Stories
Can a Selfie Predict Cancer Survival? New AI Study Says Yes
N
News18•20-10-2026, 15:00
Can a Selfie Predict Cancer Survival? New AI Study Says Yes
- •Researchers at Mass General Brigham have developed an AI system that estimates cancer survival rates using facial photographs.
- •The AI model was trained on more than 40 million facial images from diverse age groups and ethnic backgrounds.
- •Two tools were created, FAHR-FaceAge and FAHR-FaceSurvival, which analyze specific regions of the face to assess biological age and mortality risk.
- •Patients who appeared at least five years older than their actual age had a 21 percent higher risk of death, while those who appeared younger had a 17 percent lower risk.
- •Lifestyle factors such as smoking, heavy alcohol consumption, and drug use were linked to appearing older in the AI analysis.
- •Doctors note the technology could help guide treatment decisions, though further research is needed before routine clinical use.
Key Questions Answered
Researchers at Mass General Brigham developed two tools, FAHR-FaceAge and FAHR-FaceSurvival, which examine specific regions of a person's face to estimate biological age and predict survival chances directly from a photograph without needing chronological age calculations.
The FAHR-FaceAge tool focuses on areas such as the forehead, temples, and creases running from the nose to the corners of the mouth. Meanwhile, the FAHR-FaceSurvival tool analyzes the area below the eyes and around the bridge of the nose.
The AI analysis revealed that lifestyle factors such as smoking, heavy alcohol consumption, and drug use were associated with individuals appearing older than their actual chronological age.
