apply Drucker’s test, seriously and systematically, to what we are currently doing.

Which prenatal screening interventions improve outcomes when broadly applied, and which generate anxiety, follow-up visits, and additional cost without changing what happens to the mother or the baby? Which elements of postpartum care protocols are delivered as ritual rather than as evidence-based intervention? Which guideline recommendations are carried forward from one edition to the next because no one has formally asked whether they should be retired?

The discipline of stopping is harder than the discipline of starting. Starting feels like progress. Stopping feels like defeat, or like admitting that something we did for years did not work. In medicine, that admission is especially uncomfortable because it implies that women who did not benefit from those years of practice were owed something different.

They were. Saying so is not a condemnation of the physicians who followed the guidelines. It is the precondition for building something better.

Adding ‘Racism’ Without a Mechanism Is Not an Explanation

Racial disparities in maternal mortality are real, well-documented, and morally unacceptable. Black women in the United States die from pregnancy-related causes at approximately three times the rate of white women. (5) That disparity demands serious investigation and serious response. It does not demand that we accept every proposed explanation as equivalent, or every proposed remedy as effective.

In recent years, “racism” has been added to the list of maternal mortality causes in a way that functions more as a statement of values than as an operational hypothesis. The claim that racism causes maternal death is not wrong as a broad social observation. The problem is that naming it without specifying the mechanism, the point of clinical intervention, or the measurable outcome produces nothing actionable. It adds a category without subtracting confusion.

The relevant questions are specific ones. Does implicit bias in triage decisions delay recognition of hemorrhage? Do communication failures between patients and clinicians reflect power differentials that can be structurally addressed? Are Black women with hypertensive disorders less likely to receive timely antihypertensive therapy, and if so, at what step in the care pathway does that failure occur? (6) These questions have testable answers. Programs built around them can be evaluated. Programs built around the general premise that racism is the cause cannot be, and when they cannot be evaluated, they cannot be stopped when they fail.

The same Drucker test applies here.

Adding “anti-racism training” to an already overcrowded institutional agenda, without a specified mechanism linking that training to a measurable reduction in maternal deaths among Black women, is addition without evidence. It may make institutions feel they are responding. It does not make them respond.

Doulas Are Not a Mortality Intervention

Doulas provide genuine value within the scope of what they are trained to do. Continuous labor support is associated with shorter labors, lower rates of cesarean delivery, and higher patient satisfaction. (7) Women who want a doula and can access one are better served with one than without one. That is a real finding and it should not be dismissed.

But doulas are not trained to recognize hemorrhage. They are not trained to manage hypertensive emergencies. They cannot interpret a deteriorating fetal heart rate tracing, administer magnesium sulfate, place a uterine balloon, or perform a hysterectomy for placenta accreta. These are not gaps that advocacy can close. They are the direct, proximate causes of maternal death in the United States: hemorrhage, hypertensive disorders, sepsis, thromboembolism, and cardiomyopathy. (8)

Positioning doulas as a maternal mortality intervention is a category error.

It confuses emotional and advocacy support, which doulas provide well, with clinical recognition and clinical response, which only trained clinicians can provide. The conditions that kill women require timely diagnosis and timely treatment. A doula can insist that a nurse check on her patient. She cannot do what happens after the nurse arrives.

The countries with much lower mortality rate have no doulas.

The category error reflects poorly on the policymakers making the argument, not on the doulas themselves. Doulas did not ask to be the answer to a 23-per-100,000 mortality rate. They are being handed that responsibility by legislators and advocates who find it easier to fund a new support role than to fix the clinical system failures that are actually killing women. Expanding Medicaid coverage for doulas is a political achievement. It is not a mortality intervention. Calling it one misrepresents the evidence, misdirects resources, and, when the mortality numbers fail to move, produces the false conclusion that we tried and the problem is intractable.

The problem is not intractable. The interventions that reduce maternal mortality are known: standardized hemorrhage protocols, timely antihypertensive treatment, early warning systems, mandatory case review. These require institutional commitment and clinical accountability. They do not have a constituency as warm and sympathetic as doulas. That is a political fact, not an evidentiary one, and we should not let it determine where the resources go.

