AI tool predicts cancer survival from a single patient selfie

Researchers at Mass General Brigham built FAHR-Face, an AI system that estimates biological age and directly predicts cancer survival from one facial photograph. The model was trained on over 40 million images, with results published in Lancet Digital Health.

• Model trained on more than 40 million facial photographs
• Looking 5+ years older linked to 21% higher risk of death
• Looking 5+ years younger linked to 17% lower risk of death
• FAHR-FaceAge and FAHR-FaceSurvival rely on different facial regions