Accra:Massachusetts Researchers in the United States have developed an innovative artificial intelligence tool capable of predicting cancer patients' survival chances using a single facial photograph. The study detailing this breakthrough was published in the journal The Lancet Digital Health.

According to Anadolu Agency, the system, named FAHR-Face, was created by a team at Mass General Brigham in Massachusetts. It operates by analyzing facial features to estimate biological age and mortality risk, offering potential assistance to doctors in making treatment decisions.

The AI model was trained on over 40 million facial photos and consists of two tools FAHR-FaceAge, which estimates biological age, and FAHR-FaceSurvival, which directly predicts cancer survival chances from facial images. The researchers noted that the survival model focuses on regions beneath the eyes and around the nose, while the age-estimation model examines areas around the mouth and temples, indicating that the systems identify different health-related patterns.

For validation, the survival model was trained on images of 34,363 patients and tested on 3,820 additional images. It also underwent independent validation using data from 4,892 cancer patients in the Netherlands. Results showed that patients in the highest-risk group had over three times the mortality risk compared to those in the lowest-risk group, even after considering clinical factors.

The study found that patients whose facial appearance was at least five years older than their actual age had a 21% higher mortality risk, whereas those appearing at least five years younger had a 17% lower risk. Moreover, combining both models enhanced the accuracy of survival predictions.

The researchers emphasized that while the technology could significantly aid doctors in assessing patients' health and guiding treatment decisions, further validation is required before it can be broadly implemented in clinical settings.