My Take

The U.S. maternal mortality rate will not improve through addition alone. We have been adding for decades. The gap between our outcomes and those of comparable countries has not closed. It has, in some analyses, widened.

What we need is an honest inventory: what are we doing, what does the evidence say about each of those things, and what should we stop. That is not a political position. It is a clinical one. Drucker understood it as a management principle. MBRRACE understands it as a surveillance imperative. We should understand it as a professional obligation.

Racial disparities in maternal mortality are a genuine emergency. They deserve interventions proportional to that emergency: specific, mechanistic, measurable, and willing to be evaluated. Naming racism without specifying a clinical pathway is not that. Funding doulas without evidence they reduce mortality is not that. Both can coexist with the harder work of fixing the clinical system failures that are actually killing women, but only if we are honest about what each intervention can and cannot do.

The word “consent” does not appear in a single one of the twelve ACOG guidelines I have scored in this series. That is not a minor omission. It is a signal about whose interests those guidelines are organized around. Stopping the practices that prioritize institutional comfort over patient outcomes is exactly where this inventory should begin.

If you find this analysis useful, consider subscribing to ObGyn Intelligence. Evidence matters. So does acting on it.

References

1. Hoyert DL. Maternal mortality rates in the United States, 2021. NCHS Health E-Stats. 2023. [VERIFY: confirm most recent NCHS data year and rate]

2. Knight M, Bunch K, Patel R, et al. MBRRACE-UK: Saving Lives, Improving Mothers’ Care. National Perinatal Epidemiology Unit, University of Oxford; 2023. [VERIFY: confirm most recent MBRRACE triennial report citation]

3. Grunebaum A. GAAP series: Guideline Accountability and Action-to-Evidence analysis, Posts 1-11. ObGyn Intelligence, obmd.com. 2024-2025.

4. National Institute for Health and Care Excellence. Evidence standards framework for digital health technologies. NICE; 2022. [VERIFY: confirm specific NICE methodology document for guideline restraint]

5. Hoyert DL, Miniño AM. Maternal mortality in the United States: changes in coding, publication, and data release. Natl Vital Stat Rep. 2020;69(2):1-18. [VERIFY: confirm most current race-stratified maternal mortality data citation]

6. Shields LE, Wiesner S, Klein C, Pelletreau B, Hedriana HL. Use of maternal early warning trigger tool reduces maternal morbidity. Am J Obstet Gynecol. 2016;214(4):527.e1-6. [VERIFY: confirm best available citation for race-based disparities in triage/treatment delay]

7. Bohren MA, Hofmeyr GJ, Sakala C, Fukuzawa RK, Cuthbert A. Continuous support for women during childbirth. Cochrane Database Syst Rev. 2017;7:CD003766. [VERIFY: confirm most recent Cochrane update on continuous labor support]

8. CDC Division of Reproductive Health. Pregnancy mortality surveillance system: causes of pregnancy-related deaths. Atlanta: CDC; 2023. [VERIFY: confirm most recent PMSS data on leading causes]

They are right about that.

They also blur the line between coverage, access, and quality, and they cannot decide whether race is a social construct or an analytic category.

Two papers landed in the same issue of Obstetrics & Gynecology, both arguing that policy and structure drive severe maternal morbidity.

One is a Medicaid claims analysis of nearly seven million deliveries (1). The other is a clinical perspective on inequalities in high-income countries (2).

Read together, they are presented as a coherent case for expanding insurance, addressing structural racism, and reorganizing health systems around equity. Read carefully, they reveal a set of unresolved contradictions that the authors do not name and most readers will not catch.

The underlying question is serious.

American women are dying at rates that the rest of the high-income world does not tolerate, and the burden falls hardest on the women with the least power to push back. I support universal coverage. I support structural action on the social determinants of health. The criticism that follows is not aimed at those goals. It is aimed at the looseness with which these two papers conflate coverage, access, and quality, and the way the inequalities paper builds an argument on racial categories it has just told us are not real.

The Race Problem the Authors Create and Then Ignore

Vousden and colleagues open with a definition. Race is “a group of people connected by common descent or origin.” Ethnicity is “membership of a group, ultimately of common descent or having common national or cultural tradition.” Inequalities, they write, are “neither natural nor biologically determined.” Race, in other words, is a social category without biological grounding.

