{"id":"W2972679677","doi":"10.1002/pds.4889","title":"Data variability across Canadian administrative health databases: Differences in content, coding, and completeness","year":2019,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; McGill University; Institute for Clinical Evaluative Sciences; University of Calgary; University of Manitoba; Jewish General Hospital; Manitoba Health; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Pharmacoepidemiology; Confidence interval; Observational study; Database; Coding (social sciences); Demography; Statistics; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02001669,0.0001820087,0.000750091,0.00007141656,0.0009745086,0.00000519819,0.000262139,0.0001334395,0.0004395477],"category_scores_gemma":[0.002914035,0.0001445535,0.0000145648,0.000112635,0.000248101,0.0003140622,0.0002956253,0.001088609,0.0000484183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001649202,"about_ca_system_score_gemma":0.001071503,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1485656,"about_ca_topic_score_gemma":0.22053,"domain_scores_codex":[0.9928682,0.004373551,0.001233287,0.0005221621,0.0001014547,0.0009013452],"domain_scores_gemma":[0.9898008,0.008557637,0.0004029632,0.0004231243,0.00006565352,0.0007497907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001692524,0.00001864135,0.9770812,0.0007918398,0.00001288548,0.000001392715,0.003742568,7.398414e-7,0.000001989363,0.008332875,0.006018409,0.003828198],"study_design_scores_gemma":[0.001815604,0.00004546473,0.8929948,0.0003112129,0.000007632847,0.0000043994,0.005013163,0.01480906,3.772086e-7,0.0003316679,0.08449717,0.0001695119],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8975778,0.001103927,0.003750653,0.08159408,0.001780171,0.002582044,0.007495983,0.00008407512,0.004031333],"genre_scores_gemma":[0.9728385,0.002265999,0.0003469907,0.02317548,0.0001003078,0.00004030166,0.001056535,0.000006655386,0.0001692982],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08408647,"threshold_uncertainty_score":0.8571042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6711014377746589,"score_gpt":0.5662363753812069,"score_spread":0.1048650623934521,"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."}}