WASHINGTON (dpa-AFX) - A study published in The Lancet Digital Health reported that researchers at Mass General Brigham had developed an artificial intelligence model called FAHR-Face (Foundation Artificial Intelligence for Health Recognition), which was trained using more than 40 million facial images.
Using this model, researchers created two tools: FAHR-FaceAge, which estimates a person's biological age, and FAHR-FaceSurvival, which predicts survival chances in cancer patients.
The study found that FAHR-FaceAge performed better than existing comparison models and estimated age accurately across different stages of life. Although both tools were developed from the same AI model, they provided different but complementary information about a person's health.
The two tools also examined different areas of the face to make their predictions. FAHR-FaceAge mainly looks at wrinkles running from the sides of the nose to the corners of the mouth, the forehead area above the eyes, and the temples. In contrast, FAHR-FaceSurvival focuses on the area below the eyes and around the bridge of the nose.
'FAHR-FaceSurvival advances the field of facial health recognition AI a step further by learning survival risk directly from facial photographs of patients with cancer,' said co-senior author Hugo Aerts. 'To our knowledge, this is the first demonstration that an AI model can directly predict cancer survival from a simple photograph.'
The study included cancer patients from the United States and the Netherlands. Most were in their 50s or 60s, although the group also included children and people in their 90s.
Among cancer patients in the United States who received radiotherapy, those whose faces were estimated to look at least five years older than their actual age had a 21% higher risk of dying during an average follow-up period of four years. In contrast, patients whose faces appeared at least five years younger than their actual age had a 17% lower risk of dying.
'Another surprising finding was how consistent FAHR-FaceAge was across common real-world photo variations, including pose, lighting, facial expression and makeup,' said Dr Raymond Mak, a radiation oncologist at Mass General Brigham. 'It was also stable across most tested plastic surgery procedures, with only a small shift observed after rhinoplasty.'
The researchers believe these tools could help doctors make better-informed treatment decisions in the future. However, the technology is not yet ready for use in hospitals, and further work is needed before it can become part of routine medical care.
Copyright(c) 2026 RTTNews.com. All Rights Reserved
Copyright RTT News/dpa-AFX
© 2026 AFX News
