{"id":"W4399390176","doi":"10.1016/j.jbi.2024.104666","title":"Understanding random resampling techniques for class imbalance correction and their consequences on calibration and discrimination of clinical risk prediction models","year":2024,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"Medical Research Council; Lotto New Zealand; All-India Institute of Medical Sciences; KU Leuven; Natural Sciences and Engineering Research Council of Canada; Stroke Association; European Commission; Fonds Wetenschappelijk Onderzoek; National Heart Foundation of Australia","keywords":"Undersampling; Resampling; Computer science; Estimator; Artificial intelligence; Calibration; Oversampling; Random forest; Machine learning; Brier score; Statistics; Data mining; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002914336,0.00009640722,0.0002650544,0.0003203817,0.00008896012,0.0001688303,0.0001753752,0.0001429808,3.762723e-7],"category_scores_gemma":[0.0006455791,0.00006547768,0.00006391681,0.0002155982,0.000293585,0.001641634,0.00004374264,0.0002493782,4.67399e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007951932,"about_ca_system_score_gemma":0.0001342546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002220162,"about_ca_topic_score_gemma":0.000001078986,"domain_scores_codex":[0.9981642,0.0000865174,0.001258345,0.0001001999,0.0002860677,0.0001047223],"domain_scores_gemma":[0.9976585,0.001172534,0.0008120202,0.0001276614,0.0001442642,0.00008501159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007619318,0.0002925306,0.0007005487,0.001739603,0.0002955573,0.000004262658,0.01136633,0.0005653345,0.005503535,0.2460543,0.02540832,0.7073078],"study_design_scores_gemma":[0.0003766687,0.0006735871,0.00006762973,0.0006868002,0.00002052384,0.00005238578,0.0006019755,0.9424255,0.004301904,0.04992872,0.0008018293,0.00006245638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003290815,0.0001161012,0.9947367,0.0007489674,0.0006546107,0.0002295071,0.00005680876,0.00008733958,0.00007918658],"genre_scores_gemma":[0.900941,0.002170504,0.09666092,0.00007332915,0.0001186949,0.000008934919,0.00001671558,0.000005357698,0.000004542893],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9418602,"threshold_uncertainty_score":0.2670102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1356301825345485,"score_gpt":0.3526789340283135,"score_spread":0.217048751493765,"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."}}