Researchers develop AI model to predict biological age and cancer survival via facial scans

Scientists at Mass General Brigham Hospital have developed a new artificial intelligence model capable of estimating biological age and predicting cancer survival rates through facial imagery. The model, named Foundation Artificial Intelligence for Health Recognition-Face (FAHR-Face), was trained on a dataset of over 40 million facial photographs.

The research team fine-tuned the system for two specific tasks: biological age estimation (FAHR-FaceAge) and survival prediction (FAHR-FaceSurvival). By analyzing a person's facial appearance, the AI can provide a non-invasive assessment of how cells, tissues, and organ systems are functioning.

In a study published in The Lancet Digital Health, researchers utilized a dataset of cancer patients from a research center in the Netherlands to test mortality risk detection. The study claims this is the first report of an AI algorithm capable of directly predicting cancer patient survival from a simple photograph.