Particle.news

Download on the App Store

AI Tool FaceAge Links Facial Photos to Cancer Survival Predictions

FaceAge, developed by Mass General Brigham, uses deep learning to estimate biological age from facial images, showing promise in improving cancer prognosis accuracy.

Image
Image
Image
Face ID. Future. Half Face of Young Caucasian Woman for Face Detection. Brown Female Eye Biometrical Iris Scan Reading for Person Identification. Augmented Reality. 3D Technology Concept.

Overview

  • FaceAge analyzes facial photographs to estimate biological age, which correlates with health outcomes and survival rates in cancer patients.
  • The tool was trained on nearly 59,000 images of healthy individuals and validated on over 6,200 cancer patients, finding they appear biologically five years older on average.
  • Higher FaceAge scores are strongly linked to worse survival outcomes, particularly when biological age exceeds 85 years.
  • FaceAge outperformed clinicians in predicting short-term life expectancy for patients undergoing palliative radiotherapy, enhancing clinical decision-making.
  • Ongoing research aims to expand FaceAge’s applications to other diseases, evaluate factors like cosmetic interventions, and ensure fairness and ethical use.