{"id":"W3016344200","doi":"10.1089/dia.2019.0458","title":"Predicting and Preventing Nocturnal Hypoglycemia in Type 1 Diabetes Using Big Data Analytics and Decision Theoretic Analysis","year":2020,"lang":"en","type":"article","venue":"Diabetes Technology & Therapeutics","topic":"Diabetes Management and Research","field":"Medicine","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Institutes of Health; Leona M. and Harry B. Helmsley Charitable Trust","keywords":"Hypoglycemia; Medicine; Bedtime; Nocturnal; Type 1 diabetes; Diabetes mellitus; Receiver operating characteristic; Confidence interval; Artificial pancreas; Internal medicine; Endocrinology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000646583,0.0002444328,0.0006101598,0.0009936165,0.000125145,0.00008437468,0.0004063088,0.0002739977,0.00001416648],"category_scores_gemma":[0.0003009363,0.0002077689,0.00005548564,0.002899003,0.0004624752,0.000124705,0.0009826418,0.0006086318,0.000002383206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003520347,"about_ca_system_score_gemma":0.0000458276,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002006592,"about_ca_topic_score_gemma":0.000007353054,"domain_scores_codex":[0.9979964,0.00005470469,0.0004269934,0.0006280015,0.000300726,0.0005931965],"domain_scores_gemma":[0.998706,0.0002816986,0.0001425004,0.0006383735,0.00009867334,0.0001327352],"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":[0.00003665193,0.0000444433,0.8106934,0.0001163033,0.001052592,0.000008667419,0.00007160263,0.00004258541,0.005796039,0.0000574417,0.000004696477,0.1820756],"study_design_scores_gemma":[0.001750809,0.0005452449,0.103891,0.0002859522,0.004686211,0.000001499497,0.0003688295,0.8807768,0.002683585,0.003912443,0.0007454778,0.0003521941],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9912508,0.006126522,0.0003582986,0.001682323,0.00006561429,0.000328915,0.0000114208,0.0001172584,0.00005891628],"genre_scores_gemma":[0.9939226,0.0007892367,0.004341295,0.0007607746,0.00009158508,0.000003898485,0.00004234472,0.0000369648,0.00001131119],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8807342,"threshold_uncertainty_score":0.8472571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08514565126685408,"score_gpt":0.327203361074498,"score_spread":0.242057709807644,"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."}}