AI virtual trials match real trial results for GLP-1 vs insulin in type 2 diabetes
Last updated May 16, 2026
Key finding
AI models can recreate trial results, but need more validation before use in treatment decisions.
Researchers used AI to create virtual patients and test whether they could recreate results from a real diabetes trial. They trained the AI using data from over 5,000 people with type 2 diabetes. The AI successfully matched the original trial's findings that GLP-1 drugs work better than basal insulin for blood sugar control, weight loss, and blood pressure. The AI model correctly showed GLP-1 was more effective across all three outcomes tested. When researchers used the AI to test treatments in broader groups of people beyond the original trial, they found GLP-1 wasn't always the best choice for everyone. This suggests treatment benefits may vary depending on individual characteristics.
Quick read
Study at a glance
The essential study design details in one scan.
EvidenceScore™
Moderate
Study type
non-randomized clinical trial (non-RCT or NRCT)
Follow-up
Medium-Term (3–12 mo)
Risk of bias
Some Concerns
Save research, organize studies, and quickly find important evidence again.
Plain-language summary
What this paper says
A plain-language read of the study’s main message and where it applies.
Study focus
AI models can recreate trial results, but need more validation before use in treatment decisions.
Published in
Journal Reference
Publication details and source links for this paper.
MacLellan CR, Petkov H, McKeag C, et al. Emulating real-world GLP-1 efficacy in type 2 diabetes through causal learning and virtual patients. PLOS Digit Health. 2025;4(7):e0000927. doi:10.1371/journal.pdig.0000927
Main Effects
HbA1c → ↓ (GLP-1 better than insulin)
Weight (BMI) → ↓ (GLP-1 better than insulin)
Blood pressure → ↓ (GLP-1 better than insulin)
Evidence Suggest
- AI models can recreate results from real diabetes trials, correctly showing GLP-1 drugs work better than insulin for blood sugar, weight, and blood pressure.
- Treatment benefits may vary by individual, with GLP-1 not always the best choice for everyone.
- This AI method needs more testing before it can be used widely for treatment decisions.
Who this applies to
People with type 2 diabetes on metformin and sulfonylurea considering GLP-1 or insulin treatment; healthcare providers choosing between treatment options; researchers testing new AI methods for drug evaluation.
Keep in Mind
This tests an AI method, not actual treatments, so it doesn't provide new clinical evidence.
Between the Lines
- Tested drug classes, not specific medications
- Virtual patients showed less variation than real people
- Only validated against one trial
- Excluded records with missing data
No ads. No tracking.
Focused on evidence, not advertising.
Secure & private
Your data is always protected.
Always up to date
New studies added every day.