This AI tool can predict your cancer survival from selfies
What's the story
Researchers at Mass General Brigham have developed an artificial intelligence (AI) tool that can predict a cancer patient's survival chances from just one photograph of their face. The groundbreaking work was published in the Lancet Digital Health journal. The system uses facial analysis to assess biological age and directly predict survival outcomes for cancer patients.
Training data
How the AI system was trained
The AI system was trained on data from over 40 million facial photographs across different ethnicities and ages.
This extensive training allows the tool to estimate biological age, the age a person looks, rather than their actual chronological age, and predict survival chances for cancer patients from an ordinary photograph of their face.
Tool development
Two tools developed using the technology
The technology was used to develop two complementary tools: FAHR-FaceAge and FAHR-FaceSurvival.
While the former estimates a patient's biological age and predicts cancer survival, the latter directly predicts survival from a facial photograph.
Both algorithms capture different aspects of a patient's health by analyzing distinct parts of the face for respective predictions of age and mortality risk.
Innovation
First AI model to predict cancer survival from photographs
FAHR-FaceSurvival takes facial health recognition AI a step further by learning survival risk directly from facial photographs of cancer patients.
Hugo Aerts, a co-senior author of the study, said this is the first time an AI model has directly predicted cancer survival from a simple photograph.
The tool could help doctors make difficult decisions about treatment options for their patients.
Prediction accuracy
Findings of the study
The study found that among US cancer patients treated with radiotherapy, those who looked five or more years older than their actual age had a 21% higher risk of dying during an average four-year follow-up.
Conversely, those who appeared younger had a 17% lower risk.
This suggests that biological age estimates are closely linked to physical health and could reflect survival ability after certain treatments.
Future applications
AI could assist in treatment decisions for patients
The breakthrough could pave the way for AI facial analysis to assist doctors in making difficult decisions about the best way forward in terms of treatment for their patients.
Dr. Raymond Mak, a radiation oncologist at Mass General Brigham, said, "Our goal is to make face photograph-based health assessment more quantitative, consistent and scalable so it can support personalized treatment decisions rather than replace physician judgment."