{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1605423,0.00176866,0.003150961,0.004961167,0.0005390497,0.002770288,0.002869743,0.003596313,0.002460162],"category_scores_gemma":[0.3831406,0.0005380023,0.005830757,0.005610864,0.002114342,0.00422663,0.003182186,0.003417906,0.0004390031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001699646,"about_ca_system_score_gemma":0.001719822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007319207,"about_ca_topic_score_gemma":0.0004977479,"domain_scores_codex":[0.8535874,0.1126658,0.01339074,0.007836914,0.01187791,0.0006412433],"domain_scores_gemma":[0.4513689,0.474885,0.03238302,0.02765953,0.01245683,0.001246818],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01193278,0.0007403133,0.1566658,0.01298012,0.05627048,0.0006832797,0.001346318,0.4029272,0.006955621,0.08096431,0.007602771,0.2609309],"study_design_scores_gemma":[0.003022894,0.01691603,0.1096554,0.003403269,0.02067454,0.002152365,0.0004369357,0.61505,0.01595915,0.1876375,0.02417844,0.0009135665],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05425206,0.01039848,0.9265512,0.001040404,0.0006355366,0.001172983,0.002526009,0.000507656,0.00291569],"genre_scores_gemma":[0.745749,0.001715234,0.2411546,0.001708255,0.0004729127,0.004211967,0.003500746,0.0002764851,0.001210733],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8394578,"threshold_uncertainty_score":0.8490388,"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."}}