{"id":"W3123935279","doi":"10.2196/20123","title":"Risk Stratification for Early Detection of Diabetes and Hypertension in Resource-Limited Settings: Machine Learning Analysis","year":2021,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Diabetes, Cardiovascular Risks, and Lipoproteins","field":"Medicine","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Random forest; Medicine; Diabetes mellitus; Receiver operating characteristic; Machine learning; Risk stratification; Risk assessment; Population; Framingham Risk Score; Environmental health; Disease; Artificial intelligence; Computer science; Internal medicine","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009398961,0.00008883705,0.0006143671,0.0008169964,0.00004524604,0.00004249438,0.0001278649,0.0001968549,0.0000640608],"category_scores_gemma":[0.01201271,0.0000685183,0.0003340572,0.0008905602,0.0001460809,0.00007400246,0.00007212591,0.001327916,9.372779e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006485706,"about_ca_system_score_gemma":0.0001342921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001001593,"about_ca_topic_score_gemma":0.0005647799,"domain_scores_codex":[0.9963611,0.0008332258,0.0006524784,0.0002134571,0.001685013,0.0002547246],"domain_scores_gemma":[0.9974827,0.0008775399,0.0002441508,0.0001855774,0.000963196,0.0002468129],"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":[0.0005730541,0.0004194865,0.1565001,0.0004076568,0.002700742,0.0001733103,0.0009959289,0.00007081232,0.01549091,0.000009394601,0.0003240383,0.8223345],"study_design_scores_gemma":[0.005715444,0.003049669,0.781384,0.00157825,0.001671366,0.0001374078,0.002113483,0.106207,0.08667434,0.0002093371,0.01108344,0.0001762604],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920877,0.004359381,0.001789999,0.001492634,0.00003919934,0.0001774744,0.000003142357,0.000005451385,0.00004505908],"genre_scores_gemma":[0.99841,0.0007836982,0.0003826057,0.00004454913,0.0001891335,0.000007918838,0.0000173728,0.00001386431,0.0001508493],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8221583,"threshold_uncertainty_score":0.9963095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03193128810641655,"score_gpt":0.3284119244240641,"score_spread":0.2964806363176475,"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."}}