Mass General Brigham researchers develop AI to predict cancer survival

Researchers at Mass General Brigham in Massachusetts have developed an artificial intelligence system, known as FAHR-Face, capable of estimating a cancer patient's biological age and survival odds from a single facial photograph. The study, published in The Lancet Digital Health, utilized a foundation model trained on over 40 million diverse facial images.

The technology consists of two complementary tools. FAHR-FaceAge estimates biological age by analyzing the forehead, temples, and nasolabial folds, while FAHR-FaceSurvival predicts mortality risk directly by examining the area under the eyes and the nasal bridge. In a study of US patients undergoing radiotherapy, those who appeared at least five years older than their chronological age faced a 21% higher risk of death during a four-year follow-up period.

Experts note that while the AI provides a scalable way to assess a patient's general health and frailty, it is intended as a clinical decision-support tool rather than a replacement for medical tests or a definitive diagnosis. The system aims to help oncologists personalize treatments by providing an objective measure of a patient's ability to tolerate intensive therapies.