{"id":"W4407729374","doi":"10.2139/ssrn.5138371","title":"Enhancing Diabetes Risk Prediction: A Comparative Evaluation of Bagging, Boosting, and Ensemble Classifiers with Smote Oversampling","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Oversampling; Boosting (machine learning); Artificial intelligence; Machine learning; Computer science; Random subspace method; Ensemble learning; Pattern recognition (psychology); Support vector machine; Bandwidth (computing)","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":[0.008412337,0.001462346,0.002438931,0.001754609,0.000496232,0.001309946,0.001270217,0.001288983,0.0008704375],"category_scores_gemma":[0.00943892,0.0003857599,0.001131586,0.00124712,0.0002938445,0.001769854,0.001152222,0.001507131,0.0004343375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005034464,"about_ca_system_score_gemma":0.001156886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006600269,"about_ca_topic_score_gemma":0.005631744,"domain_scores_codex":[0.9980794,0.0008715407,0.0001093144,0.0003062607,0.0004763009,0.00015714],"domain_scores_gemma":[0.9934279,0.00445129,0.0001815436,0.0005263295,0.001208772,0.0002040494],"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":[0.004029962,0.002027573,0.03743576,0.0003875878,0.001534109,0.0000663402,0.0001584219,0.1406989,0.003645927,0.001003588,0.006304318,0.8027075],"study_design_scores_gemma":[0.0001344767,0.001147097,0.008723014,0.00007481981,0.0006638382,0.00007535818,0.00006797715,0.9829517,0.003085697,0.001499383,0.001547872,0.00002892417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7463083,0.02060981,0.2188306,0.001489129,0.0009378274,0.0002862343,0.001171254,0.003702083,0.006664885],"genre_scores_gemma":[0.8916652,0.002825708,0.1014422,0.000377149,0.0003027219,0.00007078902,0.001661183,0.0001139799,0.001541076],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008412337,"threshold_uncertainty_score":0.0444892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1242596101640117,"score_gpt":0.4480131405016227,"score_spread":0.3237535303376109,"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."}}