Researchers at Mass General Brigham in Boston, United States, developed FAHR-Face, an artificial intelligence foundation model for analysing health-related information in facial photographs. They used it to develop FAHR-FaceAge, which estimates biological age, and FAHR-FaceSurvival, which assesses survival risk in patients with cancer.
The foundation model was trained on more than 40 million facial images spanning different ages and ethnic backgrounds.
According to the report, the study was published in The Lancet Digital Health on October 19, 2026. Among 122 patients assigned to a high-mortality-risk group, 52.5% died within 90 days of assessment. This percentage describes the observed outcome for that group.
The report also states that 21% of 1,060 patients whose estimated biological age exceeded their chronological age by more than 20 years died within 90 days. Among 4,195 patients whose estimated biological age was at least 10 years younger, about 6% died over the same period. These are statistical associations in the study population. The researchers say the tools are intended to support clinical assessment and do not replace physician judgment. Article: Rithy.
