Doctors at Mass General Brigham built an AI that predicts a cancer patient’s survival from a single photo of their face.

The study was published on Monday in the journal Lancet Digital Health.

The model, FAHR-Face, was trained on over 40 million facial photos plus photos of more than 30,000 cancer patients.

One tool estimates biological age, the age a person looks. Another predicts survival directly from the photo.

Patients who looked at least five years older than their real age had a 21% higher risk of death.

Those who looked at least five years younger had a 17% lower risk, over about four years of follow-up.

In a test group of 3,820 patients, 64 of the 122 highest-risk patients died within 90 days of their photo.

Author Raymond Mak said doctors are generally not very good at estimating life expectancy just by looking at patients.

Read the full article for more details on the face-photo cancer AI.