{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05034084,0.0008197676,0.001039366,0.00142216,0.0008321108,0.002932954,0.002189723,0.002483538,0.0008525638],"category_scores_gemma":[0.2116197,0.0006667995,0.0008532367,0.001306333,0.002057952,0.003706425,0.002273655,0.003608114,0.0002724986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0010871,"about_ca_system_score_gemma":0.001885932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00222984,"about_ca_topic_score_gemma":0.002355205,"domain_scores_codex":[0.9817284,0.01355511,0.0006621412,0.001288161,0.002434863,0.0003313715],"domain_scores_gemma":[0.8274956,0.1514396,0.005458893,0.008756405,0.00639114,0.0004582647],"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":[0.0003419116,0.0002427154,0.0216377,0.0003544846,0.0003947101,0.0004424601,0.00170008,0.2898605,0.006826519,0.322088,0.005237577,0.3508734],"study_design_scores_gemma":[0.00003869666,0.0000795469,0.003436044,0.0001059016,0.00005842598,0.0002351109,0.0001721846,0.7923135,0.003319988,0.1982479,0.001945101,0.00004770318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.019851,0.0006082001,0.9770091,0.001588298,0.0001063908,0.00005169207,0.00004286073,0.0001334066,0.000609146],"genre_scores_gemma":[0.4827227,0.001236228,0.5124245,0.001052226,0.0006122025,0.0002771243,0.0002453107,0.0001531577,0.001276511],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9496592,"threshold_uncertainty_score":0.2662309,"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."}}