{"id":"W3127976655","doi":"10.1089/pop.2020.0306","title":"Comparing the Predictive Effects of Patient Medication Adherence Indices in Electronic Health Record and Claims-Based Risk Stratification Models","year":2021,"lang":"en","type":"article","venue":"Population Health Management","topic":"Medication Adherence and Compliance","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario","funders":"","keywords":"Medicine; Medical prescription; Medication adherence; Retrospective cohort study; Electronic health record; Medication therapy management; Emergency medicine; Population; Cohort; Predictive validity; Prescription drug; Predictive modelling; Polypharmacy; Predictive value; Internal medicine; Family medicine; Health care; Pharmacy; Machine learning; Pharmacist; Environmental health","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":[0.0006481028,0.0001054271,0.0002703253,0.000123082,0.0001328611,0.00001121126,0.00007027835,0.0000353594,0.00002004216],"category_scores_gemma":[0.00004672922,0.0000888823,0.00002520385,0.0003875478,0.00003655403,0.00009139044,0.00002346877,0.0002098111,0.000004437156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002885953,"about_ca_system_score_gemma":0.0003027108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001131651,"about_ca_topic_score_gemma":0.0004726201,"domain_scores_codex":[0.9980288,0.000348993,0.0006608929,0.0003121362,0.0004107526,0.0002383921],"domain_scores_gemma":[0.9986696,0.0001087427,0.0007063611,0.0003303992,0.00007204923,0.0001127978],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001946687,0.0005558209,0.5834397,0.003789451,0.00007695738,0.000002476332,0.00206808,0.004935485,0.000009523597,0.02110534,0.0007206511,0.3831018],"study_design_scores_gemma":[0.001008007,0.0004812088,0.8626573,0.0008751479,0.00002864074,0.000001210123,0.0006616103,0.1280426,0.0000475434,0.005857248,0.0002733656,0.00006614716],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9390227,0.004413568,0.0444998,0.008752502,0.0001525399,0.002771231,0.000003219777,0.00004831475,0.000336081],"genre_scores_gemma":[0.9937604,0.003017846,0.001391563,0.001363765,0.00001699517,0.0002703213,0.0001393172,0.000007678915,0.00003211634],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3830357,"threshold_uncertainty_score":0.3624515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04022153335182458,"score_gpt":0.3323426576397518,"score_spread":0.2921211242879272,"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."}}