{"id":"W3157439450","doi":"10.2196/25237","title":"Improving Current Glycated Hemoglobin Prediction in Adults: Use of Machine Learning Algorithms With Electronic Health Records","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Machine learning; Logistic regression; Glycated hemoglobin; Random forest; Artificial intelligence; Support vector machine; Multilayer perceptron; Computer science; Predictive modelling; Receiver operating characteristic; Health records; Preprint; Perceptron; Data mining; Artificial neural network; Medicine; Diabetes mellitus; Health care; Type 2 diabetes","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":[0.0009611559,0.0002011585,0.0003912506,0.0002149062,0.0001048674,0.00007371459,0.0004751936,0.0001419031,0.00004366862],"category_scores_gemma":[0.0006370837,0.000170339,0.00004920709,0.001174429,0.00005995613,0.0007703249,0.0003041178,0.001821772,0.000008522457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003571654,"about_ca_system_score_gemma":0.001963015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008299112,"about_ca_topic_score_gemma":0.0005019021,"domain_scores_codex":[0.9965686,0.0003009384,0.001172141,0.0002415774,0.001075475,0.0006413261],"domain_scores_gemma":[0.9981799,0.0002081064,0.0005906847,0.0004546161,0.0002409527,0.0003257395],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005346231,0.0002019077,0.03433831,0.001914436,0.00001647114,0.00001936833,0.008196759,0.001194251,0.00000177523,0.001055898,0.0002416784,0.9527657],"study_design_scores_gemma":[0.001106401,0.0006735559,0.003330227,0.00115467,0.000002279662,0.0001080652,0.0002692413,0.9868167,0.00003097644,0.00002944576,0.006326647,0.0001518125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2986846,0.001373908,0.6942878,0.003207309,0.0007063751,0.001014713,0.00002524685,0.0005661602,0.0001338675],"genre_scores_gemma":[0.8417172,0.001701481,0.1532807,0.002037675,0.0002546536,0.0001932891,0.0005589302,0.00006686321,0.0001892018],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9856224,"threshold_uncertainty_score":0.7914796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01324685576049121,"score_gpt":0.289157379833488,"score_spread":0.2759105240729968,"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."}}