{"id":"W2975003289","doi":"10.2196/14452","title":"Development of a Deep Learning Model for Dynamic Forecasting of Blood Glucose Level for Type 2 Diabetes Mellitus: Secondary Analysis of a Randomized Controlled Trial","year":2019,"lang":"en","type":"article","venue":"JMIR mhealth and uhealth","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institute of General Medical Sciences","keywords":"Type 2 Diabetes Mellitus; Randomized controlled trial; Medicine; Diabetes mellitus; Type 2 diabetes; Physical therapy; Internal medicine; Artificial intelligence; Computer science; Endocrinology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0312187,0.001727011,0.005006079,0.001165842,0.0003325789,0.001385891,0.001678292,0.00197274,0.004314934],"category_scores_gemma":[0.0343826,0.000926802,0.008617947,0.0009226763,0.0005015949,0.001740897,0.000988894,0.004235316,0.0004387146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001377702,"about_ca_system_score_gemma":0.002566054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002763318,"about_ca_topic_score_gemma":0.002037981,"domain_scores_codex":[0.9867837,0.01038143,0.000702673,0.0009844379,0.0006482789,0.0004995135],"domain_scores_gemma":[0.9804888,0.01429724,0.002199525,0.001290418,0.001220829,0.0005032276],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.4910339,0.008397658,0.03754843,0.005728609,0.07115233,0.0003781408,0.0001697527,0.194013,0.002414511,0.004300731,0.01163187,0.1732311],"study_design_scores_gemma":[0.199951,0.03443146,0.01685724,0.0006021802,0.03363385,0.0001432372,0.00007556173,0.6964281,0.002100941,0.01129397,0.004309568,0.0001728641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.646883,0.01783924,0.2869521,0.00741687,0.003445258,0.01937385,0.01118059,0.001950578,0.004958546],"genre_scores_gemma":[0.9303833,0.001656787,0.04789266,0.001353921,0.0003449896,0.01381645,0.002725866,0.00008228145,0.001743792],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0312187,"threshold_uncertainty_score":0.1651023,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08763964338857322,"score_gpt":0.4245654763130927,"score_spread":0.3369258329245195,"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."}}