{"id":"W3139397034","doi":"10.1109/access.2021.3068614","title":"The Benefits of the Matthews Correlation Coefficient (MCC) Over the Diagnostic Odds Ratio (DOR) in Binary Classification Assessment","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Magyar Tudományos Akadémia; University of Southampton; Belarusian Republican Foundation for Fundamental Research","keywords":"Contingency table; False positive paradox; Computer science; Confusion; Kappa; Confusion matrix; Artificial intelligence; Correlation coefficient; Statistics; Correlation; Data mining; Mathematics; Machine learning; 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"],"consensus_categories":[],"category_scores_codex":[0.07559287,0.002420013,0.002581493,0.01994473,0.002068654,0.005553326,0.002076886,0.003143945,0.001717371],"category_scores_gemma":[0.337135,0.0007283366,0.00173776,0.01428929,0.005832612,0.005786739,0.004757175,0.003793158,0.0008866983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002713126,"about_ca_system_score_gemma":0.002720363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005588192,"about_ca_topic_score_gemma":0.005784216,"domain_scores_codex":[0.9151787,0.04571934,0.009803331,0.01174241,0.0166951,0.0008611576],"domain_scores_gemma":[0.5796528,0.3451814,0.03006835,0.01969668,0.02292696,0.002473744],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001381197,0.0001936833,0.3363019,0.002899016,0.003828669,0.001139804,0.003773888,0.03011442,0.004058939,0.1172728,0.03329439,0.4657413],"study_design_scores_gemma":[0.0002771126,0.002407725,0.2454051,0.002327842,0.00213928,0.007200753,0.003336716,0.2152511,0.013825,0.4415178,0.06478796,0.001523516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1253475,0.03472468,0.7938021,0.009912996,0.002775609,0.0008411826,0.003682369,0.002971377,0.02594236],"genre_scores_gemma":[0.7214788,0.004820824,0.2649333,0.001860808,0.002041773,0.0009144596,0.00120975,0.0006564281,0.002083924],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9244071,"threshold_uncertainty_score":0.3997781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03775231095962638,"score_gpt":0.3249331132441325,"score_spread":0.2871808022845061,"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."}}