[REVISION HISTORY]

Mass General Brigham AI cancer survival research

Updated 1 time since CLSTR started tracking revisions of this situation.

What changed

2026-10-25 13:29 UTC → 2026-10-25 19:42 UTC · added ~~removed~~

Researchers at Mass General Brigham have developed an artificial intelligence system, utilizing a foundation model known as FAHR-Face, to estimate a cancer patient’s biological age and mortality risk from a single facial photograph. The study, published in The Lancet Digital Health, involved training the model on a dataset of over 40 million facial ~~images.~~ images across diverse ethnicities and ages. The technology employs two specific tools: FAHR-FaceAge, which analyzes features like forehead ~~creases~~ creases, temples, and nasolabial folds to estimate biological age, and FAHR-FaceSurvival, which focuses on the nasal bridge and the area below the eyes to predict survival probability. Clinical findings indicated that patients appearing at least five years older than their chronological age faced a 21% higher risk of death during a four-year ~~follow-up.~~ follow-up, while those appearing five years younger showed a 17% lower risk. In testing, the survival model showed significant differentiation in risk levels, with 52.5% of high-risk patients dying within 90 days compared to 2% of the low-risk group. Researchers noted the tool’s performance remained consistent regardless of makeup or cosmetic interventions like Botox. The system is intended to function as a clinical decision-support tool to assist oncologists in ~~personalizing treatments.~~ assessing physical resilience before intensive treatments such as surgery or radiation.

Versions

Only revisions since CLSTR began indexing content versions appear here. Select a version to see what changed compared to the one before it.