Photo of patient’s face could predict whether they’ll survive cancer?

Scientists have developed an artificial intelligence (AI) model that can help predict cancer patients’ survival prospects using a single photograph of their faces, potentially improving medical assessments and treatment decisions.

According to The Washington Post, researchers at Mass General Brigham developed FAHR-FaceSurvival, an AI tool trained using facial photographs and medical outcomes from more than 30,000 cancer patients.

The model was built on a foundation system trained on over 40 million facial images and is designed to identify patterns associated with mortality risk.

Researchers found that approximately half of patients whose scores ranked in the highest 10 per cent died within 90 days, compared with about two per cent among those in the lowest 10 per cent.

However, experts cautioned that the technology requires further testing before clinical use. Researchers also raised concerns about potential racial bias and whether the model offers information beyond existing medical assessments.

The findings, published in The Lancet Digital Health, could eventually support doctors in evaluating patients’ health and tailoring treatment decisions.