AI tool can predict a cancer patient's chances of survival from a single SELFIE, US researchers say

An AI system that examines eye bags and the bridge of the nose to estimate how long patients may live has been developed by researchers at Mass General Brigham in Massachusetts. They trained it on a dataset of over 40 million facial photographs, among them 35,000 drawn from cancer patients in the US and the Netherlands. Professor Hugo Aerts called it 'the first demonstration' of using a single photograph to directly predict a cancer patient's chances of survival. The findings appear in Lancet Digital Health.

A companion tool, FaceAge, estimates biological age from nasolabial folds, forehead and temples.

Current smokers appeared older than former smokers, who in turn appeared older than those who had never smoked.