Pulse.

a daily field guide to health research that matters

◆ Console

‹ Tue · 3 Nov 2026
Promising but preliminary

Diagnosing Rare Genetic Diseases From Facial Images Using Visual Prompting With Multimodal Large Language Models: Diagnostic Accuracy Study.

Current AI systems struggle to diagnose rare genetic diseases from facial images alone, highlighting the importance of human expertise in diagnosis.

OBJECTIVE, This study aimed to evaluate the diagnostic accuracy of MLLMs for rare genetic diseases using facial images and to assess whether super-resolution enhancement or red-circle visual prompting improved performance. CONCLUSIONS, Under the evaluated experimental settings, the 3 MLLMs showed limited ability to diagnose rare genetic diseases from facial images, particularly diseases in GMDB-Rare.

What the study was

Study design
Diagnostic accuracy study
Category
Diagnostics
Maturity
Exploratory
Journal
JMIR medical informatics

Why it surfaced

Abstract-reviewed diagnostic accuracy study scored conservatively for diagnostics; 8/10 reflects the available design, relevance, novelty, and population or unmet-need evidence.

A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.