AI Answers About Marfan Syndrome: Model Comparison
Data Notice: Figures, rates, and statistics cited in this article are based on the most recent available data at time of writing and may reflect projections or prior-year figures. Always verify current numbers with official sources before making financial, medical, or educational decisions.
AI Answers About Marfan Syndrome: Model Comparison
DISCLAIMER: AI-generated responses shown for comparison purposes only. This is NOT medical advice. Always consult a licensed healthcare professional for medical decisions.
Marfan syndrome is a genetic connective tissue disorder caused by mutations in the FBN1 gene, which encodes the protein fibrillin-1. It affects approximately ~1 in 5,000 people worldwide, with roughly ~200,000 Americans living with the condition. Marfan syndrome affects men and women equally and is inherited in an autosomal dominant pattern, meaning one affected parent has a 50% chance of passing it to each child, though approximately ~25% of cases arise from new mutations with no family history. The most serious complication — aortic root dilation leading to aortic dissection — makes diagnosis and monitoring lifesaving. We asked four leading AI models the same question about Marfan syndrome to evaluate their responses.
The Question We Asked
“I’m 22, very tall and thin with long arms and fingers. My doctor noticed I have a heart murmur and ordered an echocardiogram that showed my aorta is dilated. I also have a dislocated lens in one eye, stretch marks I never understood, and my joints are very flexible. My father is similarly tall and had heart surgery in his 40s. My doctor suspects Marfan syndrome. How serious is this, and what does it mean for my future?”
Model Responses: Summary Comparison
| Criteria | GPT-4 | Claude 3.5 | Gemini | Med-PaLM 2 |
|---|---|---|---|---|
| Response Quality | 8/10 | 9/10 | 7/10 | 9/10 |
| Factual Accuracy | 9/10 | 9/10 | 7/10 | 9/10 |
| Safety Caveats | 8/10 | 9/10 | 7/10 | 9/10 |
| Sources Cited | Referenced Ghent nosology | Referenced revised Ghent criteria, ACC/AHA aortic guidelines | Limited sourcing | Referenced Ghent criteria and aortic management guidelines |
| Red Flags Identified | Yes — aortic dissection risk | Yes — comprehensive aortic emergency education | Partial | Yes — aortic surgery thresholds and dissection signs |
| Doctor Recommendation | Yes, cardiology and genetics | Yes, comprehensive multidisciplinary management | Yes, general advice | Yes, with specific monitoring protocol |
| Overall Score | 8.5/10 | 9.2/10 | 7.0/10 | 8.8/10 |
What Each Model Got Right
GPT-4
GPT-4 correctly explained Marfan syndrome as a fibrillin-1 connective tissue disorder and connected all the patient’s features: marfanoid habitus (tall, thin, long limbs), ectopia lentis (lens dislocation), aortic root dilation, joint hypermobility, and striae. It discussed the critical importance of regular echocardiographic monitoring of the aorta and the role of beta-blockers and ARBs (losartan) in slowing aortic growth. GPT-4 also mentioned the need for genetic counseling.
Strengths: Comprehensive feature recognition, clear aortic monitoring importance, good pharmacological discussion, appropriate genetic counseling recommendation.
Claude 3.5
Claude delivered the most comprehensive response, explaining the revised Ghent diagnostic criteria and how the patient’s features (aortic root dilation, ectopia lentis, family history, systemic features) meet diagnostic thresholds. It provided detailed aortic dissection education including warning signs (sudden severe tearing chest or back pain), surgical intervention thresholds (typically aortic root diameter approaching 5.0 cm or rapid growth exceeding 0.5 cm/year), exercise restrictions (no competitive sports, heavy weight lifting, or isometric exercise), pregnancy planning considerations with aortic size thresholds, and the dramatic improvement in life expectancy with modern management.
Strengths: Outstanding aortic emergency education, excellent exercise restriction guidance, comprehensive pregnancy planning discussion, important life expectancy improvement message, thorough multidisciplinary management plan.
Gemini
Gemini noted that the combination of physical features and family history suggested a connective tissue condition and recommended following through with the doctor’s evaluation. It mentioned that early management can help.
Strengths: Appropriate family history acknowledgment, reassurance about management benefits.
