{"id":"W2614362749","doi":"","title":"Investigating the Process of Developing a KDD Model for the Classification of Cases with Cardiovascular Disease Based on a Canadian Database","year":2013,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Database; Data mining; Process (computing); Artificial intelligence; Information retrieval; Data science; Programming language","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":[0.0003588086,0.0001816464,0.0002776233,0.0002497137,0.0002985897,0.00003051912,0.001394118,0.00008646653,0.000001970224],"category_scores_gemma":[0.000121255,0.0001317838,0.0001289452,0.0003954405,0.0001971001,0.0003745936,0.00004067656,0.0001381684,7.520009e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001023331,"about_ca_system_score_gemma":0.001544109,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1299427,"about_ca_topic_score_gemma":0.1376005,"domain_scores_codex":[0.9987221,0.0000702274,0.0001674626,0.0003866915,0.00046198,0.000191494],"domain_scores_gemma":[0.9972177,0.0001810953,0.0004802659,0.001342148,0.0006798212,0.00009900211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001309219,0.0007070978,0.003599194,0.0204722,0.003841868,0.00007420935,0.4411882,0.2395562,0.01831493,0.1872704,0.01164734,0.07201907],"study_design_scores_gemma":[0.0003112193,0.00005801388,0.005541252,0.0007459095,0.0002531392,9.040823e-7,0.01435277,0.9739052,0.004235588,0.0002870222,0.00006891565,0.0002400772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4537257,0.0001708785,0.5379549,0.003850014,0.00008136976,0.00297952,0.001072764,0.0001062664,0.00005857987],"genre_scores_gemma":[0.9281798,0.00003526455,0.06808358,0.00006762076,0.00001037344,0.00003910029,0.001250122,0.00002528724,0.002308876],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.734349,"threshold_uncertainty_score":0.878136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03385744037593748,"score_gpt":0.2331769007423344,"score_spread":0.1993194603663969,"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."}}