AI tool can predict cancer survival from a single selfie

Experts at Mass General Brigham have developed a new artificial intelligence-based system that can estimate patients' biological age from a single facial photograph and directly predict cancer survival outcomes. According to the study published in The Lancet Digital Health, the system was trained using more than 40 million facial photographs.

Doctors and researchers at Mass General Brigham designed the FAHR-Face artificial intelligence tool to guide cancer patients' treatment processes. The system consists of two complementary tools: FAHR-FaceAge, which estimates the patient's biological age and cancer survival, and FAHR-FaceSurvival, which predicts survival directly from a facial photograph. Both algorithms utilize different regions of the face to estimate age and risk of death.

Hugo Aerts, co-senior author of the study, stated that this is the first instance showing an AI model can directly predict cancer survival from a simple photograph. An analysis of cancer patients receiving radiotherapy in the US found that those who appeared five years older or more than their actual age had a 21 percent higher risk of death over an average four-year follow-up period, while those who appeared five or more years younger had a 17 percent lower risk.

Dr. Raymond Mak, a radiation oncologist at Mass General Brigham, stated that the goal of this technology is to make health assessments based on facial photographs more quantitative and scalable to support personalized treatment decisions. On the other hand, the AI analysis determined that lifestyle factors such as excessive alcohol, drug use, and smoking are linked to individuals appearing biologically older.