{"id":"W4415169415","doi":"10.1007/s10916-025-02278-w","title":"Predicting All-Cause Mortality in Diabetic Patients 2 Years in Advance Using Aggregated EHR Data and Machine Learning","year":2025,"lang":"en","type":"article","venue":"Journal of Medical Systems","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Public Health Ontario; University of Toronto; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Health informatics; Disease; Resource allocation; Predictive modelling; Health care; Emergency department; Informatics; MEDLINE","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004455804,0.0001159797,0.0003965385,0.0003007532,0.00004543954,0.00009072899,0.001197551,0.0001364273,0.000003274732],"category_scores_gemma":[0.004001032,0.0001019823,0.00002186879,0.0005572776,0.00004055244,0.0004303299,0.000684401,0.001296309,5.368593e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001590786,"about_ca_system_score_gemma":0.0002396088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002027605,"about_ca_topic_score_gemma":0.0002626862,"domain_scores_codex":[0.9964489,0.000866692,0.001018796,0.000295572,0.001078271,0.0002917371],"domain_scores_gemma":[0.9983559,0.0004307114,0.0005493086,0.0003747052,0.00008491417,0.0002045062],"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":[0.000006522173,0.00005180331,0.9858232,0.0002283202,0.00003463681,0.0002052804,0.0003065139,0.003518878,0.000004526104,0.0000938788,0.00001254356,0.00971388],"study_design_scores_gemma":[0.0008429873,0.00005116046,0.2982652,0.002296758,0.00001119517,0.00003680753,0.00004935083,0.6978619,7.055711e-7,0.00003034819,0.0004899282,0.00006373492],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9872364,0.003219947,0.007721268,0.0006599977,0.0009581869,0.0001588139,0.000002750368,0.00001987522,0.0000227781],"genre_scores_gemma":[0.99884,0.0002260128,0.0007617862,0.00007912478,0.00007212574,0.000001363556,0.000003954485,0.000006603608,0.000009058506],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.694343,"threshold_uncertainty_score":0.5631891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0566886838156516,"score_gpt":0.3649545467764447,"score_spread":0.3082658629607931,"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."}}