Doctors have developed an artificial intelligence tool that can predict a cancer patient's chances of survival from a single photograph of their face, in what researchers call one of the most comprehensive demonstrations yet of how AI analysis of a selfie could help assess health and guide care.
The system, built by experts at Mass General Brigham in Massachusetts and published in Lancet Digital Health, produced two tools from one foundation model trained on more than 40 million facial photographs across ages and ethnicities. FAHR-FaceAge estimates biological age — how old a person looks — while FAHR-FaceSurvival predicts survival directly, reading the region below the eyes and around the nasal bridge.
Among U.S. cancer patients receiving radiotherapy, those estimated to look at least five years older than their chronological age had a 21 per cent higher risk of death over an average four-year follow-up, while those who looked at least five years younger had a 17 per cent lower risk. Smoking showed the strongest ageing pattern, ahead of heavy alcohol and drug use.
'To our knowledge, this is the first demonstration that an AI model can directly predict cancer survival from a simple photograph,' said co-senior author Hugo Aerts. The team stresses the goal is to support — not replace — physician judgment, helping assess frailty and physical reserve before radiation, surgery or systemic therapy, and says more research is needed before widespread clinical use.



