Artificial intelligence can predict mortality risk from facial photographs of cancer patients
Researchers at the Mass General Brigham Cancer Institute have developed an artificial intelligence model that calculates the 90-day mortality risk by analyzing facial photographs of cancer patients. Published in the journal The Lancet Digital Health, the study emphasizes that the model is not yet ready for clinical use.
Ray Mak, a radiation oncologist at the Mass General Brigham Cancer Institute, and his team have developed an artificial intelligence model capable of predicting the biological age and 90-day mortality risks of cancer patients by examining their facial photographs. Published in the journal The Lancet Digital Health on October 19, 2026, the research aims to establish an objective basis for physicians' observational assessments.
Evaluation: The researchers state that the model is not yet ready for clinical use due to being trained on predominantly white data from the Boston area. Matthew Liao, a bioethics expert from New York University, warns that erroneous predictions by the system could lead to delays in care processes or be misused in areas such as insurance and hiring.
Sources
- gazeteoksijen.com · Link