{"id":"W2971543728","doi":"10.1136/bmjopen-2018-024625","title":"Empirical evaluation of SUCRA-based treatment ranks in network meta-analysis: quantifying robustness using Cohen’s kappa","year":2019,"lang":"en","type":"article","venue":"BMJ Open","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":87,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; St. Joseph’s Healthcare Hamilton; University of Toronto; McMaster University; Children's Hospital of Eastern Ontario; Impact","funders":"","keywords":"Kappa; Medicine; Robustness (evolution); Meta-analysis; Statistics; Mathematics; Combinatorics; Internal 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":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.570354,0.004414081,0.0114118,0.01902638,0.003706119,0.01166983,0.008435192,0.007219225,0.003393652],"category_scores_gemma":[0.8253879,0.00232432,0.0234058,0.01442146,0.01251354,0.008958871,0.00937494,0.008097659,0.0004658145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005115947,"about_ca_system_score_gemma":0.004253832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003587659,"about_ca_topic_score_gemma":0.002896412,"domain_scores_codex":[0.2681448,0.5983108,0.05862581,0.04128262,0.03188054,0.001755476],"domain_scores_gemma":[0.06117672,0.8527457,0.04016136,0.03382652,0.01123093,0.0008588425],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006495505,0.0002838064,0.2323649,0.04995,0.3793046,0.001140556,0.005284435,0.1000848,0.002488684,0.03989356,0.008488447,0.1742207],"study_design_scores_gemma":[0.00284694,0.004591519,0.119341,0.02054995,0.1513828,0.002707728,0.003515396,0.3035133,0.009497623,0.3494447,0.03039898,0.002210057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07502857,0.06756198,0.8327257,0.006672467,0.001942534,0.004524589,0.00463353,0.001713304,0.005197348],"genre_scores_gemma":[0.7934437,0.002716324,0.1929207,0.001969503,0.0005642442,0.006163642,0.001471789,0.0003648125,0.0003853639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9885882,"threshold_uncertainty_score":0.5298301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9733493916709587,"score_gpt":0.6926810856945466,"score_spread":0.2806683059764121,"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."}}