FaceAge as a biomarker for prognosis and treatment stratification in large-scale oncology cohort
A partir de données cliniques portant sur 24 556 patients âgés de plus de 60 ans et atteints d'un cancer traité par radiothérapie entre 2008 et 2023, cette étude examine, en fonction du sexe, la valeur pronostique de l'extrême différence entre l'âge basé sur les caractéristiques du visage et l'âge chronologique
Humans age at different rates and facial characteristics may yield insight into biological age and physiologic health. FaceAge, a deep learning system estimating biological age from facial photographs, has shown potential as a biomarker for cancer prognosis. This study investigates the prognostic value of extreme discordance between FaceAge and chronological age (FaceAge–Age) in predicting survival and early mortality across a large clinical dataset of 28 cancer types.Data from 24,556 cancer patients aged ≥60 treated with radiation therapy between 2008–2023 were analyzed. FaceAge estimates were compared with chronological age across different diagnoses/clinical contexts, and survival analyses were performed. All tests were two-sided.FaceAge was older than chronological age in 65% (median FaceAge 74 versus age 70). Younger patients, female sex, diagnoses with worse prognosis, and treated for palliative intent had higher likelihood of FaceAge–Age ≥10 years. Patients with FaceAge–Age ≥10 years had significantly worse survival while those with FaceAge–Age ≤-5 years had better survival. On multivariate analysis, FaceAge–Age ≥10 years predicted higher mortality risk (HR 1.26, P<.001) and early mortality at 30 days (OR 1.38, P=.004) and 60 days (OR 1.33, P<.001), whereas FaceAge–Age ≤-5 years predicted lower mortality risk (HR 0.90, P<.001).Patients with more advanced cancers tend to have significantly older FaceAge compared with age, and extreme discordance between FaceAge and chronological age is a novel, independent predictor of survival and early mortality. These findings support further development of facial health assessments for clinical prognostication models and personalized treatment decision-making.
Journal of the National Cancer Institute , résumé, 2025