And then for the rest of the paper, they categorize, count, stratify, and report by race. Go figure.

Black women in the UK have a 2.3 times higher risk of maternal death than White women. Black women in the US have three to four times the risk. Black African and Bangladeshi women in the UK have the highest rates of severe maternal morbidity.

These numbers appear throughout the paper as if the categories doing the counting are stable, meaningful, and comparable across the Atlantic. They are not.

“Black” in the United States is not the same population as “Black” in the United Kingdom, which is not the same population as “Black African” in France.

“Hispanic” in a US dataset includes women whose ancestors arrived 400 years ago and women who arrived last week, from twenty different countries with very different health profiles.

The paper itself acknowledges this when it points out that migrant women from sub-Saharan Africa, the Caribbean, and parts of Asia carry higher risk than other migrants.

That is the right observation. It also undermines the racial categories the rest of the paper depends on.

The authors cannot have it both ways.

Either race is a coherent enough category to drive a paper full of disparity statistics, or it is so socially constructed and context-dependent that the disparity statistics need a different framing. The honest position is the second one. The paper does not take it.

This matters at the bedside. When a woman walks into Labor and Delivery, what we want to know is her actual risk profile, which includes obesity, hypertension, prior pregnancy outcomes, access to prenatal care, language barriers, housing stability, and trust in the health system. Race is a crude proxy for some of these and an irrelevant proxy for others. Treating it as a unified risk factor produces both undertreatment when a White woman with the same social vulnerabilities is missed, and overgeneralization when a Black woman with abundant resources is treated as high-risk on category alone.

What the Medicaid Paper Actually Shows

Guernsey and colleagues report that in 30 states that expanded Medicaid under the Affordable Care Act, women who delivered at least 21 months after expansion had lower odds of severe maternal morbidity than women who delivered before expansion (odds ratio 0.79, 95 percent CI 0.68 to 0.90 with transfusion, 0.76, 0.65 to 0.88 without) (1). The absolute risk reduction was 0.5 percent with transfusion and 0.3 percent without. The number needed to treat was 196 to prevent one case of severe morbidity including transfusion, and 311 without.

Subscribe now

That is a real signal in a very large dataset. It is also a smaller and more specific signal than the framing suggests.

First, the 9-month lag did not produce a statistically significant effect in the changepoint model. Only the 21-month lag did. The authors interpret this as evidence that pre-pregnancy and inter-pregnancy care matter. That interpretation is reasonable. It is also the only interpretation that supports their hypothesis. A different reading is that whatever Medicaid expansion is doing, it is doing it through care before conception, not through prenatal or intrapartum care, which is the period most directly relevant to severe maternal morbidity.

Second, an earlier study by Chatterji and colleagues, using Healthcare Cost and Utilization Project data combined with birth certificates, found no effect of Medicaid expansion on severe maternal morbidity at all. The current paper handles this disagreement by pointing out that birth certificates underreport morbidity and do not reliably identify Medicaid coverage. Both points are valid. They also do not resolve the fact that two large analyses of overlapping populations reached opposite conclusions, which should make any reader cautious before declaring a settled finding.

Third, the paper excluded Maryland because the data were anomalous. That is defensible. It also illustrates how fragile state-level Medicaid claims data can be.

None of this argues against expanding coverage. It argues against treating a 0.3 to 0.5 percent absolute risk reduction in one analysis, contradicted by another, as evidence that the structural debate is settled.

The rest of this post is for paid subscribers.

Read more

The paper focuses on neurodivergent pregnant women, including those with autism, ADHD, sensory processing differences, learning disorders, developmental coordination disorder, or Tourette syndrome. Its central point is simple: the goal is not to diagnose neurodivergence in the obstetric office. The goal is to identify how a patient receives information, processes stress, tolerates touch, and participates in time-sensitive decisions.

The paper emphasizes that pregnancy and labor are sensory-intensive experiences. Fetal monitoring, cervical exams, venipuncture, ultrasound, alarms, bright lights, repeated touch, urgent explanations, and unfamiliar staff can overwhelm patients whose processing needs are not recognized. What may look like anxiety, refusal, distrust, “noncooperation,” or poor motivation may instead reflect a mismatch between standard obstetric communication and the patient’s processing style.

