Facial AI estimates cancer patients’ biological age and survival prospects

Researchers at Mass General Brigham have developed AI models that estimate biological age and predict survival for people with cancer from a facial photograph. The study suggests facial analysis could provide doctors with another way to assess patients’ health and help inform decisions about intensive treatment, while the researchers say it should support rather than replace medical judgement.

The models were built from more than 40 million facial photographs spanning different ages and ethnicities, and tested using cancer patient data. Among US patients who received radiotherapy, those judged to look at least five years older than their actual age had a 21% higher risk of dying during an average four-year follow-up; those judged at least five years younger had a 17% lower risk. The study, published in The Lancet Digital Health, reports that one model predicts survival directly from facial features, while another uses estimated biological age.