{"id":"W4410197107","doi":"10.1016/j.landig.2025.03.002","title":"FaceAge, a deep learning system to estimate biological age from face photographs to improve prognostication: a model development and validation study","year":2025,"lang":"en","type":"article","venue":"The Lancet Digital Health","topic":"Telomeres, Telomerase, and Senescence","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre","funders":"H2020 European Research Council; European Research Council; National Institutes of Health","keywords":"Artificial intelligence; Deep learning; Computer science; Face (sociological concept); Computer vision; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004014516,0.0001663047,0.0004333853,0.00008983898,0.0002203408,0.0001227642,0.0001396137,0.00004154021,0.000002632126],"category_scores_gemma":[0.0003264583,0.0001105306,0.00002379143,0.0003556985,0.00003180761,0.00006554122,0.0001220156,0.0001750509,0.00002421701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009588081,"about_ca_system_score_gemma":0.0001457002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008728062,"about_ca_topic_score_gemma":0.00004854929,"domain_scores_codex":[0.9986336,0.00007827127,0.0003414994,0.000405162,0.0001940798,0.0003474396],"domain_scores_gemma":[0.999144,0.0002302765,0.00007714072,0.0002797747,0.00005670755,0.0002120918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002253089,0.001022613,0.3222708,0.001092866,0.0002854284,0.00007047707,0.05686518,0.001649256,0.0008698593,0.0007769194,0.001049083,0.6117945],"study_design_scores_gemma":[0.003936423,0.002694991,0.9323695,0.001846303,0.00008363477,0.00002301427,0.02009404,0.03085812,0.001343395,0.0003065827,0.005742317,0.0007016305],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9780647,0.0001535509,0.01702371,0.001504699,0.00005489093,0.002335911,0.00007029174,0.0002182762,0.0005740024],"genre_scores_gemma":[0.9934793,0.00001043678,0.004880263,0.0009299874,0.00004361979,0.0002611138,0.0001374944,0.000011044,0.0002467812],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6110928,"threshold_uncertainty_score":0.4507306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04725634595743487,"score_gpt":0.3515246378157204,"score_spread":0.3042682918582855,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}