AI Tool Predicts Cancer Survival and Biological Age from Single Facial Photo

Assessing frailty and physiologic reserve remains challenging when clinicians consider intensive cancer treatment. Chronological age alone may not reflect how well a patient can tolerate radiation, surgery, or systemic therapy, complicating personalized treatment decisions for older adults. To provide a more individualized assessment, researchers have developed AI facial health recognition tools that estimate biological age and predict survival risk from a single facial photograph.

Mass General Brigham (Boston, MA, USA) developed Foundation Artificial Intelligence for Health Recognition, or FAHR-Face, as a large AI foundation model for facial health analysis. Trained on more than 40 million face images, the model was then used to create two complementary tools for assessing health in cancer care and aging research.

FAHR-FaceAge estimates biological age from a facial photograph and outperformed previous age-estimation algorithms, while FAHR-FaceSurvival predicts survival outcomes in patients with cancer. Although both tools were derived from the same foundation model, they captured different aspects of patient health.

In the development and validation study, the difference between a patient’s FAHR-FaceAge and chronological age was independently associated with survival. FAHR-FaceAge and FAHR-FaceSurvival were only weakly correlated, and both remained independently associated with survival when analyzed together. Combining the two measures also improved survival-model fit in an external validation cohort of patients with cancer.

The tools also relied on different facial regions for their predictions. FAHR-FaceAge focused on the nasolabial folds, the forehead area above the orbits, and the temples. FAHR-FaceSurvival evaluated the region below the eyes and around the nasal bridge. The findings were published in The Lancet Digital Health on October 19, 2026.

The study also linked lifestyle factors with facial aging. Heavy alcohol use, drug use, and smoking were associated with looking biologically older. Smoking showed the strongest pattern, with current smokers appearing older than former smokers, and former smokers appearing older than people who had never smoked. FAHR-FaceAge remained consistent across common photo variations, including pose, lighting, facial expression, and makeup, and was stable across most tested plastic surgery procedures, with only a small shift after rhinoplasty.

Related Links
Mass General Brigham