{"id":"W4294647301","doi":"10.1186/s13063-022-06689-9","title":"Overestimation of benefit when clinical trials stop early: a simulation study","year":2022,"lang":"en","type":"article","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Toronto","funders":"","keywords":"Relative risk; Medicine; Early stopping; Interim analysis; Interim; Sprint; Clinical trial; Randomized controlled trial; Confidence interval; Physical therapy; Internal medicine; Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07376135,0.001215726,0.001709555,0.00115444,0.0005345438,0.002191602,0.002173079,0.003008513,0.004385587],"category_scores_gemma":[0.2244613,0.0008748331,0.004413274,0.00136923,0.001733326,0.002136765,0.00178166,0.003625163,0.000412829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00312601,"about_ca_system_score_gemma":0.002496404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004103663,"about_ca_topic_score_gemma":0.002773158,"domain_scores_codex":[0.9462306,0.04910654,0.001363128,0.001379773,0.00112323,0.0007966156],"domain_scores_gemma":[0.372755,0.591674,0.01511045,0.01300055,0.005870381,0.00158963],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01958891,0.002186892,0.04219658,0.001827807,0.004299889,0.000697121,0.001227662,0.8588899,0.0009171483,0.03426291,0.004024403,0.02988077],"study_design_scores_gemma":[0.007945704,0.007982616,0.01078085,0.001145696,0.003006189,0.0006908794,0.0003678745,0.9226304,0.001336815,0.03922856,0.004657572,0.0002269312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8252509,0.005233011,0.148416,0.003196447,0.0002498452,0.003568285,0.002033131,0.000288404,0.01176398],"genre_scores_gemma":[0.9723691,0.0006574745,0.02308238,0.0007455003,0.00006246951,0.001757896,0.0004673767,0.00003357435,0.0008242317],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9262387,"threshold_uncertainty_score":0.390092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.930647252010631,"score_gpt":0.7294744882088581,"score_spread":0.201172763801773,"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."}}