Lancet Study Finds AI Predicts Cancer Survival From Face Photos
The model trained on more than 40 million face images and separated cancer patients into risk groups with different 90-day death rates, researchers said.
- On October 19, 2026, Mass General Brigham researchers introduced FAHR-Face, an AI foundation model capable of estimating biological age and predicting cancer survival from facial photographs, published in The Lancet Digital Health.
- Trained on more than 40 million images, the model powers two complementary tools: FAHR-FaceAge and FAHR-FaceSurvival, which assess biological aging and cancer mortality risk by analyzing specific facial features like the nasal bridge and eye areas.
- Lifestyle factors like smoking influence facial aging patterns, the study found, while the tools showed consistency across real-world photo variations including lighting and makeup, making assessments "quantitative, consistent and scalable."
- Radiation oncologist Raymond Mak at the Mass General Brigham Cancer Institute noted physicians often struggle to estimate end-of-life expectancy, suggesting the AI could serve as "a way for doctors to have one more piece of information."
- University of Surrey professor Miroslaw Bober cautioned the tool is not ready for clinical use, emphasizing it requires testing against physicians' judgments across diverse hospitals and patient groups to demonstrate clinically useful value.
256 Articles
256 Articles
AI Can Use a Face Scan to Predict Your Biological Age and If You'll Survive Cancer
(The Daily Caller)—A new artificial intelligence model can measure someone’s biological age and predict their chances of surviving cancer just by looking at an image of the person’s face, researchers say. Scientists at Mass General Brigham Hospital in Boston built a new AI model that can provide what they’re calling a “non-invasive window into health,” […] The post AI Can Use a Face Scan to Predict Your Biological Age and If You’ll Survive Cance…
The system was trained with facial images of millions of healthy people and around 35,000 photos of cancer patients.
AI model uses face photos to estimate biological age, predict survival risk in cancer patients
A new AI model, FAHR-Face, estimates biological age and predicts cancer patient survival risk using facial photos. This model was trained on millions of images and showed an average error of about five years. Alongside this, another model identified high-risk cancer patients based on their appearance, highlighting significant survival differences. While results were promising in the US and Netherlands, further validation is needed in other popul…
American scientists have developed a system that analyzes facial features to estimate biological age and survival chances, providing information that could help doctors choose treatment. An ordinary facial photograph may contain important information about the health status and survival chances of cancer patients. This is suggested by a new American study, in which scientists have developed an artificial intelligence (AI) system that analyzes fa…
Coverage Details
Bias Distribution
- 56% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium




































