Researchers in the United States have developed an artificial intelligence tool that can estimate a cancer patient’s biological age and assess survival risks using a single facial photograph. The technology could help doctors make treatment decisions, although further clinical validation is required.
How Does the AI Tool Work?
Researchers at Mass General Brigham, affiliated with Harvard Medical School, developed the model called FAHR-Face, short for Foundation Artificial Intelligence for Health Recognition.
The system was trained using more than 40 million facial images. Researchers also examined photographs of more than 30,000 cancer patients to develop tools for estimating biological age and predicting survival outcomes.
Unlike chronological age, biological age reflects aspects of a person’s physical condition. Researchers believe facial features may provide clues about overall health and physiological resilience.
FCRF’s Chief AI Officer Certification Returns on November 14 to Prepare Future AI Leaders
Can It Predict Survival?
The AI model assigned risk scores to cancer patients based on their facial photographs. Patients receiving higher scores were more likely to die within 90 days, according to the findings.
The system also estimated age with an average error of approximately five years and distinguished between higher-risk and lower-risk patients. Researchers reported that the model performed across different age groups, races, genders and cancer types, suggesting potential applications in cancer care.
What Did Researchers Find?
Raymond Mak, a radiation oncologist at Mass General Brigham Cancer Institute and one of the researchers, said doctors already assess patients partly through their physical appearance.
However, estimating life expectancy accurately remains difficult. The researchers believe AI could identify subtle facial characteristics associated with declining health.
Mak said the model focused particularly on the bridge of the nose and the area beneath the eyes when making its assessments.
Is the Technology Ready?
Despite the findings, experts have cautioned against introducing the system into routine clinical practice without further testing.
Miroslaw Bober, a professor at the University of Surrey, questioned whether predicting an outcome necessarily explains the medical reasons behind it.
He said the model should be evaluated against doctors’ clinical assessments and established hospital data before being relied upon for treatment decisions.
About the author — Ayesha Aayat writes on cybercrime, digital safety, and emerging online threats. Her work focuses on public awareness, legal clarity, and technology-driven risks.
Follow for daily updates on cybercrime, corporate fraud, DFIR, hacking, investigations, and digital forensics
