{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008150054,0.0001338964,0.0001321764,0.00006267447,0.0003585224,0.0004395362,0.002355178,0.00007324928,0.00001056938],"category_scores_gemma":[0.0003795396,0.00007425178,0.00005997319,0.001183884,0.0001375651,0.000642177,0.0004476005,0.000258565,0.00000834302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001550722,"about_ca_system_score_gemma":0.0002427933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004670306,"about_ca_topic_score_gemma":0.0001378978,"domain_scores_codex":[0.9979961,0.0003964017,0.0004911302,0.0003596259,0.0005452432,0.0002115166],"domain_scores_gemma":[0.9961813,0.001458182,0.0004168305,0.001677325,0.0002401651,0.00002620617],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00001606298,0.0007093283,0.11631,0.00005366749,0.0000401649,0.000005871512,0.00124661,0.03784282,0.01651992,0.7345913,0.01807968,0.07458457],"study_design_scores_gemma":[0.0001397703,0.0000136038,0.7935044,0.00005504698,0.000007135714,0.000003412184,0.00004363647,0.1887884,0.01483087,0.001273684,0.001249684,0.00009045138],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.217321,0.0002958566,0.7693207,0.009341759,0.00161703,0.0009808454,0.00002694538,0.0001156477,0.0009802441],"genre_scores_gemma":[0.9983118,0.000217456,0.0005933002,0.0004715201,0.00004133883,0.0002092883,0.00001705494,0.0000101037,0.0001281988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7809908,"threshold_uncertainty_score":0.4376547,"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."}}