Can a simple photo of your face reveal how ill you are?

A tired woman wearing a pink dressing gown looks at herself in the mirror, with her hand touching the side of her forehead

Image source, Getty ImagesByMichelle RobertsDigital health editor

Published4 minutes ago

An AI tool may be able to help doctors judge how ill a patient is using a single photograph of their face, say US researchers.

Trained on millions of healthy faces, and 35,000 photos of cancer patients, the tool can make estimates on survival by looking closely at features near the eyes, the scientists say.

While it's a long way from being suitable for use in hospitals, the researchers say their goal is to help doctors recommend the right treatments for their patients.

The preliminary findings are published in the Lancet Digital Health, external journal.

The eyes have it

The image shows a computer graphic of two faces, one for each AI model, and depicts which facial features appear to be most important for assessing biological age and survival, using a heat map colour code.

Image source, Mass General Brigham/Lancet Digital HealthImage caption,

The researchers developed two AI tools to estimate biological age and predict cancer survival from a single face photo. The face on the left shows features most important to cancer survival outcomes, while the right face shows those key to age. Areas shown in yellow had the greatest impact on predictions.

The 'FaceSurvival' AI tool suggests the area under the eyes and around the bridge of the nose are the most vital parts of the face to assess when estimating how long they might have left to live.

These metrics applied across many different types of cancers, varying in severity, including ones that had spread to the patient's bones or brain.

Most of the cancer patients, who were from the US and the Netherlands, were in their 50s or 60s, but some were children, while others were in their 90s.

Doctors already examine patients and run comprehensive checks and tests to judge how unwell they are, and what their prognosis might be.

The AI tool, which has a patent application pending, is designed to help doctors doing this work, not replace them.

Lead researcher Dr Raymond Mak, from Mass General Brigham in Boston, explained: "As the population ages, physicians need better ways to estimate physical reserve and frailty before recommending intensive treatments such as radiation, surgery or systemic therapy.

"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."

Collagen: Do you drink it? Inject it? Rub it on your skin? And does it work?
- Published27 September 2025
Why doing a mix of exercise could be the key to longer life
- Published21 January
Can two hours of strength training a week reduce the risk of dying early?
- Published3 June

Fresh-faced?

Mak and colleagues are also evaluating an AI tool for predicting biological age, or how old someone looks, as opposed to their birthday age.

The 'FaceAge' tool suggests the skin below the nose and near the mouth - the so-called nasolabial folds and marionette lines - plus the forehead (frown lines), temples (crows' feet) and cheeks are a good indicator of how fast we age.

Some lifestyle habits can speed that process up, like heavy alcohol use, drug use and smoking.

Mak says the tool was "surprisingly consistent" across common real-world photos despite variations in pose, lighting, facial expression and make-up.

"It was also stable across most tested plastic surgery procedures, with only a small shift observed after rhinoplasty [a nose job]," he says.

But the researchers stress they need much more data and photos of faces, particularly from lots of different ethnic groups, to determine how well the tools work. They are still very much under development.

The research team is inviting the public to take part, external and receive a personalised biological age estimate by uploading their own facial photo the research team.

Prof Miroslaw Bober, an expert in video processing and machine learning at the University of Surrey in the UK, says any claims that the tool could track ageing or lifestyle changes over time would be "premature".

"This is a promising proof of concept, but it is not ready for clinical use," he said.

"The tool still needs testing against doctors' own judgement and across different hospitals and patient groups."

And he warned: "Predicting an outcome is not the same as explaining it."