{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006101519,0.001095531,0.001464219,0.003956012,0.0006454192,0.002349867,0.001779154,0.0016426,0.001289718],"category_scores_gemma":[0.0250511,0.0004433721,0.00169242,0.002416314,0.001006984,0.002316961,0.001683766,0.00244098,0.0003801588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008653887,"about_ca_system_score_gemma":0.001530857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002468341,"about_ca_topic_score_gemma":0.00214947,"domain_scores_codex":[0.9967263,0.001216731,0.000327739,0.0008468787,0.0006144058,0.0002679641],"domain_scores_gemma":[0.9728601,0.02119813,0.00240293,0.00207989,0.001034988,0.0004238942],"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":[0.002633209,0.001081149,0.3778888,0.0006782081,0.0007621031,0.003231206,0.0009963326,0.1090171,0.008460975,0.02078956,0.01376524,0.4606963],"study_design_scores_gemma":[0.00009974618,0.0001338168,0.02396444,0.00005421068,0.0001563723,0.0006504274,0.0002024242,0.8971205,0.002119522,0.07409137,0.001373972,0.00003317131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3771227,0.002376835,0.6084626,0.00607944,0.0002807945,0.0002520958,0.003056512,0.001211261,0.001157676],"genre_scores_gemma":[0.9301227,0.000553776,0.06438134,0.000345829,0.0002995585,0.0001290108,0.003403977,0.00005545229,0.0007084527],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006101519,"threshold_uncertainty_score":0.03226829,"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."}}