AI tool predicts cancer patients’ survival chances from facial photos, study finds

Researchers from Mass General Brigham have developed an AI model called FAHR-Face that can estimate biological age and predict survival chances in cancer patients based on a single facial photo. The model, which was trained on over 40 million publicly available facial images, uses two complementary tools - FAHR-FaceAge and FAHR-FaceSurvival - to assess biological age and predict survival prospects.

Biological age, which reflects how a person appears in terms of age rather than chronological age, was found to be an important factor in predicting mortality risk. Patients with an estimated biological age at least five years older than their actual age had a 21% higher risk of death during an average follow-up of four years, while those with an estimated biological age at least five years younger had a 17% lower risk.

The AI model also showed robust performance across various variations in facial photographs. The study's findings suggest that facial photographs could offer a non-invasive way to assess certain aspects of a patient's health and help inform treatment decisions. However, the technology still requires further validation before it can be used routinely in clinical practice.