{"id":"W4408808277","doi":"10.6000/1929-6029.2025.14.16","title":"A Choice of Performance Metrics for Evaluating Predictive Accuracy of Survival Models","year":2025,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Statistics; Econometrics; Machine learning; Artificial intelligence; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06457327,0.00009047695,0.0007714161,0.001767379,0.00005023498,0.00002774489,0.0009718114,0.0001332241,0.0001871284],"category_scores_gemma":[0.2362654,0.000100337,0.00008768918,0.0005292162,0.0002372359,0.0003249329,0.000144972,0.0005803797,0.000005530964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006726585,"about_ca_system_score_gemma":0.001729246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003414103,"about_ca_topic_score_gemma":0.00006218916,"domain_scores_codex":[0.9925914,0.0005283979,0.004975999,0.0002115486,0.00141027,0.0002824147],"domain_scores_gemma":[0.9598808,0.03408584,0.002417138,0.0001790477,0.003296233,0.0001408891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006569969,0.0006057281,0.0777592,0.001425923,0.0005177924,0.000007267578,0.00187473,0.009036647,0.0000150446,0.87643,0.007974816,0.0236958],"study_design_scores_gemma":[0.002948479,0.000556403,0.01932317,0.001308326,0.00001004841,0.000003753109,0.0009739272,0.7310881,0.00006338168,0.2400985,0.003519753,0.0001061905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1797753,0.001507846,0.8024968,0.009427438,0.001729179,0.0005975175,0.001068186,0.000003266339,0.003394515],"genre_scores_gemma":[0.9686218,0.001203266,0.02941493,0.000317777,0.000240756,0.0000306791,0.00001661302,0.00001214,0.0001420358],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7888466,"threshold_uncertainty_score":0.9632187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6491725716129512,"score_gpt":0.6344758245705483,"score_spread":0.01469674704240287,"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."}}