{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2418049,0.0002717421,0.004353459,0.0001893644,0.0001910918,0.0000513553,0.0004972398,0.0001876918,0.004998537],"category_scores_gemma":[0.7702074,0.0002277843,0.0008808915,0.000324816,0.0001003231,0.0001037116,0.0003590203,0.000537109,0.00002934411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009338888,"about_ca_system_score_gemma":0.0001251993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005521736,"about_ca_topic_score_gemma":0.000002858535,"domain_scores_codex":[0.897939,0.08084183,0.01731611,0.001056736,0.002330692,0.0005155831],"domain_scores_gemma":[0.3290457,0.6628486,0.006365505,0.001200867,0.0003377184,0.0002016124],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.03577219,0.0246005,0.02716882,0.0005349742,0.005049829,0.00006874777,0.0104205,0.01913521,0.00131486,0.35877,0.01312632,0.5040381],"study_design_scores_gemma":[0.009587346,0.002224635,0.005032802,0.00003125659,0.001146936,7.006247e-7,0.0003901569,0.003833283,0.0001338273,0.9770879,0.0002838646,0.0002473636],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7595259,0.00007689002,0.2208381,0.0003152211,0.004401142,0.01249092,0.00110244,0.0002620225,0.0009873622],"genre_scores_gemma":[0.7370155,0.000004690932,0.2612608,0.00008054027,0.000842644,0.0003820178,0.000006944744,0.00005328617,0.0003534963],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6183178,"threshold_uncertainty_score":0.995911,"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."}}