{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003443428,0.0001717339,0.000449306,0.0003153007,0.000244997,0.0002824223,0.0003099663,0.0001268179,0.000002661454],"category_scores_gemma":[0.003508516,0.0001394042,0.00004374644,0.000836901,0.00008484825,0.001170288,0.0002969645,0.000457006,6.598291e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004357413,"about_ca_system_score_gemma":0.0002624484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008496558,"about_ca_topic_score_gemma":0.0001036507,"domain_scores_codex":[0.9980196,0.000414413,0.0005049383,0.0002495478,0.0004593581,0.0003521159],"domain_scores_gemma":[0.9969656,0.002228877,0.0001388661,0.0003529767,0.0001333727,0.0001802639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006423727,0.0001385422,0.8916869,0.0003260973,0.0002311864,0.00001378773,0.04123339,0.0145536,0.000001612283,0.01796638,0.00001290431,0.03377139],"study_design_scores_gemma":[0.000433265,0.0002149032,0.02881209,0.0002525712,0.00005242557,0.000001753486,0.007307271,0.9499367,0.00006624674,0.01267752,0.00006365924,0.0001816384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5085503,0.0001322065,0.4906425,0.0001129154,0.000051926,0.0004144014,2.632093e-7,0.00005578654,0.00003974497],"genre_scores_gemma":[0.8665985,0.00002679401,0.1329325,0.0002075318,0.00001139062,0.0001886147,0.000003708236,0.000009183065,0.00002180321],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9353831,"threshold_uncertainty_score":0.568474,"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."}}