Researchers at Mass General Brigham have developed AI tools, FAHR-FaceAge and FAHR-FaceSurvival, trained on over 40 million facial images to predict biological age and cancer survival chances from a single photograph. Published in The Lancet Digital Health in October 2026, the study showed that over 50% of cancer patients identified as high risk by FAHR-FaceSurvival died within 90 days. Intended to objectively quantify frailty to guide personalized treatment decisions, the tools require further clinical trial validation before hospital implementation.
FAHR-FaceSurvival cancer mortality predictions
- ▪The FAHR-FaceSurvival artificial intelligence tool predicts cancer mortality risk directly from a photograph by evaluating facial features in the region below the eyes and around the nasal bridge.
- ▪In a study of 122 cancer patients categorized as high mortality risk by FAHR-FaceSurvival, 52.5 percent died within 90 days, compared to approximately two percent of 975 low-risk patients.
Development of the FAHR-Face model
- ▪Mass General Brigham researchers fine-tuned the FAHR-Face foundation model into two complementary tools: FAHR-FaceAge for biological age estimation and FAHR-FaceSurvival for direct cancer survival prediction.
- ▪Researchers at Mass General Brigham developed the FAHR-Face artificial intelligence foundation model by training the algorithm on over 40 million facial photographs across diverse ages and ethnic backgrounds.
Biological age links to mortality and lifestyle
- ▪In a Mass General Brigham study published in October 2026, cancer patients whose FAHR-FaceAge estimated biological age was five or more years older than their chronological age had a 21 percent higher risk of death.
- ▪Mass General Brigham researchers found that lifestyle factors including heavy alcohol use, drug use, and smoking were associated with older biological age estimates, with smoking demonstrating the strongest effect.
FAHR-FaceAge facial analysis and performance
- ▪Mass General Brigham study findings indicated that the FAHR-FaceAge model maintained consistent performance across photo variations in pose, lighting, expression, and makeup, with rhinoplasty causing subjects to evaluate slightly older.
- ▪The FAHR-FaceAge artificial intelligence tool estimates biological age by analyzing specific facial regions including the nasolabial folds, forehead area above the eye sockets, and temples.
Clinical applications and prospective trials
- ▪Mass General Brigham researchers designed the FAHR-Face tools to provide objective measurements of patient frailty and physical reserve to support, rather than replace, clinical decision-making by physicians.
- ▪Independent experts noted that while Mass General Brigham's findings show strong proof-of-concept associations, FAHR-Face tools require prospective clinical trials across diverse populations before clinical deployment.
- ▪Mass General Brigham is conducting clinical trials to test whether FaceAge can identify frail elderly lung cancer patients needing support services before radiation therapy and predict surgical complication risks.
Public FaceAge online research portal
- ▪The public FaceAge portal allows participants to track biological age estimates over time while expanding dataset diversity to refine and validate Mass General Brigham's facial health algorithms.
- ▪In March 2026, Mass General Brigham launched a public online research portal at faceage.bwh.harvard.edu, enrolling over 10,000 participants who upload facial photos to estimate biological age.
Story comments
Loading comments…