{"id":"W3089158044","doi":"10.1007/s11548-020-02260-6","title":"Assessing and mitigating the effects of class imbalance in machine learning with application to X-ray imaging","year":2020,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"ca_institutions":"St. Francis Xavier University; Ontario Institute for Cancer Research; University of Toronto","funders":"","keywords":"Undersampling; Oversampling; Artificial intelligence; Machine learning; Computer science; Class (philosophy); Random forest; Convolutional neural network; Set (abstract data type); Pattern recognition (psychology); Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.01185064,0.001046536,0.001388175,0.001886336,0.001047594,0.002243965,0.001170326,0.001323701,0.0006303837],"category_scores_gemma":[0.03711297,0.0003259146,0.0006551342,0.001433777,0.0009061145,0.002386184,0.002107498,0.002032921,0.0002757937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006508203,"about_ca_system_score_gemma":0.001562471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001905123,"about_ca_topic_score_gemma":0.002122086,"domain_scores_codex":[0.9960421,0.001441132,0.0004122477,0.0004964398,0.001378011,0.0002300057],"domain_scores_gemma":[0.9706635,0.0190115,0.002900214,0.002152656,0.004807992,0.0004641916],"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":[0.001152387,0.0008535603,0.0466075,0.0003666073,0.0002934329,0.0002248869,0.0006035691,0.1696444,0.02289726,0.005552841,0.004014882,0.7477887],"study_design_scores_gemma":[0.00003685057,0.0003555721,0.01244927,0.00005916461,0.0001135978,0.0001853255,0.0002748425,0.9601096,0.01529303,0.008964669,0.002117114,0.00004099831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1802886,0.001984407,0.8136403,0.00114009,0.0003465514,0.0001764988,0.0001939584,0.001149352,0.001080273],"genre_scores_gemma":[0.7498671,0.0006710542,0.2471063,0.0002342075,0.0002768722,0.0001122468,0.0004662444,0.000141086,0.001124919],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01185064,"threshold_uncertainty_score":0.06267291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01002388954796545,"score_gpt":0.2563395927293854,"score_spread":0.24631570318142,"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."}}