AI Model Predicts Mortality Risk in Cancer Patients Using Facial Images

Washington, October ( وكالة الأنباء السعودية ۔ ‎‎‎ 21 اكتوبر 2026ء) According to researchers at Mass General Brigham, the model, called FAHR-Face, was trained on more than 40 million face images. It was used to develop two tools: one that estimates biological age more accurately than previous algorithms, and another that predicts survival outcomes in cancer patients. The study found that the difference between a patient's FAHR-FaceAge and their chronological age was independently associated with survival outcomes. Combining the two tools also improved predictive accuracy compared with using either tool alone. The researchers explained that the tools analyze different facial regions. The first focuses on the nasolabial folds, lips, forehead and temples to estimate biological age, while the second analyzes the area below the eyes and around the nasal bridge to predict mortality risk. Radiation oncologist Raymond Mak and co-senior author Hugo Aerts said the technology could help physicians assess patients' health more accurately and select treatments based on their ability to tolerate intensive interventions, including surgery, radiation therapy and drug therapy. Mak noted that these efforts are intended to 'support personalized treatment decisions rather than replace physician judgment' and that the goal is 'to make face photograph-based health assessment more quantitative, consistent and scalable.'