{"id":"W2889900146","doi":"10.2217/cer-2018-0035","title":"Some issues for the evaluation of noninferiority trials","year":2018,"lang":"en","type":"article","venue":"Journal of Comparative Effectiveness Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre","funders":"H2020 European Research Council","keywords":"Medicine; Confidence interval; Margin (machine learning); Adjuvant therapy; Placebo; Medical physics; Cancer; Internal medicine; Alternative medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.873785,0.004333627,0.0124294,0.01244092,0.005255637,0.02013014,0.01604139,0.0276387,0.006816913],"category_scores_gemma":[0.9390764,0.00392421,0.01659859,0.01168622,0.05051873,0.02517991,0.009910557,0.04141298,0.002556264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01343635,"about_ca_system_score_gemma":0.01870864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002559288,"about_ca_topic_score_gemma":0.002368615,"domain_scores_codex":[0.0726471,0.786211,0.09735988,0.01039338,0.03204947,0.001339093],"domain_scores_gemma":[0.01589455,0.9341443,0.01401612,0.01764719,0.01726621,0.001031613],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.007666081,0.0004064823,0.005116284,0.04601904,0.01026792,0.0009753455,0.01099043,0.003737252,0.0007152499,0.4590389,0.1146961,0.3403709],"study_design_scores_gemma":[0.006126158,0.002561263,0.003812991,0.06561202,0.003281878,0.001147896,0.002125965,0.0113448,0.001857079,0.687676,0.2138094,0.0006444989],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.003687672,0.1199006,0.3211085,0.4781757,0.05522547,0.01006746,0.0008753733,0.000811274,0.01014795],"genre_scores_gemma":[0.06962612,0.0166015,0.5699927,0.2386965,0.0561447,0.04575296,0.0003676169,0.0006082394,0.002209675],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.126215,"threshold_uncertainty_score":0.1556457,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9613010515836794,"score_gpt":0.7999582645757043,"score_spread":0.1613427870079751,"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."}}