{"id":"W2955606726","doi":"10.1016/j.conctc.2019.100402","title":"An alternative trial-level measure for evaluating failure-time surrogate endpoints based on prediction error","year":2019,"lang":"en","type":"article","venue":"Contemporary Clinical Trials Communications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Cancer Research; Institut National Du Cancer; Ligue Contre le Cancer","keywords":"Statistics; Correlation; Surrogate endpoint; Standard error; Clinical trial; Measure (data warehouse); Mathematics; Medicine; Computer science; Data mining; Internal medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1479213,0.0005999134,0.003513604,0.0002475942,0.0004445593,0.0001866472,0.002757259,0.0007892741,0.0006218462],"category_scores_gemma":[0.6064066,0.0005101421,0.001549169,0.0004309557,0.0005447686,0.0004083724,0.0003277162,0.001369339,0.0003444482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001399689,"about_ca_system_score_gemma":0.0009662957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001368323,"about_ca_topic_score_gemma":0.00001158191,"domain_scores_codex":[0.9381815,0.05057046,0.00824679,0.00129732,0.001163504,0.0005404343],"domain_scores_gemma":[0.5517452,0.4381197,0.003334894,0.00529629,0.001040846,0.00046301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.4205584,0.04190158,0.005412668,0.0009985949,0.005859329,0.00001451084,0.001011438,0.0008157504,0.009067998,0.2418953,0.07860608,0.1938584],"study_design_scores_gemma":[0.1547398,0.01183686,0.0004318289,0.0009882904,0.0007731433,0.00000108059,0.000165018,0.2377802,0.0005792241,0.587988,0.003809145,0.0009074181],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06638074,0.0003251825,0.7910889,0.02213336,0.01209586,0.06686768,0.01557255,0.002083661,0.02345211],"genre_scores_gemma":[0.417753,0.00001745866,0.5782912,0.0007874637,0.0009189315,0.001373423,0.0002811905,0.0001320129,0.0004452576],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4584853,"threshold_uncertainty_score":0.999735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9352083243389143,"score_gpt":0.6897237555682655,"score_spread":0.2454845687706488,"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."}}