Open access
Aug 2026
Expert-Guided Visual Correction for Characterizing Diagnostic Performance and Error Patterns of Multimodal Large Language Models Using Periodontal In-Service Examination Images
The expert-guided visual correction framework introduced here provides a generalizable, mechanism-based approach to benchmarking multimodal AI diagnostic performance that extends beyond periodontics to other visually driven diagnostic domains in medicine.
P. Dhaimade, R. Henderson
· medRxiv · 0 citations