{"id":"W3022470673","doi":"10.1186/s40537-020-00302-z","title":"Leveraging machine learning and big data for optimizing medication prescriptions in complex diseases: a case study in diabetes management","year":2020,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Diabetes, Cardiovascular Risks, and Lipoproteins","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Toronto Metropolitan University","funders":"","keywords":"Computer science; Bayesian network; Big data; Machine learning; Medical prescription; Variable (mathematics); Artificial intelligence; Bayesian probability; Data mining; Medicine; Mathematics","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":[0.00141531,0.0001236378,0.0004713857,0.0002670499,0.00007466472,0.00006214757,0.000397398,0.00002644478,0.000006437796],"category_scores_gemma":[0.0006516185,0.0001079663,0.00005101901,0.0002397171,0.00003269713,0.0003326245,0.0006861353,0.0003053958,4.694243e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004144635,"about_ca_system_score_gemma":0.00005696666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007418843,"about_ca_topic_score_gemma":0.0005468224,"domain_scores_codex":[0.9984334,0.0001547603,0.0005257669,0.0003440649,0.0003473512,0.0001947057],"domain_scores_gemma":[0.9987989,0.00008596526,0.0002022584,0.0006750652,0.00004597022,0.0001918448],"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":[0.0001744823,0.0006461276,0.1363914,0.0006564864,0.0008482373,0.002770461,0.001614401,0.0002877135,0.00006160369,0.000001011189,0.001755762,0.8547923],"study_design_scores_gemma":[0.03309386,0.001805817,0.4392381,0.001776797,0.004698812,0.0009509247,0.03446658,0.3481633,0.00001663446,0.00005174518,0.1350871,0.0006502432],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9747171,0.008536033,0.01154587,0.002707196,0.0002610031,0.001617038,0.0005516615,0.00002380752,0.00004032681],"genre_scores_gemma":[0.9932399,0.0006394335,0.004418921,0.000204726,0.0005493708,0.00001453272,0.0009054556,0.00002061933,0.000007007467],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.854142,"threshold_uncertainty_score":0.4402738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2050337070575335,"score_gpt":0.3363276992871178,"score_spread":0.1312939922295843,"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."}}