{"id":"W6902169149","doi":"10.6084/m9.figshare.22606970.v1","title":"Additional file 1 of The Matthews correlation coefficient (MCC) should replace the ROC AUC as the standard metric for assessing binary classification","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Metric (unit); Binary number; Receiver operating characteristic; Correlation coefficient; Correlation; Pattern recognition (psychology)","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003182028,0.001198354,0.00124317,0.003114281,0.0008142305,0.002223653,0.001969226,0.001682505,0.8567104],"category_scores_gemma":[0.07876533,0.0006639795,0.001191506,0.003449656,0.0004054748,0.00247569,0.001170997,0.001399908,0.2765569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001116959,"about_ca_system_score_gemma":0.001946875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003933884,"about_ca_topic_score_gemma":0.007530768,"domain_scores_codex":[0.9984072,0.0004019335,0.000290158,0.000342546,0.0003720777,0.0001861084],"domain_scores_gemma":[0.9120545,0.07382768,0.00279815,0.003734943,0.006639961,0.0009447418],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001985226,0.00004955426,0.001735799,0.00112594,0.00002889355,0.00004019856,0.00002809035,0.0002981754,0.00005084652,0.0006704809,0.9860806,0.009692894],"study_design_scores_gemma":[0.002261573,0.0002113373,0.01981553,0.003461083,0.0001584336,0.0006632016,0.0002876269,0.002941459,0.001156111,0.02366501,0.9451863,0.0001922297],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.0002927405,0.00004324632,0.0008256622,0.00039174,0.00008399691,0.00008159581,0.9947429,0.001290438,0.002247695],"genre_scores_gemma":[0.0148593,0.0003378538,0.009874973,0.001806708,0.0004762195,0.00200696,0.9443542,0.005113986,0.02116973],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9968179,"threshold_uncertainty_score":0.2043851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2187583996844545,"score_gpt":0.3827402006888099,"score_spread":0.1639818010043554,"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."}}