Mass General Brigham's AI predicts cancer survival from a selfie, study suggests
Doctors at Mass General Brigham have built an artificial‑intelligence system that can estimate a cancer patient’s biological age and directly predict survival risk from a single facial photograph. The tool, described in a Lancet Digital Health paper, includes two algorithms – FAHR‑FaceAge and FAHR‑FaceSurvival – that were trained on more than 40 million diverse face images and focus on different…
Key points
- FAHR-FaceAge estimates biological age and predicts cancer survival from a single facial photograph.
- Patients appearing ≥5 years older than their chronological age had a 21% higher four‑year mortality risk in the study.
- The model was trained on over 40 million diverse facial images and uses distinct facial regions for age and survival predictions.
In a cohort of radiotherapy patients, those whose faces appeared five or more years older than their chronological age faced a 21% higher risk of death over an average four‑year follow‑up, while those appearing five or more years younger had a 17% lower risk. Researchers say lifestyle factors such as heavy alcohol use, drug use and smoking were linked to older‑looking faces. The authors caution that further validation is needed before the approach can be used widely, but suggest it could become a low‑cost, scalable aid for personalising cancer treatment decisions.
New AI tool can predict cancer survival by a single patient selfie, study suggests
The Guardian AI · 19 October 2026
Loading the full article…
This text was published by The Guardian AI and written by Andrew Gregory Health editor. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- Study shows multi-sample network inference robustness varies with prior knowledge and data · 1 src
- Jack Clark says singularity has begun, citing AI test scores · 1 src
- Fudan paper finds four AI search tools cite fabricated concept within a week · 1 src
- MIT researchers strand Claude Opus 4.7 agents on virtual island, observe playful behavior · 1 src
- Google Gemini claims to be ChatGPT after abusive prompts · 1 src
Comments
via GitHub Discussions