Decoding biological age from face photographs using deep learning
Authors:Osbert Zalay,Dennis Bontempi,Danielle S Bitterman,Nicolai Birkbak,Derek Shyr,Fridolin Haugg,Jack M Qian,Hannah Roberts,Subha Perni,Vasco Prudente,Suraj Pai,Andre Dekker,Benjamin Haibe-Kains,Christian Guthier,Tracy Balboni,Laura Warren,Monica Krishan,Benjamin H Kann,Charles Swanton,Dirk De Ruysscher,Raymond H Mak,Hugo JWL Aerts
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.