{"id":"W4248447296","doi":"10.21203/rs.3.rs-28409/v4","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":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Class (philosophy); Artificial intelligence; Computer science; Data mining; Pattern recognition (psychology); Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003312421,0.0008541535,0.0009829103,0.003991973,0.0004828766,0.001374117,0.001134131,0.0008784383,0.000975125],"category_scores_gemma":[0.01522674,0.0002845372,0.001178118,0.002640062,0.0007168186,0.001434513,0.001299965,0.001699301,0.0002844382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008640371,"about_ca_system_score_gemma":0.001387862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003503159,"about_ca_topic_score_gemma":0.002999599,"domain_scores_codex":[0.9976273,0.0006450579,0.0003119169,0.0007394455,0.0005283561,0.0001478478],"domain_scores_gemma":[0.9794196,0.01488557,0.002210464,0.001628861,0.001372553,0.0004829341],"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":[0.001792177,0.0008918994,0.3780037,0.0007422312,0.0004515652,0.003220911,0.001193854,0.120945,0.009577665,0.009160264,0.008435854,0.4655848],"study_design_scores_gemma":[0.00005002193,0.00009504705,0.01620807,0.00003342711,0.00005951218,0.0004623055,0.0001398046,0.9637734,0.002568107,0.01521197,0.001373215,0.00002505354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4290926,0.001648449,0.559975,0.002753194,0.0001410506,0.0003589666,0.003374103,0.001631749,0.001024965],"genre_scores_gemma":[0.8376424,0.0003813708,0.1567762,0.0002142739,0.00009173925,0.0001585502,0.004184844,0.00004282299,0.0005076695],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003991973,"threshold_uncertainty_score":0.01751798,"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."}}