{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002452488,0.0002073354,0.0004717001,0.0002097509,0.0002795779,0.000297753,0.001881128,0.000212893,0.000003853327],"category_scores_gemma":[0.0004313265,0.0001420123,0.0001191002,0.0008003597,0.000311906,0.001712337,0.0004032843,0.0004375798,0.000002762516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009804008,"about_ca_system_score_gemma":0.0004945102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005264031,"about_ca_topic_score_gemma":0.000001361756,"domain_scores_codex":[0.9971505,0.0001405668,0.001370782,0.0002155959,0.0006993635,0.0004231416],"domain_scores_gemma":[0.9966101,0.0005706812,0.00132262,0.0009238081,0.0003394733,0.0002333066],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008876782,0.001315575,0.006602808,0.0003031482,0.001579694,0.0001602628,0.005955976,0.0165843,0.005142317,0.01619585,0.5852843,0.3599881],"study_design_scores_gemma":[0.001383708,0.0004879902,0.0002137246,0.00009557433,0.00003001582,0.00009470202,0.0002959138,0.9741469,0.0002923647,0.0001563628,0.02261012,0.000192642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01397484,0.00004998275,0.9833813,0.0008900113,0.000913577,0.000309895,0.0003428634,0.0001285054,0.000009011023],"genre_scores_gemma":[0.1727343,0.0003442841,0.8241065,0.0006966802,0.001022425,0.00001202079,0.00104329,0.00002154025,0.00001905468],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9575626,"threshold_uncertainty_score":0.5791095,"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."}}