New AI tool predicts cancer survival from a single patient selfie
Experts at Mass General Brigham in Massachusetts developed an artificial intelligence system that estimates biological age and predicts survival for cancer patients using facial photographs.
System trained on millions of photos
The AI model was built by specialists within the nonprofit academic healthcare system to analyze ordinary images of faces. It utilized data from more than 40 million facial photographs covering various ethnicities and age groups. Researchers published details of this breakthrough in the Lancet Digital Health journal.
Two complementary tools for assessment
Doctors created two distinct algorithms derived from the same underlying model to capture different health information. One tool called FAHR-FaceAge estimates a person's biological age rather than their chronological years. The second algorithm named FAHR-FaceSurvival predicts survival chances directly without inferring results through age first.
Potential impact on medical care
This technology represents one of the most comprehensive demonstrations of how selfie analysis could assess patient health. The system aims to potentially guide medical care for individuals diagnosed with cancer based on facial data. Each algorithm relies on distinct parameters to provide these specific estimates and predictions.
Reported by one outlet
Only one outlet has published this. Nothing here has been checked against a second report, so read it as that outlet's account and follow the link below for the original.
Reported by
1 independent outlet. Headline as published. Links open the original report.