How a photo of a patient’s face could predict whether they’ll survive cancer
Mass General
Mass General· 2 min read
illuminem summarises for you the essential news of the day, reviewed by our editorial team. Read the full piece on The Washington Post or enjoy below:
🗞️ Driving the news: Researchers at Mass General Brigham in Boston have developed FAHR-FaceSurvival, an AI model trained on more than 40 million facial photographs to help predict mortality risk among cancer patients
• Published in The Lancet Digital Health, the study suggests that facial images contain measurable health signals that could complement existing clinical assessments
🔭 The context: The system builds on FaceAge, an earlier model designed to estimate biological age from facial photographs
• Researchers used images and medical outcome data from more than 30,000 cancer patients to train the new mortality-prediction model
• It identified the area beneath the eyes, including the bridge of the nose, as particularly influential in its predictions
• However, scientists do not yet know exactly which physiological features the algorithm detects
🌍 Why it matters for the planet: The research has no direct environmental implications
• Its broader sustainability relevance lies in the potential for low-cost digital tools to expand access to health assessment, provided they are validated, equitable and responsibly deployed
⏭️ What’s next: Researchers say prospective clinical trials and validation across more diverse populations are needed before the technology can be adopted in routine care. They must establish whether facial AI adds meaningful information beyond existing clinical data and whether its use leads to better patient outcomes.
💬 One quote: “Showing that a photograph predicts survival is not the same as showing that it tells us something a clinician doesn’t already know,” said Suchi Saria, a professor at Johns Hopkins University who was not involved in the study.
📈 One stat: Around 50% of cancer patients in the model’s highest-risk 10% died within 90 days, compared with approximately 2% in its lowest-risk 10%. These are study findings, not guarantees of an individual patient’s prognosis.
Subscribe to our free newsletters to never miss a beat in sustainability.
The world needs sustainability knowledge. At illuminem, no interest group or shareholder can influence our work. Thank you for supporting our mission to make high-quality and independent sustainability information free for all. Every contribution helps. Thank you for donating today.
illuminem briefings

AI · Wellbeing
illuminem briefings

Sustainable Business · Climate Change
Seham Farouk

Sustainable Finance · Public Governance
Nikkei Asia

AI · Sustainable Finance
Forbes

AI · Sustainable Lifestyle
Financial Times

AI · Green Tech