AI Model Developed by Mass General Brigham Predicts Cancer Survival from Facial Photographs

Researchers at Mass General Brigham have developed a new artificial intelligence model, FAHR-FaceSurvival, capable of predicting cancer mortality risk from a single facial photograph. The technology, detailed in a study published in The Lancet Digital Health, analyzes subtle facial features to assess a patient's health status and survival likelihood. Findings showed that among cancer patients with the highest FAHR-FaceSurvival scores, approximately half died within 90 days, compared to about 2% in the lowest scoring group. This builds upon earlier work on FaceAge, which estimated biological age from facial photos.