When “Guess the Diagnosis” Meets AI: The End of Educational Guesswork
What happens when an AI can not only identify fetal achondroplasia, but also explain exactly why—and what to do next?
The Society for Maternal-Fetal Medicine (SMFM) regularly posts an “Ultrasound Case of the Week Challenge.” It’s meant to sharpen our diagnostic instincts and celebrate the art of pattern recognition.
But the exercise now has a rival: artificial intelligence that can see what we see—and explain it better.
The Case (as posted by the Society of Maternal-Fetal Medicine - SMFM)
Case Summary:
A patient is referred to Maternal-Fetal Medicine at 32 weeks’ gestation because of ultrasound findings of short long bones. On detailed scan, you confirm:
Shortened limbs with mild femoral bowing
Normal ossification
No evidence of fractures
Amniotic fluid index (AFI): 29 cm (polyhydramnios)
No other structural anomalies noted
Question: Based on these findings, what is the most likely diagnosis?
Options:
A. Thanatophoric dysplasia
B. Achondroplasia
C. Osteogenesis imperfecta
D. Campomelic dysplasia
E. Diastrophic dysplasia
Correct Answer: B. Achondroplasia
The AI Prompt
Prompt to ChatGPT-5:
“You are a Maternal-Fetal Medicine specialist. Interpret this 32-week fetal ultrasound showing short long bones, mild femoral bowing, normal ossification, no fractures, and an AFI of 29 cm. What is the most likely diagnosis? Explain your reasoning, discuss the differential, outline recommended management, and address ethical issues related to prenatal counseling.”
ChatGPT’s Full Response (abridged for clarity)
Diagnosis:
The findings are most consistent with achondroplasia, the most common non-lethal skeletal dysplasia.
Reasoning:
Limb pattern: Shortening of long bones (rhizomelic pattern—proximal > distal) with mild bowing is typical.
Ossification: Normal echogenicity distinguishes achondroplasia from lethal dysplasias like thanatophoric dysplasia, which show poor ossification or platyspondyly.
Fractures: Absence of fractures argues against osteogenesis imperfecta.
Thorax: Normal size (not narrow) suggests adequate pulmonary development, differentiating from lethal dysplasias.
Polyhydramnios: Common secondary feature due to limited fetal swallowing or altered skeletal mechanics.
Differential Diagnosis:
Thanatophoric dysplasia: More severe bowing, narrow chest, poor ossification.
Campomelic dysplasia: Anterior bowing of tibia/fibula, ambiguous genitalia possible.
Diastrophic dysplasia: Hitchhiker thumb, clubfoot, cystic ear swelling.
Osteogenesis imperfecta: Multiple fractures, hypomineralization.
Management Plan:
Confirmatory Testing:
Offer FGFR3 genetic testing (dominant mutation) by amniocentesis if diagnosis uncertain.
Counsel parents about inheritance (often de novo, but 50% recurrence if one parent affected).
Monitoring:
Serial ultrasounds for growth, AFI, and head circumference (often macrocephalic).
Assess fetal well-being and plan delivery at a tertiary center with neonatal support.
Delivery Planning:
Mode of delivery: Vaginal delivery often possible, but cephalopelvic disproportion may occur; cesarean may be required if fetal head size exceeds maternal pelvic dimensions.
Postnatal Care:
Neonatal evaluation to confirm diagnosis.
Early referral to genetics and orthopedics.
Ethical Considerations:
Autonomy: Parents must be given accurate, balanced information—achondroplasia is non-lethal and compatible with a normal lifespan.
Non-maleficence: Avoid framing as “abnormal” or “lethal.” Words matter.
Justice: Families deserve equal access to expert counseling regardless of geography; AI-assisted image interpretation could bridge that gap.
Beneficence: Encourage connection with patient support networks (e.g., Little People of America).
Summary:
Most likely diagnosis: Achondroplasia.
