Opinion: AI model predicts cancer survival from selfies, but its usefulness is uncertain
Researchers at Mass General Brigham have built a suite of AI tools called FAHR‑Face. The facial‑age estimator, FAHR‑FaceAge, was trained on more than 40 million facial images, while the survival predictor, FAHR‑FaceSurvival, used almost 35,000 photos of cancer patients. The models focus on facial regions historically linked to health, such as the forehead, wrinkles, and the area below the eyes.
Key points
- Researchers at Mass General Brigham trained FAHR‑Face on >40 million facial images and ~35,000 cancer patient photos.
- AI‑estimated facial age correlated with survival in 18 of 28 cancer types, but not for Black patients after adjustment.
- Authors say the tool still needs testing against doctors and across hospitals before clinical use.
The Lancet Digital Health paper reports that AI‑estimated facial age was significantly associated with survival in 18 of 28 cancer categories, but the association vanished for Black patients after adjusting for other factors. Dr Raymond Mak, a study author, notes the link to ancient observations of muscle wasting. Prof Miroslaw Bober cautions that the tool still needs testing against doctors’ judgments and across diverse hospitals and patient groups. The article’s author, Prof Devi Sridhar, warns that lighting, cosmetics, and anti‑ageing treatments could distort predictions, and argues that a selfie‑based estimate is far from a proven clinical prognostic tool.
The story so far
2 episodes →- Opinion: AI model predicts cancer survival from selfies, but its usefulness is uncertainthis story
Can AI really predict cancer survival better than a doctor? I have my doubts
The Guardian AI · 23 October 2026
Loading the full article…
This text was published by The Guardian AI and written by Devi Sridhar. 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 →- MIT historian says early AI engineers added randomness to mimic human creativity · 1 src
- Researchers introduce MemPlan for text-based planning with PDDL · 1 src
- Researchers present CiteAnchor framework for detecting hallucinated citations · 1 src
- Researchers find self‑rewarded moral argumentation makes language models decisive but pliable · 1 src
- AQL-Lite improves Arabic LLMs with curated data and partial-parameter training · 1 src
Comments
via GitHub Discussions