The proposed solution is practical. Clinicians should ask early about communication preferences, written versus verbal instructions, sensory triggers, processing time, warning before touch, and the role of a support person.

These needs should be documented in a brief communication care plan, visible to the labor and delivery team, and included in handoffs. During labor, clinicians should use plain language, give one instruction at a time, allow processing time, warn before examinations, reduce unnecessary stimulation when safe, involve the support person, and use teach-back to confirm understanding.

This approach is especially important during urgent intrapartum decisions, when complex explanations may delay consent or worsen distress. In emergencies, the paper recommends direct, concrete statements: problem, action, reason. Details can be reinforced afterward with written summaries.

The evidence base remains limited and is drawn largely from qualitative studies and patient-reported experiences rather than randomized obstetric outcome trials.

Still, the clinical logic is strong. Better communication is not a separate program. It is basic obstetric safety adapted to patients whose needs have too often been missed.

A care gap is not a lack of knowledge. It is a failure to apply what we already know, consistently, to the patient in front of us.

A woman has preeclampsia. She delivers. She is discharged. Six weeks later, she is told she looks well. Years later, she presents with advanced kidney disease. No one made an obvious mistake. The system performed exactly as designed. That is the problem.

The evidence is not unclear. Pregnancy complications such as preeclampsia are long-term risk markers for chronic disease, including kidney disease. Screening exists. It is simple. It is inexpensive. It is not being done. This is not a knowledge gap. It is a reliability failure.

We rely on memory. That is unsafe.

Clinicians are busy, interrupted, and managing competing priorities. Even excellent clinicians will not reliably connect a pregnancy complication from ten years ago to a silent long-term risk today. That is not negligence. It is a structural limitation.

AI changes this immediately.

Not by replacing clinicians. By enforcing consistency where humans cannot.

AI does what guidelines cannot do on their own. It operationalizes them.

It identifies patients with prior preeclampsia from the record. It keeps that risk visible across time. It prompts the clinician at the point of care. It links that prompt to the correct tests. It does this every time, for every patient, without fatigue.

This is not innovation. It is basic systems engineering applied to medicine.

If a system allows a known 5- to 9-fold risk signal to disappear after discharge, that system is defective.

What implementation looks like now and where patients can help themselves:

The rest of this post is for paid subscribers.

Read more

The United States and Germany both practice advanced medicine. Yet the organization of care, the role of physicians, and the structure of prenatal services reveal two very different medical cultures.

At first glance, medicine in the United States and Germany looks remarkably similar. Both countries train highly skilled physicians, rely on modern hospitals, and practice evidence-based medicine. Yet beneath that shared scientific foundation lies a system shaped by very different structures, professional roles, and expectations about how care should be delivered.

Even the language of medicine reflects the difference. In the United States physicians in training are residents, supervised by attendings.

In Germany they are Assistenzärzte, supervised by Fachärzte or Oberärzte, with department leaders called Chefärzte.

American hospitals speak of labor and delivery units, emergency departments, and attendings.

German hospitals refer to Kreißsäle, Notaufnahmen, and Dienstärzte. The terminology signals different professional hierarchies and different traditions in how authority is structured within hospitals.

Prenatal care also begins in different places.

In Germany most pregnant women receive routine prenatal care from community-based office obstetricians or gynecologists (Frauenärzte). These physicians typically operate in private outpatient practices and follow standardized national prenatal care schedules. Insurance coverage is nearly universal through statutory health insurance or private insurance, so access to prenatal visits, ultrasounds, and laboratory testing is rarely limited by coverage status.

All patients in Germany can see a doctor in her practice

In the United States the situation is more fragmented. Prenatal care depends heavily on insurance status. Some pregnant women receive care through private insurance plans with broad access to specialists and imaging. Others rely on Medicaid, which finances a large share of births but varies by state in provider participation and reimbursement.

There is rarely a private physician in the US seeing a Medicaid patient in her practice

A smaller group of women begins pregnancy without insurance and may delay care until Medicaid eligibility is established or until they reach hospital systems that provide safety-net services.

