Decoding biological age from face photographs using deep learning

Authors:
DPID: 143Published:

Abstract

FaceAge, a deep learning system, estimates biological age from facial photographs, trained on 58,851 individuals and validated on 6,196 cancer patients. It proved prognostically relevant, showing cancer patients typically appear older than their chronological age, correlating with worse survival. FaceAge enhances end-of-life predictions for palliative care patients and is linked to molecular senescence mechanisms, demonstrating its potential in clinical decision-making beyond cancer.