New AI tool can predict cancer survival by a single patient selfie, study suggests

A novel artificial intelligence tool developed by doctors at Mass General Brigham, a nonprofit healthcare system in Massachusetts, can predict a cancer patient's survival chances using a single selfie, according to a recent study. The AI system, which was trained on more than 40 million facial photographs representing various ethnicities and ages, estimates a person's biological age and predicts survival outcomes.

This technology consists of two complementary tools: FAHR-FaceAge, which estimates a patient's biological age, and FAHR-FaceSurvival, which directly predicts cancer survival from a facial photograph.

The study, published in the Lancet Digital Health journal, demonstrates the potential for AI analysis of a selfie to assess a patient's health and guide their medical care. The researchers found that patients who appeared five or more years older than their actual age, according to FAHR-FaceAge, had a 21% higher risk of dying during a four-year follow-up compared to the rest of the group. Conversely, patients who looked five or more years younger had a 17% lower risk of dying.

The breakthrough could help doctors make more informed decisions about treatment options, such as radiation, surgery, or systemic therapy, especially for aging populations who require better ways to gauge physical reserve and frailty before recommending intensive treatments. By making face photograph-based health assessment more quantitative, consistent, and scalable, the tool could support personalized treatment decisions while still relying on physician judgment.