{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005734006,0.00008872449,0.0002422586,0.0001732844,0.0000462685,0.0001038152,0.0003895796,0.00003145181,3.422697e-7],"category_scores_gemma":[0.0002054493,0.00006287176,0.0000317253,0.0001852153,0.00008506217,0.0003815372,0.0001152477,0.0002590745,2.120041e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000243562,"about_ca_system_score_gemma":0.00004356281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005397425,"about_ca_topic_score_gemma":8.429321e-7,"domain_scores_codex":[0.9989125,0.0002339756,0.0003989411,0.0001753481,0.000179238,0.00009998298],"domain_scores_gemma":[0.9978397,0.001381142,0.0004439819,0.00009353741,0.0001845316,0.00005711934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008577546,0.0000497568,0.6369231,0.00006531431,0.0001197764,0.000153861,0.001090097,0.001148326,0.02892914,0.001904673,0.0004111826,0.329119],"study_design_scores_gemma":[0.0004570133,0.000127954,0.7531118,0.0003400882,0.000009620039,0.0008560408,0.00003825598,0.241463,0.001892978,0.0001890089,0.001373546,0.0001406244],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.206024,0.0003094037,0.7840157,0.009418706,0.0001404758,0.00006233426,5.722604e-7,0.00001855916,0.00001026658],"genre_scores_gemma":[0.9557629,0.00006715718,0.04263391,0.001426438,0.00009708521,0.000004527057,0.000002703209,0.000004642066,6.456825e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7497389,"threshold_uncertainty_score":0.2563836,"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."}}