AI model estimates cancer patients' survival from a single face photo
Physician in the Loop, Oct 21, 2026
Listen to this post
read by AI voices ยท all episodesTHE SHORT READ
Mass General Brigham researchers reported Oct. 19 that an AI model trained on more than 40 million face photographs predicted survival in cancer patients, sorting them into risk groups whose mortality differed more than threefold.
The study, published in The Lancet Digital Health, tested the model in two independent cancer cohorts, and the authors said a face photo could help with risk stratification when other biomarkers are unavailable. No prospective clinical use has been reported. Separately, the Food and Drug Administration finalized guidance on how drugmakers label apps sold for use with prescription drugs, Radical Numerics said phages designed by its AI model were given to a patient with a drug-resistant infection, and Intuitive reported that da Vinci procedures grew about 14% in the third quarter.
THE DETAILS
- FYIEvidence Oct 19, 2026The Mass General Brigham model, FAHR-Face, was fine-tuned into two tools: FAHR-FaceAge, which estimates biological age with a mean absolute error of 5.1 years on public datasets, and FAHR-FaceSurvival, trained on 34,363 photographs of patients with cancer. Patients in the highest-risk quartile of FAHR-FaceSurvival had more than triple the mortality of the lowest quartile after adjustment for clinical prognostic factors (hazard ratio 3.23), and the results held in an independent cohort, the authors reported. The two tools drew on different facial regions, and combining them improved prognostic accuracy. Dr. Raymond Mak, a radiation oncologist and the corresponding author, said the aim is to support treatment decisions "rather than replace physician judgment," according to Becker's. The health system said it has filed a provisional patent application on facial health algorithms.
- FYIRegulation Oct 20, 2026The guidance, Regulatory Considerations for Prescription Drug Use-Related Software, finalizes a September 2023 draft and was published in the Federal Register Oct. 21. Software tied to a device used with the drug, such as an app paired with an asthma inhaler, generally should be described in the prescribing information; standalone apps such as symptom trackers, dose reminders and coaching tools belong there only if the drugmaker shows they are essential to safe and effective use or deliver a meaningful clinical benefit, the agency said. Content most companion apps show users will be treated as promotional labeling. Jared Seehafer, FDA deputy commissioner for technology, said companion apps "are quickly moving beyond simple dose reminders toward tools that adapt to each patient."Sources: FDA, Federal Register
- FYIEvidence Oct 20, 2026A phage cocktail containing designs from Omnii-1, the company's genome language model, cleared the patient's resistant bacterial isolate in laboratory testing before it was given through a physician-led compassionate-use pathway, the company said Oct. 20. It described the case as the first clinical use of AI-designed phages. The company did not name the bacterium, the hospital or the treating physicians and did not disclose the patient's clinical course or outcome. It said observations from one patient cannot establish safety or efficacy, the therapies are not approved for broader use, and no paper on the case has been published.Source: Radical Numerics
- FYIMoney Oct 20, 2026Worldwide da Vinci procedures rose about 14% from a year earlier and procedures on its Ion system about 31%, the company said in its Oct. 20 earnings release. It placed 546 da Vinci systems, 315 of them da Vinci 5, bringing the installed base to 12,094, and revenue rose 22% to $3.05 billion. Intuitive put full-year 2026 da Vinci procedure growth at about 14% to 15%. Chief Executive Dave Rosa said customers performed more than 10,000 procedures a day on average.Source: Intuitive (SEC filing)
- FYIEvidence Oct 20, 2026Daymark Health's program, launched in April 2025 with Blue Cross & Blue Shield of Rhode Island across 20 oncology practices, was associated with 10.4% fewer hospital admissions and 8.1% lower total spending than projected, or $789 per patient per month, Healthcare IT News reported Oct. 20. The analysis compared claims after launch with trends projected from two prior years and had no randomized control group; the authors wrote that it shows an association, not causation. The findings were presented as an ASCO abstract.Source: Healthcare IT News