{"id":"W4384133663","doi":"10.1016/j.jbi.2023.104436","title":"Generating synthetic clinical data that capture class imbalanced distributions with generative adversarial networks: Example using antiretroviral therapy for HIV","year":2023,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Wellcome Trust","keywords":"Computer science; Machine learning; Artificial intelligence; Autoencoder; Adversarial system; Class (philosophy); Data mining; Artificial neural network","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001973552,0.0005675066,0.0002885861,0.0003526216,0.0002850441,0.0004720535,0.0006321023,0.0008284869,0.001353529],"category_scores_gemma":[0.006511986,0.0001814838,0.0006198331,0.0003485778,0.0007109434,0.0003721178,0.0006081652,0.001108635,0.0001588981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007012696,"about_ca_system_score_gemma":0.0004884346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004841194,"about_ca_topic_score_gemma":0.00439591,"domain_scores_codex":[0.9993212,0.0004029695,0.00002442038,0.00009812587,0.0001053352,0.00004796075],"domain_scores_gemma":[0.994507,0.004539611,0.0002330144,0.0003401442,0.0002807473,0.00009957614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000195527,0.0001115933,0.009954048,0.00007121557,0.00005331685,0.0002399371,0.0001029673,0.9617292,0.001098888,0.004420999,0.002428751,0.01959355],"study_design_scores_gemma":[0.00002068356,0.00005837603,0.001285189,0.0000119007,0.000005901396,0.00005200824,0.00002545313,0.9928784,0.001270331,0.003790475,0.0005921099,0.000009305491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7309038,0.0007689092,0.255138,0.00289661,0.000276168,0.0003412355,0.002829873,0.000548109,0.006297267],"genre_scores_gemma":[0.960538,0.0001404501,0.03618149,0.0003234944,0.00004591211,0.0001305301,0.001391828,0.00002920849,0.001218967],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.004841194,"threshold_uncertainty_score":0.01043725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1119402727444882,"score_gpt":0.3553270268300627,"score_spread":0.2433867540855745,"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."}}