{"id":"W4417515038","doi":"10.1038/s41598-025-31562-5","title":"Predicting and classifying type 2 diabetes using a transparent ensemble model combining random forest, k-nearest neighbor, and neural networks","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Interpretability; Random forest; Ensemble learning; Artificial neural network; Feature selection; Missing data; Decision tree; Leverage (statistics); Deep learning; Data pre-processing","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":[0.003498621,0.001017792,0.001335007,0.001490391,0.0004984133,0.000806638,0.001162396,0.0007780934,0.0004164357],"category_scores_gemma":[0.003151756,0.0003662197,0.001382526,0.0007343444,0.0002129105,0.0008035004,0.0006437816,0.0008709258,0.0002160059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000511974,"about_ca_system_score_gemma":0.0006947016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01315603,"about_ca_topic_score_gemma":0.01231325,"domain_scores_codex":[0.9992129,0.0003123465,0.00006218647,0.0001838333,0.0001196658,0.0001089882],"domain_scores_gemma":[0.9986439,0.0006817537,0.0001230915,0.0001153807,0.0003694466,0.00006643018],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004653736,0.0004839131,0.03495167,0.00004036022,0.0004490184,0.0001615743,0.00009104793,0.7857826,0.00293566,0.0005857634,0.001119385,0.1729337],"study_design_scores_gemma":[0.000002870231,0.00002744513,0.00105207,0.000002882897,0.00002390916,0.000009328701,0.000006322749,0.9984618,0.0001935971,0.0001760052,0.00003848003,0.000005168534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5814494,0.0009458884,0.4140391,0.0005111333,0.0001680744,0.0001065719,0.0003542881,0.0008872933,0.001538247],"genre_scores_gemma":[0.9450084,0.000136736,0.05371625,0.00008129692,0.00006362274,0.00004913642,0.0003136071,0.00001439457,0.0006165225],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01315603,"threshold_uncertainty_score":0.02615893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1487885684133083,"score_gpt":0.4222256248179109,"score_spread":0.2734370564046026,"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."}}