ISTANBUL: Researchers in the United States have developed an artificial intelligence (AI) tool that can predict cancer patients’ survival prospects from a photograph of their face, according to a study published on Monday in The Lancet Digital Health, Anadolu Ajansi reported.
Developed by researchers at Mass General Brigham in Massachusetts, the system, known as FAHR-Face, analyses facial features to estimate biological age and mortality risk, potentially helping doctors make more informed treatment decisions.
The system was trained on more than 40 million facial images and adapted into two tools: FAHR-FaceAge, which estimates biological age, and FAHR-FaceSurvival, which predicts cancer patients’ survival prospects directly from facial images without relying on age estimates.
Researchers found that the survival prediction model focused mainly on areas beneath the eyes and around the nose, while the biological age model analysed facial features around the mouth and temples.
The findings suggest that the two systems identify different patterns associated with a person’s health.
FAHR-FaceSurvival was trained using images from 34,363 patients and tested on another 3,820 patients. Its findings were independently validated using data from 4,892 cancer patients in the Netherlands.
The study found that patients classified in the highest-risk group had more than three times the risk of death compared with those in the lowest-risk group, even after clinical factors were taken into account.
Patients whose faces appeared at least five years older than their actual age also had a 21% higher risk of death, while those who appeared at least five years younger had a 17% lower risk.
Combining the two models further improved the accuracy of survival predictions, according to the researchers.
The team said the technology could potentially help doctors assess patients’ health and guide treatment decisions. However, further validation is needed before it can be widely adopted in clinical practice.
-AWANI