Rationale: Rhizomelic limb shortening, normal ossification, no fractures, normal chest, polyhydramnios.
Next steps: Confirm via FGFR3 testing, multidisciplinary perinatal care, delivery planning, and ethical counseling.
The Meta-Lesson
In this single exchange, the AI performed the entire intellectual arc of a case challenge: observation, reasoning, differential, testing, management, and ethics. It didn’t just choose the right answer—it articulated the why and the how.
What SMFM’s quiz presents as a game of recall, AI transforms into a masterclass in reasoning. The educational format can evolve: the point isn’t whether the AI knows, but whether we can understand what it knows.
Imagine if each SMFM “Case of the Week” included a “ChatGPT-5 analysis” sidebar. Learners could study the logic, question assumptions, and compare human versus machine reasoning. Instead of multiple choice, the challenge becomes interpretive: Do you agree with the AI’s rationale? Why or why not?
That is true diagnostic education—understanding, not guessing.
The Ethical Frontier
Is it ethical to use AI in prenatal diagnosis?
Today, the stronger argument is that it is unethical not to use AI.
When a technology demonstrably enhances diagnostic accuracy, speeds interpretation, reduces disparities, and helps explain findings in language families can understand, deliberately avoiding it violates the physician’s duty to beneficence and nonmaleficence.
The core ethical obligation of medicine is to use the best available means to prevent harm. A clinician who ignores AI-assisted tools, despite knowing they outperform unaided human interpretation in certain pattern-recognition tasks, is choosing a lower standard of care. This is not professional humility; it is ethical inertia. If AI can flag skeletal dysplasia earlier, identify anomalies that could otherwise be missed, or prepare families for counseling with greater clarity, then refusing to integrate it is no different from refusing to use an improved diagnostic test because one prefers the old microscope.
AI is not a replacement for the physician’s judgment—it is a moral assistant that strengthens it. Used responsibly, it widens access to expertise, supports overworked clinicians, and makes high-quality prenatal imaging interpretation available in underserved regions where MFM specialists are scarce. In that sense, AI becomes an equalizer, not an intruder. To withhold such a tool from patients because of habit, pride, or fear of change is to violate the principle of justice.
Of course, ethical use demands oversight. Clinicians must understand when the model’s confidence is justified, when to override it, and how to explain uncertainty transparently. Accountability remains human. But to reject AI altogether when it can reduce diagnostic errors, improve counseling, and spare families unnecessary suffering would be a failure of professional duty.
The true ethical risk today lies not in using AI, but in refusing to—thereby accepting preventable errors, slower recognition, and less informed care. History has seen this pattern before: skepticism toward antisepsis, ultrasound, and even fetal monitoring delayed their adoption and cost lives. In the same way, ignoring validated AI assistance in obstetric imaging is no longer a neutral choice. It is an ethically indefensible one.
There are many precedents where not using available technology became ethically unacceptable once its benefits were proven.
Refusing to perform ultrasound in pregnancy, when it can detect life-threatening conditions like placenta previa or anencephaly, would be indefensible.
Declining electronic fetal monitoring during labor in high-risk cases would ignore decades of evidence linking timely intervention to improved neonatal outcomes.
Omitting Rho(D) immune globulin after an Rh-negative pregnancy, or refusing to use antibiotic prophylaxis for cesarean delivery, would likewise violate the duty to prevent avoidable harm. In the same way, neglecting validated AI diagnostic assistance when it can enhance accuracy and patient understanding now falls within that same ethical category—a failure to use the best tools medicine has to protect mothers and babies.
Reflection / Closing
The “Ultrasound Case of the Week” once tested what we could see. Soon, it may test how we think alongside AI. The ultimate goal is not to outguess the machine but to outgrow our dependence on guessing. The next generation of maternal-fetal medicine will belong to those who can merge evidence, empathy, and ethics—whether the first diagnosis comes from a human hand or a silicon brain.