{"id":"W4243294319","doi":"10.21203/rs.3.rs-28409/v3","title":"Explanation and Prediction of Clinical Data with Imbalanced Class Distribution based on Pattern Discovery and Disentanglement","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interpretability; Computer science; Class (philosophy); Set (abstract data type); Notice; Machine learning; Artificial intelligence; Data mining; Data set","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":[0.001999771,0.0001900514,0.0003410409,0.0001506275,0.0001070953,0.0003334488,0.001114465,0.000179188,0.00000231614],"category_scores_gemma":[0.0004717096,0.0001578775,0.00003130412,0.0002888846,0.0002379641,0.0006152331,0.002482918,0.0008174858,0.000001402018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001183458,"about_ca_system_score_gemma":0.0002984568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000548002,"about_ca_topic_score_gemma":0.00001831344,"domain_scores_codex":[0.996112,0.0006157362,0.0005643585,0.001224529,0.001230912,0.0002524694],"domain_scores_gemma":[0.9967773,0.0004334633,0.0003234247,0.002026347,0.0002872302,0.0001522123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001280308,0.001872389,0.5361947,0.006020948,0.0002706733,0.00009141201,0.0005712014,0.0001878003,0.001222,0.02399369,0.05290703,0.3753878],"study_design_scores_gemma":[0.0009027906,0.001018089,0.4411246,0.001143956,0.00001702656,0.000001752741,0.00008426081,0.5510473,0.001415549,0.001038987,0.001988575,0.0002171143],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009914596,0.00005835682,0.974509,0.00450697,0.0001204559,0.001127194,0.009544522,0.0001493522,0.00006955271],"genre_scores_gemma":[0.9814473,0.0004611612,0.004559742,0.00005790196,0.0001052388,0.0001386757,0.01320778,0.00001408567,0.000008118005],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9715327,"threshold_uncertainty_score":0.6438059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1800614714183979,"score_gpt":0.4348338638435065,"score_spread":0.2547723924251086,"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."}}