Algorithmovigilance in AI-Based Oral-Health Surveillance: Temporal Drift, Cross-Survey Differences, and Predictor-Level Structural Stability in Population-Level Severe Tooth Loss Prediction.

Researchers monitored an AI model predicting severe tooth loss across five years of U.S. survey data, finding that whilst overall discrimination remained stable, model calibration and the relationship between specific risk factors and tooth loss changed over time and between different survey systems.

A plain-English summary of the study's own findings — we don't add our own claims or interpretation. Read the full paper for the complete methods and results, and apply your own clinical judgement.