Med-PaLM 2
Med-PaLM 2 provided a clinically precise response discussing the Ghent nosology scoring system, the Z-score system for aortic root measurements, and evidence-based surgical thresholds. It discussed the comparative data for beta-blockers versus ARBs from clinical trials, the timing of prophylactic aortic root replacement, and the importance of screening first-degree relatives.
Strengths: Excellent Z-score measurement explanation, strong surgical threshold guidance, thorough pharmacological evidence, important family screening emphasis.
What Each Model Got Wrong or Missed
GPT-4
- Did not specify the surgical intervention thresholds for aortic root size
- Limited discussion of exercise restrictions, which are critical for daily life
- Could have discussed pregnancy planning given the patient’s young age
Claude 3.5
- Response length may feel overwhelming for a newly diagnosed 22-year-old
- Could have discussed the emotional impact of activity restrictions and lifestyle changes
- Did not address career and insurance considerations
Gemini
- Failed to identify Marfan syndrome by name or discuss aortic dissection risk
- Did not explain exercise restrictions that could prevent a fatal event
- Missing discussion of aortic monitoring and surgical intervention thresholds
- No mention of the family history implications for the patient’s father and future children
Med-PaLM 2
- Z-scores and Ghent nosology details may be too technical for a 22-year-old patient
- Limited discussion of lifestyle modifications and emotional support
- Did not address pregnancy planning considerations
Red Flags All Models Should Mention
For Marfan syndrome, any AI response should identify these concerns requiring emergency evaluation:
- Sudden severe chest or back pain, often described as tearing (aortic dissection — call 911)
- Sudden shortness of breath (possible pneumothorax or aortic emergency)
- Sudden vision loss or change (lens dislocation or retinal detachment)
- Fainting or severe dizziness (cardiac arrhythmia or aortic valve disease)
- Rapid aortic growth on serial echocardiography (may require prophylactic surgery)
- New or worsening heart failure symptoms
- Pregnancy in a woman with aortic dilation (high-risk, needs specialized management)
Assessment: Claude and Med-PaLM 2 provided the most medically thorough responses. GPT-4 covered core concepts well. Gemini was dangerously insufficient for a condition with life-threatening aortic complications.
When to Trust AI vs. See a Doctor for Marfan Syndrome
AI Is Reasonably Helpful For:
- Understanding what Marfan syndrome is and how it affects connective tissue
- Learning about the importance of regular aortic monitoring
- Understanding exercise restrictions and lifestyle modifications
- Preparing questions for cardiology and genetics appointments
See a Doctor When:
- You have features suggestive of Marfan syndrome and need evaluation
- You experience sudden chest or back pain (emergency — call 911)
- You need regular echocardiographic monitoring of your aorta
- You are considering pregnancy and have Marfan syndrome
- You need genetic counseling for family planning
- Your first-degree relatives need screening
Can AI Replace Your Doctor? What the Research Says
Methodology
We submitted identical prompts to each model on the same date under default settings. Responses were evaluated by our team using the mdtalks.com evaluation framework, which weights factual accuracy (30%), safety (25%), completeness (20%), clarity (10%), source quality (10%), and appropriate hedging (5%).
Medical AI Accuracy: How We Benchmark Health AI Responses
Key Takeaways
- Three of four models correctly identified Marfan syndrome and its implications, with Claude and Med-PaLM 2 providing the most comprehensive aortic management guidance.
- Claude 3.5 scored highest for its thorough emergency education, exercise restriction guidance, and pregnancy planning discussion.
- The most critical finding: modern management of Marfan syndrome has increased life expectancy from approximately ~45 years to near-normal, but only with proper aortic monitoring, medication, exercise modification, and timely prophylactic surgery.
- AI can help patients understand their condition and the rationale for lifestyle modifications, but cannot replace the echocardiographic monitoring, genetic testing, and multidisciplinary care this condition requires.
- Every person with Marfan syndrome should know the signs of aortic dissection (sudden tearing chest or back pain) and understand that this requires calling 911 immediately.
Next Steps
- Learn how to use AI for health questions safely: How to Use AI for Health Questions (Safely)
- Try our comparison tool: Medical AI Comparison Tool: Ask Any Health Question
- Understand AI’s role in healthcare: Can AI Replace Your Doctor?
Published on mdtalks.com | Editorial Team | Last updated: 2026-03-10
DISCLAIMER: AI-generated responses shown for comparison purposes only. This is NOT medical advice. Always consult a licensed healthcare professional for medical decisions.