{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6145861,0.004178065,0.01180675,0.01249153,0.003024216,0.007753123,0.00398528,0.006215272,0.007030313],"category_scores_gemma":[0.8479232,0.00394589,0.0154161,0.01004383,0.007557563,0.008062926,0.008874269,0.007026286,0.001101621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005247444,"about_ca_system_score_gemma":0.007357867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001127634,"about_ca_topic_score_gemma":0.0024045,"domain_scores_codex":[0.1959254,0.5804358,0.1723572,0.01633686,0.03293256,0.002012291],"domain_scores_gemma":[0.05340837,0.8210357,0.05293177,0.04813585,0.0236543,0.0008339781],"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":[0.01280786,0.001029247,0.1769182,0.148031,0.1682733,0.001324419,0.01403036,0.01123498,0.002743416,0.09189067,0.0182893,0.3534273],"study_design_scores_gemma":[0.01800698,0.01026968,0.1757917,0.0608082,0.1674616,0.00384481,0.003884011,0.09149179,0.01782837,0.3511339,0.09689242,0.002586641],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03807729,0.04404817,0.8350652,0.004819316,0.002965992,0.05997121,0.004088289,0.001591678,0.009372814],"genre_scores_gemma":[0.4920018,0.002913842,0.4313553,0.003630882,0.0009065864,0.06581557,0.001200115,0.000540159,0.001635717],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3854139,"threshold_uncertainty_score":0.475284,"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."}}