Researchers at Mass General Brigham, a nonprofit academic healthcare system in Massachusetts, have developed an artificial intelligence (AI) tool capable of estimating biological age and predicting cancer patients' survival chances from a single photograph of their face.
The findings, published in The Lancet Digital Health, highlight the potential of facial analysis to provide doctors with additional information about patients' health and help guide personalised treatment decisions.
The AI system, known as FAHR-Face, was trained on data from more than 40 million facial photographs representing people of different ages and ethnicities. Researchers developed two complementary tools from the model: FAHR-FaceAge, which estimates biological age and predicts cancer survival, and FAHR-FaceSurvival, which directly assesses survival risk from facial images without relying on biological age estimates.
Also Read | Layoffs Are Rising In Tech, But These Skills Are Helping People Unlock Better Pay
Although both tools share the same underlying model, they analyse different facial features to generate their predictions. FAHR-FaceAge focuses on areas such as forehead wrinkles, temples and creases around the nose and mouth, while FAHR-FaceSurvival primarily examines the region beneath the eyes and around the bridge of the nose.
In clinical trials involving US radiotherapy patients followed over four years, the predictive power proved significant. Patients who appeared five or more years older than their chronological age faced a 21% higher risk of mortality, whereas patients who appeared five or more years younger demonstrated a 17% lower mortality risk.
ALSO READ: UK Woman Spends Rs 37 Lakh On Content Creation Degree, Internet Asks: 'Worth It?'
Researchers said the findings suggest that facially estimated biological age may reflect aspects of physical health, including a patient's ability to withstand demanding cancer treatments. The study also found that smoking, heavy alcohol consumption and drug use were associated with signs of accelerated facial ageing.
Co-senior author Hugo Aerts said the technology represents a significant advance because it can learn general facial characteristics from a large image dataset and adapt them to predict different health outcomes.
Radiation oncologist Raymond Mak said the tool could eventually help doctors assess physical fitness and frailty before recommending intensive treatments such as radiotherapy, surgery or systemic therapy. He stressed, however, that the technology is intended to support, not replace, clinical judgement.
Researchers also found that FAHR-FaceAge remained relatively consistent despite variations in lighting, facial expressions, camera angles and makeup, although some cosmetic procedures produced small changes in estimates.
ALSO READ: iPhone 18 Could Get A Wider Camera Module, Suggest Images Ahead Of Rumoured 2027 Launch
Despite its potential as a low-cost, accessible assessment method, the researchers cautioned that further studies are necessary before the technology can be widely adopted in clinical practice.
Essential Business Intelligence, Sharp Market Insights, Practical Personal Finance Advice, Daily Fuel, Gold and Silver Prices and Latest Stories — On NDTV Profit.
