Mon May 12 11:50:00 UTC 2025: ## AI Can Estimate Biological Age From Facial Photos, Potentially Revolutionizing Cancer Treatment
**Boston, MA** – Researchers at Mass General Brigham (MGB) have developed an AI model, dubbed FaceAge, capable of estimating a person’s biological age from a photograph of their face. This groundbreaking technology, detailed in a study published in *Lancet Digital Health*, shows promise in predicting cancer patient outcomes and potentially tailoring treatment plans.
The AI, trained on nearly 59,000 facial images, analyzes subtle features like muscle tone rather than relying solely on visible signs of aging. In a study of over 6,200 cancer patients, FaceAge revealed that those with a higher biological age (as determined by the AI) experienced poorer outcomes after treatment and higher mortality rates. Interestingly, cancer patients’ biological age was, on average, five years older than their chronological age.
The potential applications are significant. Doctors could use FaceAge to assess a patient’s biological fitness for aggressive treatments like radiation therapy, potentially optimizing care based on individual biological age rather than solely chronological age. For example, a 75-year-old with a biological age of 65 might be a better candidate for aggressive treatment than a peer with a higher biological age.
However, the study highlights crucial ethical and practical limitations. The AI’s training data primarily consisted of images of white adults over 60, raising concerns about potential biases affecting its accuracy across diverse populations. The impact of factors like makeup, plastic surgery, and lighting on the AI’s predictions also requires further investigation. Experts like Jennifer Miller, co-director of the program for biomedical ethics at Yale University, express concerns about the potential for misuse, particularly regarding insurance coverage and privacy.
While FaceAge offers a promising glimpse into personalized cancer care, MGB researchers acknowledge the need for further research to address biases, ensure reliability, and establish clear ethical guidelines for its responsible use. The technology’s potential benefits must be carefully weighed against the risks of bias and misuse.