AI facial analysis predicts cancer survival odds

Researchers at Mass General Brigham have developed AI models that predict cancer patients' biological age and survival chances from a single facial photograph, according to a study published Monday in The Lancet Digital Health. The technology could become an additional tool for doctors evaluating treatment approaches. The AI models, trained on over 40 million facial images, assess specific facial regions to gauge health and mortality risk. Among 122 patients flagged as high-risk, 52.5 percent died within 90 days, compared to about two percent of the 975 lowest-risk patients. Cosmetic changes like Botox or makeup did not affect performance. Experts call the findings a promising proof of concept but note the tool requires prospective clinical testing against doctors' judgments across diverse populations. The study was conducted only among cancer patients, though researchers suggest broader longevity applications may emerge.