● Covered by 1 source · 1 reportMedium impact1 neutral
AI Tool Predicts Cancer Survival from Facial Photographs
Key points
- AI tool predicts cancer survival from a single facial photograph.
- Developed by Mass General Brigham, published in The Lancet Digital Health.
- Estimates biological age (FAHR-FaceAge) and directly predicts survival (FAHR-FaceSurvival).
- Trained on over 40 million facial photographs across diverse demographics.
AI System for Cancer Prognosis
Doctors at Mass General Brigham have created an artificial intelligence tool capable of predicting a cancer patient's survival chances using just one photograph of their face. This custom-built system estimates biological age and directly forecasts survival outcomes for cancer patients.
Methodology and Training
The AI system was trained on a dataset of over 40 million facial photographs, encompassing a wide range of ethnicities and ages. This extensive training allows the model to analyze facial features to assess health indicators relevant to cancer prognosis. The details of this development were published in The Lancet Digital Health journal.
Two Complementary Tools
The technology yielded two distinct but related tools: FAHR-FaceAge and FAHR-FaceSurvival. FAHR-FaceAge estimates a patient's biological age and correlates it with cancer survival. FAHR-FaceSurvival directly predicts survival from a facial photograph without first inferring biological age. Both algorithms utilize different facial regions for their predictions; FAHR-FaceAge focuses on nasolabial creases, forehead, and temples, while FAHR-FaceSurvival examines the area below the eyes and around the nasal bridge.
Significance of Direct Prediction
According to Hugo Aerts, a co-senior author of the study, FAHR-FaceSurvival represents an advancement in facial health recognition AI by learning survival risk directly from patient photographs. This marks the first demonstration of an AI model directly predicting cancer survival from a simple photograph.
Initial Findings
In a study of cancer patients undergoing radiotherapy in the US, individuals whose FAHR-FaceAge indicated they looked five or more years older than their chronological age had a 21% higher risk of mortality over an average four-year follow-up period compared to others in the group.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
The daily brief
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Today's brief
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's brief
New every morning, and the back catalogue is archived by date.
Reporting from
Mass General Brigham researchers developed an AI tool that predicts cancer patient survival rates from a single facial photograph. The system, detailed in The Lancet Digital Health, estimates biological age and directly forecasts survival, offering a new method for assessing patient health.