Boston: Researchers have developed an artificial intelligence system that can estimate biological age and predict cancer survival outcomes from a single facial photograph, potentially helping doctors assess patients before recommending intensive treatment.
The system, developed by experts at Mass General Brigham in Massachusetts, is based on FAHR-Face, a foundation AI model trained on more than 40 million facial images representing different ages and ethnicities.
The findings were published in The Lancet Digital Health. Researchers developed two complementary tools: FAHR-FaceAge, which estimates biological age, and FAHR-FaceSurvival, which predicts cancer survival risk directly from facial photographs.
The study found that cancer patients whose estimated biological age was at least five years higher than their actual age had a 21 percent higher risk of death during an average four-year follow-up than other patients. Those who appeared at least five years younger had a 17 percent lower risk.
The findings indicate an association between facial ageing estimates and survival, rather than a guarantee of an individual patient’s outcome. The two tools examine different facial features to make their predictions. FAHR-FaceAge focuses on areas including the forehead, temples and folds running from the sides of the nose towards the mouth.
FAHR-FaceSurvival places greater emphasis on the area beneath the eyes and around the bridge of the nose. Researchers said the models captured complementary information about patients’ health.
The researchers also found that smoking, heavy alcohol consumption and drug use were associated with appearing biologically older in the AI analysis. They said the technology could eventually help clinicians assess physical frailty and inform decisions about radiotherapy, surgery and other cancer treatments. However, the system is intended to support medical judgment, not replace it.
The researchers cautioned that further validation is needed before the tools can be adopted widely in clinical practice. They are continuing to study how facial photographs could provide a consistent, accessible measure of health and help doctors make more personalized treatment decisions.
POPULAR | France government under pressure after weekend of violent unrest
