Truace
Subscribe

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

Doctors have developed an artificial intelligence tool that can predict a cancer patient’s chances of survival from a single photograph of their face. The AI system was custom-built by experts at Mass General Brigham, a nonprofit, integrated academic healthcare system in Massachusetts, to estimate biological age and directly predict survival outcomes in patients diagnosed with cancer. It is one of the most comprehensive demonstrations to date of how AI analysis of a selfie could help assess a patient’s health an…

By the Truvace desk2 min read1 sourceJournalismTRV-2026-1952· cite & verify
New AI tool can predict cancer survival by a single patient selfie, study suggests

In brief

Researchers at Mass General Brigham built a foundation-model system called FAHR-Face, trained on more than 40 million facial photographs, and adapted it into two tools. One estimates biological age from a face photo, while the other predicts survival for cancer patients directly. The work was published in Lancet Digital Health.

The approach could give oncologists a cheap, quantitative way to judge frailty and physical reserve before choosing intensive treatments such as radiation or surgery. The developers say it should support rather than replace physician judgment, and the article notes that more research is needed before wide clinical use.

Main points

  1. FAHR-FaceAge estimates biological age, while FAHR-FaceSurvival predicts survival directly from a facial photograph.
  2. The two tools were derived from the same model but captured different, complementary information and used different facial regions.
  3. Among US radiotherapy patients, those looking five or more years older had 21% higher mortality risk over an average four-year follow-up.
  4. Those looking five or more years younger had a 17% lower risk of dying.
  5. Heavy alcohol use, drug use and smoking were linked to looking biologically older in the AI analysis.

The gain

AI models trained on over 40 million face images estimated biological age and predicted cancer survival, stratifying mortality risk among US radiotherapy patients and potentially supporting personalised treatment decisions.

The rundown

FAHR-FaceAge focuses on the nose-to-mouth creases, the forehead above the eye sockets and the temples. FAHR-FaceSurvival evaluates the region below the eyes and around the nasal bridge. The researchers describe this as the first demonstration that an AI model can directly predict cancer survival from a simple photograph.

The foundation-model approach learns a general facial representation that can be adapted to different health outcomes. According to co-senior author Hugo Aerts, this offers a scalable way to develop multiple facial health biomarkers rather than training each model from scratch.

Dr Raymond Mak said FAHR-FaceAge was consistent across pose, lighting, facial expression and makeup. It was also stable across most tested plastic surgery procedures, with only a small shift after rhinoplasty.

Sources

  1. JournalismThe Guardian2026-10-19

The debate