Harvard researchers announced on May 21 that artificial intelligence can help predict cancer outcomes by analyzing digital photographs of patients’ faces. The studies found that both looking younger than one’s chronological age and showing slower facial aging during treatment are linked to better chances of survival for cancer patients.
This research is significant because it suggests a new, simple way to assess biological age and guide cancer care using routine photographs. If confirmed in further clinical studies, the FaceAge algorithm could allow physicians to tailor treatments based on a patient’s biological rather than chronological age.
Raymond Mak, associate professor at Harvard Medical School and co-senior author of the studies, said, “One of the first numbers they put in is your chronological age. It’s done by every single primary care doctor, the same with a pre-op evaluation, the same with a lot of our risk calculators and cancer care. What we’re arguing is why use chronological age when we’re seeing these massive deflections between biological age and chronological age? Why not use something that might be more precise for an individual?”
The research included two major studies. The first study analyzed over 24,000 cancer patients and found those who looked five years or more younger than their actual age had better outcomes while those who appeared older had worse results. The second study followed more than 2,200 patients undergoing radiation therapy; it showed that slower face aging rates were associated with longer survival times.
Hugo Aerts, professor at Dana-Farber Cancer Institute and director of Artificial Intelligence in Medicine at Mass General Brigham as well as co-senior author, explained how the next generation FaceAge algorithm was trained using millions of images: “The nice thing is that if you use that 40 million to train a foundation model…once you have that model, you can fine-tune it further to a very specific task.” He also said FaceAge assessments may eventually supplement but not replace traditional imaging methods like CT scans or MRIs: “CT and MRI will generate much, much more information. But you cannot take an MRI every day…The beauty of this is you can get rougher but more frequent health assessments using a very simple picture.”
Researchers are now working on improving the tool’s accuracy across different skin types and conditions such as makeup or plastic surgery. They have launched an online portal for public participation in ongoing clinical trials.
If future results remain positive, experts say FaceAge could become an affordable way for people worldwide to monitor their health through regular photos while supporting—not replacing—current medical practices.
