{"id":"W4381487215","doi":"10.1016/j.jbi.2023.104426","title":"A statistical comparison between Matthews correlation coefficient (MCC), prevalence threshold, and Fowlkes–Mallows index","year":2023,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Statistics; Correlation coefficient; Cohen's kappa; Correlation; Statistic; Brier score; Kappa; Mathematics; Computer science; Data mining; Econometrics","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":[],"category_scores_codex":[0.01418516,0.000785809,0.001336107,0.009798327,0.001161573,0.002221388,0.001436556,0.001361283,0.001176722],"category_scores_gemma":[0.08341973,0.0003406857,0.0008579608,0.006313571,0.001407819,0.002528606,0.00125935,0.001089983,0.0004588624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001187231,"about_ca_system_score_gemma":0.00200524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005054444,"about_ca_topic_score_gemma":0.005725741,"domain_scores_codex":[0.99147,0.002131791,0.001115876,0.001998839,0.002848296,0.0004351477],"domain_scores_gemma":[0.9208218,0.053034,0.007919657,0.005322612,0.01095923,0.001942692],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002607984,0.0004215231,0.7289428,0.0006505018,0.001863396,0.0004640812,0.0007597688,0.02118133,0.003977794,0.006681166,0.0161453,0.2163044],"study_design_scores_gemma":[0.000234855,0.002442947,0.5082968,0.0002103751,0.001250307,0.002912913,0.002159322,0.4441082,0.01079372,0.0182454,0.008941609,0.0004035601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9030347,0.006610299,0.07820574,0.0009851948,0.0006389063,0.0002546223,0.004519541,0.001737068,0.004013984],"genre_scores_gemma":[0.9702153,0.0004361729,0.02600976,0.00006979779,0.0001852567,0.0001213128,0.002259049,0.0001058691,0.0005973607],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9858148,"threshold_uncertainty_score":0.07501918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03000122756346132,"score_gpt":0.3158772012061198,"score_spread":0.2858759736426585,"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."}}