Doctors have developed an artificial intelligence tool capable of predicting a cancer patient’s chances of survival from a single photograph of their face.
The AI system was custom designed by experts at Mass General Brigham, a nonprofit integrated academic health system in Massachusetts, to estimate biological age and directly predict survival outcomes for patients diagnosed with cancer.
This is one of the most comprehensive demonstrations to date of how AI analysis of a selfie could help assess a patient’s health and potentially guide their medical care. It was trained based on data from over 40 million facial photographs of various ethnicities and ages.
Details of this advance were published in the journal Lancet Digital Health.
The system can estimate a person’s biological age – the age they look like, rather than their actual chronological age – and predict cancer patients’ chances of survival from an ordinary photograph of their face, according to the results of a study that examined the model.
Doctors used this technology to develop two complementary tools. FAHR-FaceAge estimates a patient’s biological age and predicts cancer survival. FAHR-FaceSurvival directly predicts survival from a facial photograph, rather than inferring survival based on biological age.
Although FAHR-FaceAge and FAHR-FaceSurvival were derived from the same model, they captured different and complementary information about a patient’s health.
Each algorithm also relied on distinct parts of the face to make respective predictions about age and mortality risk. FAHR-FaceAge focuses on the folds that extend from the sides of the nose to the corners of the mouth, the forehead area just above the eye sockets, and the temples. FAHR-FaceSurvival, on the other hand, assesses the area under the eyes and around the bridge of the nose.
“FAHR-FaceSurvival advances the field of facial health recognition AI by learning survival risk directly from facial photographs of cancer patients,” said Hugo Aerts, co-senior author of the study. “To our knowledge, this is the first demonstration that an AI model can directly predict cancer survival from a simple photograph.”
Among cancer patients treated with radiation therapy in the United States, people who, according to FAHR-FaceAge, looked five or more years older than their actual age had a 21 percent higher risk of death during the average four-year follow-up than the rest of the group. Patients who looked five or more years younger had a 17% lower risk.
“The key technical advancement is that FAHR-Face learns a general facial representation from more than 40 million images, which can then be tailored to distinct health outcomes such as biological age and survival,” Aerts said. “This base model-based approach gives us a scalable way to develop multiple facial health biomarkers rather than training each model from scratch. »
The study results suggest that estimates of people’s biological ages are closely related to their physical health, which could reflect their ability to survive certain treatments.
This breakthrough could pave the way for AI facial analysis to help doctors make difficult decisions about the best course of treatment for their patients.
The tool could help better predict the risk of death or complications after major surgery or other cancer treatments.
Dr. Raymond Mak, radiation oncologist at Mass General Brigham, said, “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.
“Our goal is to make facial photography-based health assessment more quantitative, consistent and scalable so that it can support personalized treatment decisions rather than replacing physician judgment. »
Researchers found that lifestyle factors were associated with facial aging. For example, heavy drinking, drug use, and smoking were linked to a biologically older appearance in AI analysis of facial photographs.
“Another surprising finding was FAHR-FaceAge’s consistency in common variations in real-world photos, including pose, lighting, facial expression and makeup,” Mak said. “It was also stable in most plastic surgery procedures tested, with only a small change observed after rhinoplasty.”
Doctors cautioned that while single-face photographs could provide a simple, inexpensive way to support personalized treatment decisions, more research was needed before the tool could be widely used.
Gn Health
