{"id":"W3112067326","doi":"10.1186/s12911-020-01356-y","title":"Explanation and prediction of clinical data with imbalanced class distribution based on pattern discovery and disentanglement","year":2021,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Computer science; Class (philosophy); Set (abstract data type); Machine learning; Artificial intelligence; Data mining; Notice; Data set; Data science","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001088648,0.0000944403,0.0001997902,0.0000519419,0.0000710685,0.0001815182,0.0002662696,0.00008294758,0.000003938793],"category_scores_gemma":[0.000566515,0.00006881225,0.00001406598,0.0001452845,0.00009131629,0.0008350866,0.0004662999,0.0001255881,3.850207e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001537301,"about_ca_system_score_gemma":0.0001379947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001194452,"about_ca_topic_score_gemma":0.00001172857,"domain_scores_codex":[0.9981478,0.00006181005,0.0007224109,0.000241467,0.0007210405,0.000105471],"domain_scores_gemma":[0.9979767,0.0009045731,0.0003066377,0.0006259602,0.00008440414,0.0001017618],"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":[0.00006964864,0.00009727047,0.03917197,0.0001481964,0.000009698352,0.000005797254,0.00006939987,0.00002460714,0.000006155755,0.004804675,0.001394979,0.9541976],"study_design_scores_gemma":[0.0007931706,0.0001144219,0.0486456,0.0005551847,0.000008390281,0.0000151963,0.0001147586,0.9485673,0.00007549311,0.000511102,0.0005273705,0.0000720634],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04558817,0.00003289546,0.9537359,0.00009692348,0.00009500887,0.0001124795,0.0002486096,0.00003442698,0.00005555347],"genre_scores_gemma":[0.7742909,0.0002512235,0.2244901,0.0003846645,0.00002574368,0.000006710195,0.0005461017,0.000003284292,0.000001303174],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9541255,"threshold_uncertainty_score":0.2806082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07022578411285324,"score_gpt":0.3616883570977912,"score_spread":0.291462572984938,"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."}}