AI could predict cancer survival from a single selfie
An AI system developed by researchers at Mass General Brigham can estimate biological age and predict cancer survival from a single facial photograph, potentially offering doctors another tool for assessing patients before treatment.
Doctors have developed an artificial intelligence system that can predict a cancer patient's chances of survival from a single photograph of their face.
The technology, developed by researchers at Mass General Brigham in Massachusetts, was trained using more than 40 million facial photographs spanning different ages and ethnicities.
Details of the research were published in The Lancet Digital Health.
The system, known as FAHR-Face, was used to create two complementary tools. FAHR-FaceAge estimates a person's biological age, based on how old they appear, while FAHR-FaceSurvival predicts cancer survival directly from a facial photograph.
The researchers found that the two tools drew on different areas of the face. FAHR-FaceAge focused on features including creases around the mouth, the forehead and temples, while FAHR-FaceSurvival analysed areas below the eyes and around the bridge of the nose.
Among US cancer patients who had received radiotherapy, those who appeared at least five years older than their chronological age had a 21 per cent higher risk of dying during an average four-year follow-up.
Those who appeared at least five years younger had a 17 per cent lower risk.
Hugo Aerts, a co-senior author of the study, said: "FAHR-FaceSurvival advances the field of facial health recognition AI a step further by learning survival risk directly from facial photographs of patients with cancer.
"To our knowledge, this is the first demonstration that an AI model can directly predict cancer survival from a simple photograph."
Researchers said the findings suggest biological age estimated from facial photographs may provide information about a person's physical health and their ability to tolerate intensive treatment.
Dr Raymond Mak, a radiation oncologist at Mass General Brigham, said the technology could help doctors assess patients before treatments such as surgery, radiotherapy or systemic therapy.
He said: "Our goal is to make face photograph-based health assessment more quantitative, consistent and scalable so it can support personalised treatment decisions rather than replace physician judgment."
The researchers also found links between facial ageing and lifestyle factors including smoking, heavy alcohol use and drug use.
However, they stressed that further research is needed before facial analysis can be widely used in clinical care.
