{"id":"W4411724417","doi":"10.2196/66200","title":"A Responsible Framework for Assessing, Selecting, and Explaining Machine Learning Models in Cardiovascular Disease Outcomes Among People With Type 2 Diabetes: Methodology and Validation Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Institutes of Health","keywords":"Interpretability; Machine learning; Artificial intelligence; Computer science; Random forest; Population; Predictive modelling; Decision tree; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1103249,0.001665594,0.001001271,0.003223973,0.001918442,0.002230644,0.003369159,0.002051701,0.001536471],"category_scores_gemma":[0.1889785,0.0007823365,0.002540075,0.001785242,0.002542408,0.00221848,0.004090171,0.002975017,0.0002454504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003448473,"about_ca_system_score_gemma":0.009396779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009258009,"about_ca_topic_score_gemma":0.0082132,"domain_scores_codex":[0.936304,0.05387475,0.001960433,0.002976514,0.004076728,0.0008074723],"domain_scores_gemma":[0.8039629,0.1493644,0.009860641,0.01427798,0.02136338,0.001170647],"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":[0.001036845,0.002282207,0.2783991,0.001215771,0.001611421,0.001030183,0.008416397,0.2839385,0.005204185,0.1482937,0.005906238,0.2626655],"study_design_scores_gemma":[0.0002062751,0.0005702731,0.01385591,0.000320323,0.0002553177,0.0001412464,0.0007327914,0.9372824,0.002826498,0.04084869,0.002873462,0.00008683585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07160403,0.0004273235,0.9231135,0.0007996624,0.0000323585,0.002237779,0.0002475379,0.0002389788,0.001298885],"genre_scores_gemma":[0.3826442,0.000125332,0.6118549,0.0002880697,0.0000364531,0.004257297,0.0004498405,0.00005170703,0.0002922521],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1103249,"threshold_uncertainty_score":0.5834608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06321971599335918,"score_gpt":0.3608376345101724,"score_spread":0.2976179185168132,"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."}}