You can detect biological age and a person's chance of surviving cancer 'with just one photo'

A person's biological age and their likelihood of surviving cancer can both be detected from a single photograph of their face, according to researchers.

An AI tool developed by experts from Mass General Brigham in Massachusetts was trained on more than 40 million pictures to determine key indicators of a person's health.

The authors of the study, which was published in Lancet Digital Health, said the cancer estimates were then checked against real patient data to verify their accuracy.

Biological ageing describes how old the body is in terms of health and function, rather than the number of years a person has lived.

The researchers found that how people live their lives also influences ageing in the face, with heavy alcohol use, drug use and smoking associated with looking biologically older.

Smoking showed the strongest pattern, with current smokers looking older than former smokers, and former smokers looking older than people who never smoked.

Hugo Aerts, professor at Harvard University and director of the AI in medicine programme at Mass General Brigham, said the new work “advances the field of facial health recognition AI a step further by learning survival risk directly from facial photographs of patients with cancer”.

He added: “To our knowledge, this is the first demonstration that an AI model can directly predict cancer survival from a simple photograph.”

Raymond Mak, associate professor of radiation oncology at Harvard Medical School, said the team was surprised by how consistent the study’s findings were “across common real-world photo variations, including pose, lighting, facial expression and makeup”.

He added: “Our goal is to make face photograph-based health assessment more quantitative, consistent and scalable so it can support personalised treatment decisions rather than replace physician judgment.”

People can upload a photo and receive their own readout by joining the research study at faceage.bwh.harvard.edu.