AI can predict cancer survival from a single facial photograph

A new system trained on 40 million images can estimate biological age and survival outcomes for cancer patients using a selfie.

AI can predict cancer survival from a single facial photograph
Photo: The Guardian

An AI system can estimate a person's biological age and predict cancer survival chances from a single photograph of their face. The technology was custom-built by experts at Mass General Brigham, an integrated academic healthcare system in Massachusetts.

The model was trained on data from more than 40 million facial photographs across various ages and ethnicities. Researchers developed two complementary tools from the system: FAHR-FaceAge, which estimates biological age, and FAHR-FaceSurvival, which predicts survival directly from a photograph.

FAHR-FaceAge focuses on the temples, the forehead area above the eye sockets, and creases running from the sides of the nose to the corners of the mouth. FAHR-FaceSurvival evaluates the nasal bridge and the region below the eyes. Hugo Aerts, a co-senior author of the study, said this is the first demonstration that an AI model can directly predict cancer survival from a simple photograph.

Among cancer patients in the US treated with radiotherapy, those who looked five or more years older than their actual age had a 21% higher risk of dying during a four-year follow-up period. Patients who looked five or more years younger had a 17% lower risk.

Lifestyle factors such as smoking, drug use, and heavy alcohol use were linked to looking biologically older in the analysis. Dr Raymond Mak, a radiation oncologist at Mass General Brigham, said the goal is to make health assessment more consistent and scalable to support personalised treatment decisions rather than replace physician judgment.

The tool could help doctors predict the risk of complications or death after major surgery or other cancer treatments. Doctors cautioned that more research is needed before the tool can be used widely, though it offers a low-cost way to support treatment decisions.

Key facts

  • The AI system was trained on more than 40 million facial photographs.
  • Patients looking five or more years older than their actual age had a 21% higher risk of death during a four-year follow-up.
  • The study was published in the Lancet Digital Health journal.

Three perspectives

Neutral

The AI system uses facial analysis to estimate biological age and predict survival outcomes for cancer patients.

Positive

The breakthrough could help doctors make difficult decisions regarding the best treatment paths for their patients.

Negative

Doctors cautioned that more research is required before the tool can be widely implemented.

Your week in news, every Wednesday

The biggest stories of the week for your edition, in your inbox every Wednesday morning, your time. Free, and you can unsubscribe at any time.

Choose your news coverage

Please choose and confirm your coverage.

Anthropic prepares for $1.4tn IPO as AI market faces uncertainty
Next storyAnthropic prepares for $1.4tn IPO as AI market faces uncertainty

All sections

Edition