Insurance also influences where women give birth in the United States.

Some hospitals predominantly serve privately insured patients, while others function as safety-net institutions caring for large Medicaid or uninsured populations. As a result, the distribution of obstetric patients across hospitals often mirrors the structure of the insurance system itself.

Germany operates differently.

Nearly all residents are insured through a universal system of statutory health insurance funds. Hospitals generally care for patients regardless of insurance fund membership, and pregnant women are usually directed to hospitals based on geography, physician referral, or patient preference rather than insurance status.

Hospital labor care reflects additional differences. In Germany, as in much of Europe, midwives play a central role in labor management. Physicians are present for complications, operative deliveries, and surgical care, but routine labor is frequently managed by midwives. German hospitals also commonly provide extended postpartum inpatient stays, historically several days after delivery.

In the United States obstetric care is typically organized around physician-led teams supported by labor nurses, anesthesiologists, and neonatal specialists. Postpartum stays tend to be shorter, and hospital throughput pressures are greater.

These structural differences occur alongside differences in national outcomes. Maternal mortality is substantially higher in the United States than in Germany. Recent national statistics report maternal mortality ratios in the United States of roughly 20 to 30 deaths per 100,000 live births, depending on the year and methodology, while Germany reports approximately 3 to 7 deaths per 100,000 births. Neonatal mortality is also somewhat higher in the United States, although the difference is smaller.

Interpreting these differences is complex. Maternal mortality reflects not only hospital care but also population health factors such as chronic disease, obesity, maternal age, access to prenatal care, and social determinants of health. Differences in how deaths are reported and classified may also influence comparisons between countries.

Both systems therefore show strengths and tensions.

Germany offers near universal coverage, strong outpatient prenatal care networks, and relatively consistent access to maternity services.

The United States offers rapid access to advanced subspecialty care and technological innovation, but access to routine prenatal services can vary depending on insurance coverage and regional resources.

The deeper difference is philosophical. German medicine developed within a regulated insurance framework designed to guarantee coverage for the entire population. American medicine evolved through a complex mix of private insurance, employer-based coverage, public programs such as Medicaid and Medicare, and hospital-based care systems.

These historical choices still shape clinical practice today.

Spend time in a German maternity clinic and then walk through an American labor unit. The science of obstetrics is the same. The textbooks are the same.

But the organization of care feels different. And outcomes are very different. More than fives times more women die in the US in and after pregnancy.

Sometimes profoundly so.

Medicine in the United States and the United Kingdom appears similar on the surface. Both countries train highly skilled physicians, rely on scientific evidence, and care for patients within advanced hospital systems. Yet beneath that shared vocabulary lies a striking cultural divide.

Much like the linguistic differences between American and British English, the practice of medicine in the two countries reflects very different assumptions about authority, responsibility, and the role of the physician.

Even the language of medicine reveals the divide.

In the United States, a physician in training is called a resident, and a fully independent physician is an attending.

In the United Kingdom, since 2024, the term “resident doctor” is used for all doctors in postgraduate training, including both foundation doctors and specialty trainees, while the fully trained physician is called a consultant, equivalent to a US attending. Despite the shared term, a UK “resident doctor” spans a broader range of training stages than a US resident and is not a direct one-to-one equivalent.

An American patient goes to the emergency department, while in Britain the same patient goes to A&E. These differences may seem cosmetic, but they reflect different professional hierarchies and expectations about who ultimately carries responsibility for decisions.

The differences become even clearer on the hospital floor. In the United States obstetric care is typically delivered by a team that includes physicians, labor nurses, anesthesiologists, and neonatal specialists. Nurses play a central role during labor, continuously monitoring patients and assisting physicians.

In many British maternity units the structure is different. Midwives are the primary professionals managing labor, often working independently, and physicians such as registrars or consultants are called when complications arise.

In general, physicians in British obstetric units do not have dedicated labor nurses assisting them in the same way American obstetricians do.

The contrast begins even earlier, during prenatal care. In Britain nearly all pregnant women receive care through the National Health Service. Prenatal visits, laboratory tests, ultrasound examinations, and delivery care are covered within a unified national system. Patients typically follow standardized care pathways coordinated by midwives and hospital-based obstetric services.

