US researchers develop AI model to predict cancer patient mortality from facial images

American researchers have developed an artificial intelligence model capable of analyzing facial images to estimate biological age and predict mortality risk in cancer patients, potentially helping doctors select the most appropriate treatments for each case, according to scientists at Mass General Brigham.

The model, named "FAHR-Face," was trained on more than 40 million facial images and used to create two tools:

• The first estimates biological age with greater accuracy than previous algorithms.
• The second predicts survival outcomes in cancer patients.

The study found that the difference between estimated biological age and actual age is linked to survival outcomes. Using both tools together improved prediction accuracy compared to using either one alone.

The researchers explained that the tools analyze different facial regions: the first focuses on the folds of the nose, lips, forehead, and temples to estimate biological age, while the second relies on the area below the eyes and around the bridge of the nose to predict mortality risk.

Radiation oncologist Raymond Mak and co-researcher Hugo Aerts noted that the technology could help doctors assess patients' health more precisely and choose treatments that match their ability to tolerate intensive interventions such as surgery, radiotherapy, and medication.

The researchers emphasized that the model is intended to support, not replace, clinical assessment, and stressed the need for further studies and validation before broader adoption in medical practice.