{"id":"W2777686840","doi":"10.1016/j.jclinepi.2017.12.015","title":"Technology-assisted risk of bias assessment in systematic reviews: a prospective cross-sectional evaluation of the RobotReviewer machine learning tool","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":54,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Blinding; Medicine; Reliability (semiconductor); Meta-analysis; Confidence interval; Publication bias; Clinical trial; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.1950844,0.001655538,0.005355889,0.005682161,0.0006051481,0.003341333,0.002246253,0.001767243,0.004158854],"category_scores_gemma":[0.4660604,0.001569706,0.008407836,0.004666341,0.0007511431,0.004269643,0.003398088,0.001900111,0.0007310184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001045986,"about_ca_system_score_gemma":0.003988444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007354611,"about_ca_topic_score_gemma":0.001626006,"domain_scores_codex":[0.7618887,0.1771886,0.03484335,0.008722492,0.01680946,0.0005473541],"domain_scores_gemma":[0.2407812,0.636699,0.06790153,0.02898103,0.02458889,0.001048448],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.04760336,0.001626137,0.1843226,0.05177052,0.1329022,0.0003119672,0.003042809,0.01207419,0.002589298,0.003067314,0.01451299,0.5461767],"study_design_scores_gemma":[0.04748929,0.03770396,0.4105503,0.02131177,0.2267097,0.004247021,0.001526481,0.1729047,0.01232741,0.0143356,0.04815428,0.00273951],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4558439,0.07111401,0.410379,0.003949078,0.00150315,0.02739599,0.01895467,0.00548813,0.005372078],"genre_scores_gemma":[0.540786,0.005972688,0.427891,0.0009480119,0.0003880591,0.01984149,0.002780286,0.0004058428,0.00098658],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8049156,"threshold_uncertainty_score":0.9926043,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9262384616759126,"score_gpt":0.7051979300689227,"score_spread":0.2210405316069899,"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."}}