{"id":"W3081089509","doi":"10.1186/s12874-020-01095-8","title":"Measuring clinical uncertainty and equipoise by applying the agreement study methodology to patient management decisions","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; University of Alberta Hospital; Centre Hospitalier de l’Université de Montréal; Health Sciences Centre; Ottawa Hospital","funders":"","keywords":"Reliability (semiconductor); Clinical equipoise; Dilemma; Medicine; Warrant; Clinical trial; Randomized controlled trial; Inter-rater reliability; Variety (cybernetics); Portfolio; Medical physics; Computer science; Psychology; Artificial intelligence; Rating scale; Surgery; Pathology; Mathematics","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":[0.08108921,0.0002800287,0.001273933,0.000195535,0.0003592251,0.000041324,0.0007096586,0.0003500371,0.0006528572],"category_scores_gemma":[0.8043064,0.0001725641,0.0002244596,0.0008440009,0.0009190803,0.0000231411,0.002257766,0.00201105,0.0001962618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001002361,"about_ca_system_score_gemma":0.0005717848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003985431,"about_ca_topic_score_gemma":0.000225618,"domain_scores_codex":[0.9542947,0.03745892,0.001780446,0.001522802,0.003658989,0.001284134],"domain_scores_gemma":[0.2684934,0.7245437,0.0002149998,0.001366034,0.0006146541,0.004767284],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002807884,0.001150208,0.02968855,0.00006692499,0.0003581626,0.0005387837,0.00167438,0.00004255141,0.00007842569,0.001008607,0.02122583,0.9413597],"study_design_scores_gemma":[0.04865035,0.07546539,0.2932192,0.006986723,0.002608842,0.0005962963,0.1230408,0.01448304,0.0005948404,0.01549575,0.4164736,0.002385178],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6512899,0.001916385,0.2887691,0.04897266,0.000656707,0.006849377,0.00001231992,0.00009995649,0.001433623],"genre_scores_gemma":[0.6480188,0.002914953,0.318666,0.02581617,0.001055141,0.003065568,0.00002573531,0.00007770939,0.0003599941],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9389745,"threshold_uncertainty_score":0.9462121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7981267890516146,"score_gpt":0.6120079939446796,"score_spread":0.186118795106935,"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."}}