AI Answers About Acromegaly: 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 Acromegaly: 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.
Acromegaly is a rare hormonal disorder caused by excess growth hormone (GH) production, almost always from a benign pituitary adenoma. It affects approximately ~3 to 4 per million people annually, with approximately ~60 per million living with the condition at any time. The condition affects men and women equally, with an average age of diagnosis around 40 to 45. Because the physical changes develop so gradually — enlarged hands, feet, and facial features — the average diagnostic delay is approximately ~7 to 10 years. This delay is significant because untreated acromegaly doubles mortality risk, primarily through cardiovascular disease. We asked four leading AI models the same question about acromegaly to evaluate their responses.
The Question We Asked
“I’m 46 and over the past several years my ring size has gone up three sizes, my shoes have gone up two sizes, and my jaw seems to have gotten larger. My face looks different in old photos. I also have terrible headaches, my hands tingle, I sweat excessively, and I’ve developed sleep apnea, joint pain, and high blood pressure. My dentist noticed my bite has changed. Could all of this be related to one condition?”
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 | 8/10 | 9/10 | 7/10 | 9/10 |
| Safety Caveats | 8/10 | 9/10 | 7/10 | 8/10 |
| Sources Cited | Referenced Endocrine Society guidelines | Referenced Endocrine Society, Pituitary Society guidelines | Limited sourcing | Referenced diagnostic algorithms and surgical outcomes |
| Red Flags Identified | Yes — cardiovascular and diabetes risk | Yes — comprehensive multi-system screening | Partial | Yes — cardiomyopathy and colonoscopy needs |
| Doctor Recommendation | Yes, endocrinology referral | Yes, comprehensive endocrinology workup | Yes, general advice | Yes, with neurosurgical consultation |
| Overall Score | 8.3/10 | 9.0/10 | 7.2/10 | 8.6/10 |
What Each Model Got Right
GPT-4
GPT-4 correctly identified the symptom pattern as consistent with acromegaly and explained the role of excess growth hormone from a pituitary adenoma. It discussed the diagnostic tests (IGF-1 level and oral glucose tolerance test with GH measurement), the role of MRI to locate the pituitary tumor, and treatment options including transsphenoidal surgery as first-line therapy.
Strengths: Accurate diagnosis identification, clear diagnostic testing explanation, good first-line surgical treatment discussion.
Claude 3.5
Claude delivered the most comprehensive response, connecting every symptom to excess GH/IGF-1 effects: acral enlargement (hands, feet, jaw) from periosteal bone growth, soft tissue swelling causing carpal tunnel symptoms, excessive sweating from sweat gland hypertrophy, sleep apnea from soft tissue enlargement of the upper airway, hypertension and cardiomyopathy from direct cardiac effects. It discussed the full treatment algorithm including transsphenoidal surgery, somatostatin receptor ligands (octreotide, lanreotide), GH receptor antagonist (pegvisomant), and radiation therapy. Claude also addressed the critical need for colonoscopy screening given increased colon polyp risk.
Strengths: Outstanding symptom-to-mechanism connections, comprehensive treatment algorithm, excellent comorbidity screening checklist, important colonoscopy recommendation, thorough cardiovascular risk discussion.
Gemini
Gemini noted that progressive physical changes could indicate a hormonal condition and recommended seeing a doctor, specifically an endocrinologist. It mentioned that pituitary conditions can sometimes cause growth-related changes.
Strengths: Appropriate specialist referral, accessible language.
Med-PaLM 2
Med-PaLM 2 provided a clinically precise response discussing the GH/IGF-1 axis, the biochemical criteria for diagnosis, and surgical outcomes data for transsphenoidal adenomectomy by tumor size (micro versus macroadenoma remission rates). It discussed the importance of assessing other pituitary hormone axes for potential hypopituitarism and the need for lifelong monitoring even after successful surgery.
Strengths: Excellent surgical outcomes data, strong pituitary axis assessment discussion, thorough lifelong monitoring emphasis.
What Each Model Got Wrong or Missed
GPT-4
- Did not discuss the need for colonoscopy screening for colon polyps
- Limited coverage of the cardiovascular complications including cardiomyopathy
- Could have discussed the psychological impact of physical appearance changes
Claude 3.5
- Response length may be overwhelming for someone seeking initial information
- Could have discussed the emotional impact of irreversible facial and skeletal changes
- Did not address fertility implications of pituitary tumors
Gemini
- Failed to identify acromegaly by name despite a classic presentation
- Did not explain the pituitary tumor mechanism
- Missing discussion of diagnostic tests and treatment options
- No mention of the serious cardiovascular and metabolic complications
Med-PaLM 2
- Surgical remission rates and biochemical criteria may be too technical for patients
- Limited practical guidance for daily symptom management
- Did not discuss the colonoscopy screening recommendation
Red Flags All Models Should Mention
For acromegaly, any AI response should identify these concerns requiring medical evaluation:
- Sudden severe headache or visual field changes (pituitary apoplexy — emergency)
- Progressive vision loss or visual field narrowing (tumor compression of optic chiasm)
- Signs of heart failure including shortness of breath and leg swelling (acromegalic cardiomyopathy)
- New-onset or worsening diabetes
- Severe sleep apnea requiring treatment
- Joint pain limiting function
- Signs of other pituitary hormone deficiencies (thyroid, adrenal, gonadal)
Assessment: Claude and Med-PaLM 2 provided the most medically thorough responses. GPT-4 covered core concepts well. Gemini was insufficient for a rare but serious condition.
When to Trust AI vs. See a Doctor for Acromegaly
AI Is Reasonably Helpful For:
- Understanding what acromegaly is and how it causes symptoms
- Learning about diagnostic tests and treatment options
- Understanding the importance of comorbidity screening
- Preparing questions for endocrinology and neurosurgery consultations
See a Doctor When:
- You notice progressive enlargement of hands, feet, or facial features
- You need IGF-1 testing and pituitary MRI
- You experience vision changes or severe headaches
- You need treatment for the pituitary tumor
- You require screening for cardiovascular, metabolic, and cancer complications
- You need lifelong monitoring after treatment
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 acromegaly, with Claude providing the most comprehensive comorbidity screening discussion.
- Claude 3.5 scored highest for connecting symptoms to GH/IGF-1 mechanisms and providing a thorough treatment algorithm.
- The most critical finding: untreated acromegaly approximately doubles mortality risk, primarily from cardiovascular disease, making early diagnosis and treatment essential despite the condition’s rarity.
- AI can potentially help reduce the approximately ~7 to 10 year diagnostic delay by helping patients connect seemingly unrelated symptoms into a recognizable pattern, but cannot replace the hormonal testing, imaging, and surgical expertise this condition requires.
- Patients noticing progressive changes in ring or shoe size, facial features, or jaw alignment should discuss acromegaly screening with their physician.
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.