In the United States prenatal care depends heavily on insurance status. Some pregnant women receive care through private insurance plans, often with relatively broad access to specialists and imaging. Others rely on Medicaid, which finances a large share of births in the United States but varies widely by state in provider participation and coverage policies.

A smaller but important group of women begins pregnancy with no insurance at all, sometimes delaying prenatal care until Medicaid eligibility is established or until they present to hospital systems that provide safety-net services.

Subscribe now

This difference shapes the experience of pregnancy. In Britain the question is rarely whether prenatal care will be covered. In the United States the question often becomes where that care will occur, which clinicians accept the insurance plan, and whether administrative barriers delay access to services.

The most obvious difference between the two systems remains structural. British medicine operates largely through the National Health Service. Physicians function inside a national system where access, resources, and clinical pathways are heavily standardized. American medicine developed in a more decentralized environment. Hospitals, insurers, and physician groups interact in a complex marketplace rather than within a single national framework.

This difference shapes clinical behavior. In the United Kingdom care is often organized around system stewardship. Guidelines and care pathways frequently determine what happens next.

In the United States physicians historically retained more individual authority in clinical decision making, even as administrative oversight and insurance constraints continue to grow.

The contrast is especially visible in obstetrics. American obstetrics traditionally emphasizes physician responsibility for individual outcomes. A clinician managing labor often carries personal legal and professional accountability for decisions made in that room. In the United Kingdom responsibility is more distributed across teams and systems of care, including a stronger institutional role for midwifery services.

Communication styles also diverge.

British medical culture tends to favor understatement, indirectness, and institutional language. American medicine often communicates more explicitly about risk, intervention, and individual decision making.

These differences can influence how clinicians frame uncertainty, how patients perceive autonomy, and how professional authority is exercised.

None of this means one system is inherently superior. Each reflects the history, law, and culture that produced it. British medicine grew inside a national health service designed after World War II to guarantee universal access. American medicine developed through a patchwork of private practice, academic centers, and insurance markets.

Yet the deeper question is philosophical. What does society expect a physician to be?

In Britain the physician often functions as a steward of public resources within a coordinated national service. In the United States the physician historically acted as an independent professional responsible primarily to the patient in front of them.

That difference still shapes attitudes toward guidelines, innovation, and clinical autonomy.

The irony is that both systems are changing. British physicians increasingly face workforce shortages and resource constraints within the NHS. American physicians increasingly practice within large health systems where administrative rules influence clinical choices.

In other words, the two traditions may slowly be converging.

Still, the cultural differences remain unmistakable. Spend time in a British hospital ward and then walk through an American labor unit. The language is the same. The textbooks are the same. The science is the same.

But the practice of medicine feels different.

Sometimes profoundly so.

LinkedIn tagline:
Two countries. Same science. Very different cultures of obstetric care.

Hashtags:
#Obstetrics #MedicalEthics #NHS #USHealthcare #HealthSystems #ClinicalResponsibility #ObstetricIntelligence

16:9 Image Prompt:
Split image of two maternity care settings. Left side shows a modern American labor and delivery unit with obstetricians and nurses reviewing fetal monitoring. Right side shows a British NHS maternity ward where midwives manage labor while a consultant obstetrician reviews a chart. Subtle visual cues of the US and UK flags in background lighting, clean professional hospital environment, editorial illustration style, soft natural light.

and add a couple sentences about division of care by insurances for hospitals too

Two Nations Divided by a Common Language. And Sometimes by a Health System.

Subtitle: The United States and the United Kingdom both practice modern medicine. Yet their cultures of care, responsibility, and decision making often feel like two professions separated by the same language.

Series: The Obstetric Intellect
Where ideas, evidence, and ethics meet to challenge assumptions in obstetrics.

Medicine in the United States and the United Kingdom appears similar on the surface. Both countries train highly skilled physicians, rely on scientific evidence, and care for patients within advanced hospital systems. Yet beneath that shared vocabulary lies a striking cultural divide. Much like the linguistic differences between American and British English, the practice of medicine in the two countries reflects very different assumptions about authority, responsibility, and the role of the physician.

