AI Face Photo Analysis Predicts Biological Age and Cancer Survival Risk

Researchers at Mass General Brigham Cancer Institute have developed artificial intelligence tools that analyse facial photographs to assess health indicators, including biological age and survival outcomes for patients with cancer.

The team built FAHR-Face, or Foundation Artificial Intelligence for Health Recognition, a large AI foundation model trained on more than 40 million facial images. It was used to develop two complementary tools. FAHR-FaceAge estimates biological age with greater accuracy than previous age estimation algorithms, while FAHR-FaceSurvival predicts survival outcomes for patients with cancer using a facial photograph.

“As the population ages, physicians need better ways to estimate physical reserve and frailty before recommending intensive treatments such as radiation, surgery or systemic therapy,” said corresponding author Raymond Mak, MD, a radiation oncologist and a faculty member in the Artificial Intelligence in Medicine (AIM) programme at Mass General Brigham. “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 key technical advance is that FAHR-Face learns a general representation of the face from more than 40 million images, which can then be adapted to distinct health outcomes such as biological age and survival,” said Hugo Aerts, PhD, co-senior author and Director of AIM at Mass General Brigham. “This foundation-model approach gives us a scalable way to develop multiple facial health biomarkers rather than training each model from scratch.”

Although both tools were derived from the same foundation model, they captured different aspects of a patient’s health. Their predictions were only weakly correlated, and both remained independently associated with survival when analysed together. Combining the measures further improved survival-model fit in an external validation cohort of patients with cancer.

The algorithms also relied on different facial features. FAHR-FaceAge focuses on the nasolabial folds, the forehead area just above the orbits and the temples, while FAHR-FaceSurvival evaluates the region below the eyes and around the nasal bridge.

“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,” Aerts said. “To our knowledge, this is the first demonstration that an AI model can directly predict cancer survival from a simple photograph.”

The model development and validation study, published in Lancet Digital Health, found that the difference between a patient’s FAHR-FaceAge and chronological age was independently associated with survival. FAHR-FaceAge achieved a mean absolute error of 5.1 years on public datasets, outperforming previous models across the full human lifespan.

Among cancer patient cohorts, those with higher predicted mortality risk according to FAHR-FaceSurvival had substantially higher death rates. The highest-risk quartile had more than three times the mortality of the lowest-risk quartile, with an adjusted hazard ratio of 3.23.

The researchers also found that lifestyle factors were associated with facial ageing. Heavy alcohol use, drug use and smoking were linked to looking biologically older. Smoking showed the strongest pattern, with current smokers appearing older than former smokers, who in turn appeared older than people who had never smoked.

The study also demonstrated the tools’ consistency across common variations in photographs. “Another surprising finding was how consistent FAHR-FaceAge was across common real-world photo variations, including pose, lighting, facial expression, and makeup,” noted Mak. “It was also stable across most tested plastic surgery procedures, with only a small shift observed after rhinoplasty.”

The team is expanding this research through the FaceAge Research Study, an online study approved by an institutional review board and open to the public at faceage.bwh.harvard.edu. Participants can upload a facial photograph and receive their own FaceAge research readout, while contributing data to help researchers improve and validate AI-based measures of facial ageing and health across larger, more diverse populations.

The tools remain at the research stage, and further validation across diverse populations and against physician assessments will be needed before they can be used routinely in hospitals. Funded by the EU European Research Council, the study represents a step towards low-cost, non-invasive biomarkers that could help personalise care for older people and patients with cancer.