{"id":"W2995241421","doi":"10.1007/s41666-019-00063-2","title":"Predicting Glycaemia in Type 1 Diabetes Patients: Experiments in Feature Engineering and Data Imputation","year":2019,"lang":"en","type":"article","venue":"Journal of Healthcare Informatics Research","topic":"Diabetes Management and Research","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto East General Hospital","funders":"","keywords":"Imputation (statistics); Missing data; Computer science; Predictive modelling; Type 2 diabetes; Diabetes mellitus; Statistics; Medicine; Machine learning; Mathematics; 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":[0.003162081,0.00008174756,0.0002721977,0.001125405,0.00002982645,0.00006368572,0.0002520657,0.00009547054,0.00001053126],"category_scores_gemma":[0.0009013599,0.00006473405,0.00001643644,0.0007076147,0.0000239802,0.0006696834,0.0003364386,0.0009952895,0.000007515387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002603187,"about_ca_system_score_gemma":0.0002287354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002085888,"about_ca_topic_score_gemma":0.00001234921,"domain_scores_codex":[0.9977735,0.00008017178,0.000607818,0.00008724466,0.001010948,0.0004403162],"domain_scores_gemma":[0.9986913,0.0002234003,0.000139208,0.0002546415,0.0005349441,0.0001565685],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001562489,0.00008386187,0.9715236,0.001911906,0.00002598417,0.00001114504,0.001830475,0.0001209835,0.00006038001,0.00004115772,0.0005904093,0.02364388],"study_design_scores_gemma":[0.007003541,0.003425099,0.6538147,0.005136271,0.0000110595,0.000008196283,0.007203104,0.3185934,0.0002910786,0.0001150815,0.004194206,0.0002042569],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9964215,0.001311239,0.000001821215,0.001244027,0.0001565985,0.000544433,0.000003626178,0.00000447615,0.0003123238],"genre_scores_gemma":[0.9983475,0.0003372511,0.001058126,0.00007083378,0.00005854926,0.000002779266,0.00004298706,0.00001209411,0.00006986646],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3184724,"threshold_uncertainty_score":0.4324093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06161369520299682,"score_gpt":0.4166492730689366,"score_spread":0.3550355778659398,"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."}}