{"id":"W3088642850","doi":"10.1016/j.jclinepi.2020.09.033","title":"Methodologically rigorous risk of bias tools for nonrandomized studies had low reliability and high evaluator burden","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University; Université de Montréal; University of Ottawa; Institute of Health Economics; St. Michael's Hospital; University of Manitoba; Centre Hospitalier de l’Université de Montréal; University of Toronto; George & Fay Yee Centre for Healthcare Innovation","funders":"","keywords":"Inter-rater reliability; Reliability (semiconductor); Medicine; Psychological intervention; Psychology; Physical therapy; Statistics; Mathematics; Psychiatry; Rating scale","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"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4557157,0.0002570131,0.006808425,0.00008502175,0.0001171677,0.00003263578,0.0009845854,0.0004024046,0.0001964303],"category_scores_gemma":[0.9642429,0.000129344,0.001776331,0.0002504448,0.001129912,0.0002588607,0.0002716594,0.0008992262,0.00001207305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003194634,"about_ca_system_score_gemma":0.0002397588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001720515,"about_ca_topic_score_gemma":0.000004412062,"domain_scores_codex":[0.9162431,0.06430107,0.01647837,0.000971187,0.001531868,0.0004744425],"domain_scores_gemma":[0.1577268,0.823528,0.01299087,0.0007457848,0.004398854,0.0006096778],"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":[0.05423428,0.0009717579,0.3662383,0.0002807779,0.002173559,0.00001637572,0.0009995799,0.02002593,0.0004300303,0.002303809,0.03097425,0.5213513],"study_design_scores_gemma":[0.02115833,0.01120088,0.1809663,0.0001394548,0.0007871204,0.00001232432,0.001020171,0.008884717,0.0001338628,0.7578323,0.01757284,0.0002916586],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.851627,0.001937948,0.09220515,0.05211805,0.001318684,0.0007204452,0.00003375594,0.000008378008,0.00003061358],"genre_scores_gemma":[0.7504053,0.005597329,0.2385682,0.0040881,0.001284872,0.00001797531,8.572713e-7,0.000008997172,0.00002834611],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7592269,"threshold_uncertainty_score":0.5604553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8644908462866121,"score_gpt":0.6267974750429381,"score_spread":0.237693371243674,"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."}}