- Researchers developed AI tools that use facial photographs to estimate cancer patients’ survival chances and how healthy they appear.
- The technology could help doctors choose suitable cancer treatments, but more research is needed before it can be widely used.
A photograph of your face could one day help doctors work out your chances of surviving cancer.
Researchers at Mass General Brigham, a healthcare system in the United States, have developed artificial intelligence tools that look for signs of a patient’s health in an ordinary facial photograph.
The findings were published in The Lancet Digital Health.
The technology was developed using more than 40 million photographs of people of different ages and ethnic groups.
Researchers created two tools.
The first estimates a person’s biological age, meaning how old their face appears compared with their actual age.
The second uses a photograph to estimate a cancer patient’s chances of survival directly.
Researchers found that cancer patients who appeared at least five years older than their actual age had a 21% higher risk of dying during an average four-year follow-up.
Those who appeared at least five years younger had a 17% lower risk.
The findings came from patients receiving radiotherapy in the United States.
Hugo Aerts, one of the study’s senior authors, said it was the first demonstration that AI could directly predict cancer survival from a simple photograph, the Guardian reported.
The technology could eventually help doctors decide whether patients are strong enough for demanding treatments such as surgery, radiation or cancer medicines.
Dr Raymond Mak, a cancer specialist at Mass General Brigham, said doctors need better ways to measure patients’ physical strength and frailty.
Researchers also found that smoking, heavy drinking and drug use were linked to faces appearing biologically older.
But the technology is not ready to replace medical assessments.
Researchers say further studies are needed before it can be widely used in hospitals.
The aim is to give doctors another tool to help make treatment decisions, not to predict with certainty how long someone will live.
