AI tool predicts cancer survival from single facial photograph

Summarised from 3 outlets · Updated 19 Oct, 23:57 · Archive

Researchers have developed an artificial intelligence system that can predict cancer patients' survival chances from a single photograph of their face.

Researchers at Mass General Brigham in Massachusetts have developed an artificial intelligence tool that predicts cancer patients' chances of survival from a single photograph of their face. The AI system was trained on more than 40 million facial photographs across a range of ethnicities and ages. The study was published in Lancet Digital Health.

Doctors created two complementary tools from the model. FAHR-FaceAge estimates a patient's biological age – how old they appear rather than their actual age – and predicts cancer survival. FAHR-FaceSurvival predicts survival directly from a facial photograph without inferring it through biological age. The algorithms focus on different facial features: FAHR-FaceAge examines the creases running from the nose to the mouth, the forehead above the eye sockets and the temples, while FAHR-FaceSurvival evaluates the region below the eyes and around the nasal bridge.

Hugo Aerts, professor at Harvard University and director of the AI in medicine programme at Mass General Brigham, said the work "advances the field of facial health recognition AI a step further by learning survival risk directly from facial photographs of patients with cancer". He added: "To our knowledge, this is the first demonstration that an AI model can directly predict cancer survival from a simple photograph." Raymond Mak, associate professor of radiation oncology at Harvard Medical School, said the team was surprised by how consistent the study's findings were across variations in pose, lighting, facial expression and makeup.

How it is being reported

• Cancer breakthrough as a single selfie could reveal your chance of surviving the deadly diseaseA deep-learning AI tool is being used to find out a person's chance of surviving cancer treatment and their biological ageThe Mirror · 20 Oct, 00:04
• You can detect biological age and a person's chance of surviving cancer 'with just one photo'An AI tool was trained on more than 40 million pictures to determine key indicators of a person's healthThe Independent · 19 Oct, 23:30
• New AI tool can predict cancer survival by a single patient selfie, study suggestsSystem can estimate a person’s biological age and predict chances of cancer survival from a single photograph Doctors have developed an artificial intelligence tool that can predict a cancer patient’s chances of survival from a single photograph of their face. The AI system was custom-built by experts at Mass General Brigham, a nonprofit, integrated academic healthcare system in Massachusetts, to estimate biological age and directly predict survival outcomes in patients diagnosed with cancer. Continue reading...The Guardian · 19 Oct, 23:30

In this story: Mass General Brigham · Massachusetts · Hugo Aerts · Harvard University · Raymond Mak

This summary was written by AI from the headlines and standfirsts above, and states as fact only what at least two outlets report. How we use AI · Report a problem