Could a selfie predict your chances of cancer survival? Researchers are developing artificial intelligence tools to do just that.
In a study, published in the Lancet Digital Health on Oct. 19, Mass General Brigham researchers shared their findings on FAHR-Face (Foundation Artificial Intelligence for Health Recognition), an AI model trained on over 40 million face images.
Using the model, they developed two tools: FAHR-FaceAge, which estimates biological age, and FAHR-FaceSurvival, which predicts survival outcomes in patients with cancer. Biological age is a term used to describe someone's health and cellular function, which doesn't always match their actual, or chronological, age.
"The key technical advance is that FAHR-Face learns a general representation
of the face from more than 40 million images, which can then be adapted to distinct health outcomes such as biological age and survival," Hugo Aerts, co-senior author and Director of Artificial Intelligence in Medicine at Mass General Brigham, said in a news release. "This foundation-model approach gives us a scalable way to develop multiple facial health biomarkers rather than training each model from scratch."
In the study, FAHR-FaceAge outperformed benchmark models and maintained accuracy across the full human lifespan.
When it came to estimating biological age, researchers also found that lifestyle factors influenced facial aging. Heavy alcohol use, drug use and smoking were associated with looking biologically older, for example.
In patients with cancer, FAHR-FaceAge also outperformed previous estimation models in survival prognostication, according to the study. And FAHR-FaceSurvival showed "robust prediction of mortality," the study found.
While these tools are not ready for use in hospitals yet, researchers say they are important in helping guide treatment options.
"As the population ages, physicians need better ways to estimate physical reserve and frailty before recommending intensive treatments such as radiation, surgery or systemic therapy," corresponding author Dr. Raymond Mak, a radiation oncologist at Mass General Brigham Cancer Institute, said in the release. "Our goal is to make face photograph-based health assessment more quantitative, consistent and scalable so it can support personalized treatment decisions rather than replace physician judgment."
This article originally appeared on USA TODAY: Researchers develop AI photo tool that estimates age, cancer survival
