AI model predicts cancer survival from facial images, but bias concerns emerge

Researchers have developed an AI model called FAHR-Face, trained on over 40 million facial images, to assess biological age and predict cancer patient survival. While the model showed associations with survival in some cancer types, its effectiveness was not consistent across all categories and notably showed a lack of association for Black patients, raising concerns about racial bias. The study's authors acknowledge the need for further testing against clinical judgment and across diverse patient groups, highlighting that a selfie's predictive power for future health outcomes remains uncertain. AI

IMPACT Raises questions about the reliability and potential biases of AI in medical diagnostics, particularly concerning diverse patient populations.

RANK_REASON AI model research published in a medical journal. [lever_c_demoted from research: ic=1 ai=1.0]

Read on The Guardian — AI →

• cardiac magnetic resonance imaging
• Devi Sridhar
• FAHR-Face
• FAHR-FaceAge
• FAHR-FaceSurvival
• Hippocrates
• Mass General Brigham
• Miroslaw Bober
• The Lancet Digital Health

• model release
• safety
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →