{"id":"W4414463559","doi":"10.1109/conit65521.2025.11167663","title":"Enhanced Diabetes Diagnosis Using Ensemble Classifiers with Explainable AI and Oversampling for Imbalanced Data","year":2025,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Random forest; Ensemble learning; Interpretability; Oversampling; Random subspace method; Preprocessor; Feature selection; Classifier (UML); Decision tree","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":[0.00237917,0.0007455205,0.001143359,0.001319063,0.0004782838,0.001005174,0.0007724639,0.0006535931,0.0005958175],"category_scores_gemma":[0.005327415,0.0002010933,0.001067263,0.0008660912,0.0002018469,0.001195181,0.0008121828,0.001373424,0.0002583742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004252649,"about_ca_system_score_gemma":0.000759664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004898723,"about_ca_topic_score_gemma":0.005077225,"domain_scores_codex":[0.9991854,0.0002542883,0.00005993084,0.0001930043,0.000200831,0.0001065872],"domain_scores_gemma":[0.9978105,0.001087263,0.0002138174,0.0002504847,0.0005637105,0.000074148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004770628,0.0003562163,0.04533136,0.00009294089,0.0004240255,0.0003386294,0.0003219058,0.316031,0.00917263,0.003905131,0.003847362,0.6197017],"study_design_scores_gemma":[0.000007491252,0.00007810278,0.002668306,0.0000115682,0.00004974667,0.00005835593,0.00003629928,0.9925686,0.001486709,0.002387284,0.0006350463,0.00001251824],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1424395,0.001109073,0.8526416,0.0006116654,0.0001714975,0.0000773839,0.0003299083,0.001173171,0.001446043],"genre_scores_gemma":[0.8825579,0.0004038415,0.1146428,0.0002461273,0.0001825975,0.00007249164,0.0008631923,0.00003930646,0.0009917212],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004898723,"threshold_uncertainty_score":0.01258236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2270710183652112,"score_gpt":0.4996705948920326,"score_spread":0.2725995765268214,"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."}}