Even the language of medicine reveals the divide. In the United States a young physician is a resident. In Britain the equivalent doctor is a registrar or senior house officer, and the senior physician is called a consultant, rather than an attending. An American patient goes to the emergency department, while in Britain the same patient goes to A&E. These differences may seem cosmetic, but they reflect different professional hierarchies and expectations about who ultimately carries responsibility for decisions.

The differences become even clearer on the hospital floor. In the United States obstetric care is typically delivered by a team that includes physicians, labor nurses, anesthesiologists, and neonatal specialists. Nurses play a central role during labor, continuously monitoring patients and assisting physicians. In many British maternity units the structure is different. Midwives are the primary professionals managing labor, often working independently, and physicians such as registrars or consultants are called when complications arise. In general, physicians in British obstetric units do not have dedicated labor nurses assisting them in the same way American obstetricians do.

The contrast begins even earlier, during prenatal care. In Britain nearly all pregnant women receive care through the National Health Service. Prenatal visits, laboratory tests, ultrasound examinations, and delivery care are covered within a unified national system. Patients typically follow standardized care pathways coordinated by midwives and hospital-based obstetric services.

In the United States prenatal care depends heavily on insurance status. Some pregnant women receive care through private insurance plans, often with relatively broad access to specialists and imaging. Others rely on Medicaid, which finances a large share of births in the United States but varies widely by state in provider participation and coverage policies. A smaller but important group of women begins pregnancy with no insurance at all, sometimes delaying prenatal care until Medicaid eligibility is established or until they present to hospital systems that provide safety-net services.

Insurance also shapes where women give birth. In the United States hospitals often have different patient mixes depending on the insurance coverage they accept. Some hospitals predominantly serve privately insured patients, while others function as safety-net institutions caring for large Medicaid or uninsured populations. As a result, the distribution of obstetric patients across hospitals can mirror the structure of the insurance system itself.

In Britain such financial sorting rarely occurs. Because the NHS finances maternity care nationally, pregnant women are generally directed to hospitals based primarily on geography and service capacity rather than insurance status.

The most obvious difference between the two systems remains structural. British medicine operates largely through the National Health Service. Physicians function inside a national system where access, resources, and clinical pathways are heavily standardized. American medicine developed in a more decentralized environment. Hospitals, insurers, and physician groups interact in a complex marketplace rather than within a single national framework.

This difference shapes clinical behavior. In the United Kingdom care is often organized around system stewardship. Guidelines and care pathways frequently determine what happens next. In the United States physicians historically retained more individual authority in clinical decision making, even as administrative oversight and insurance constraints continue to grow.

The contrast is especially visible in obstetrics. American obstetrics traditionally emphasizes physician responsibility for individual outcomes. A clinician managing labor often carries personal legal and professional accountability for decisions made in that room. In the United Kingdom responsibility is more distributed across teams and systems of care, including a stronger institutional role for midwifery services.

Communication styles also diverge. British medical culture tends to favor understatement, indirectness, and institutional language. American medicine often communicates more explicitly about risk, intervention, and individual decision making. These differences can influence how clinicians frame uncertainty, how patients perceive autonomy, and how professional authority is exercised.

None of this means one system is inherently superior. Each reflects the history, law, and culture that produced it. British medicine grew inside a national health service designed after World War II to guarantee universal access. American medicine developed through a patchwork of private practice, academic centers, and insurance markets.

Yet the deeper question is philosophical. What does society expect a physician to be?

In Britain the physician often functions as a steward of public resources within a coordinated national service. In the United States the physician historically acted as an independent professional responsible primarily to the patient in front of them.

That difference still shapes attitudes toward guidelines, innovation, and clinical autonomy.

The irony is that both systems are changing. British physicians increasingly face workforce shortages and resource constraints within the NHS. American physicians increasingly practice within large health systems where administrative rules influence clinical choices.

In other words, the two traditions may slowly be converging.

Still, the cultural differences remain unmistakable. Spend time in a British hospital ward and then walk through an American labor unit. The language is the same. The textbooks are the same. The science is the same.

But the practice of medicine feels different.

Sometimes profoundly so.