{"id":"W2036246082","doi":"10.1097/01.blo.0000218736.23506.fe","title":"Misuse of Baseline Comparison Tests and Subgroup Analyses in Surgical Trials","year":2006,"lang":"en","type":"article","venue":"Clinical Orthopaedics and Related Research","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Medicine; Subgroup analysis; Baseline (sea); Surgery; Internal medicine; Meta-analysis","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":["metaresearch"],"category_scores_codex":[0.84582,0.003006974,0.01140665,0.01821682,0.002188917,0.01057937,0.01004816,0.008067969,0.003063532],"category_scores_gemma":[0.9479514,0.002968241,0.01320152,0.02432781,0.0164439,0.01204955,0.0079495,0.01303866,0.001007257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006663788,"about_ca_system_score_gemma":0.01026476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001300669,"about_ca_topic_score_gemma":0.001099883,"domain_scores_codex":[0.03996156,0.8513632,0.07157532,0.008379182,0.02793398,0.0007868345],"domain_scores_gemma":[0.02106538,0.8989288,0.04002529,0.02912007,0.01018462,0.0006759025],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01548579,0.0003334123,0.04785729,0.06641289,0.05835474,0.001574524,0.01272057,0.009582095,0.00110407,0.1246202,0.04618737,0.6157671],"study_design_scores_gemma":[0.009815957,0.007371467,0.02945026,0.03469083,0.02200437,0.003057705,0.00427754,0.05011155,0.008927488,0.7374002,0.09177376,0.001118912],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0265773,0.09217595,0.7597951,0.07041667,0.02212245,0.01356583,0.002872342,0.002238122,0.01023632],"genre_scores_gemma":[0.4162829,0.01115525,0.4965785,0.03453602,0.0107308,0.0277099,0.0009939926,0.0009286127,0.001083998],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.15418,"threshold_uncertainty_score":0.1901315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8003229579301212,"score_gpt":0.6608809571201206,"score_spread":0.1394420008100006,"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."}}