{"id":"W4408406005","doi":"10.1093/jamia/ocaf042","title":"Optimizing the efficiency and effectiveness of data quality assurance in a multicenter clinical dataset","year":2025,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"Canada Research Chairs","keywords":"False positive paradox; Data quality; Computer science; Quality assurance; Data collection; Data mining; Chart; Identifier; Medicine; Database; Machine learning; Metric (unit); Statistics; Operations management","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08165553,0.001246898,0.001333548,0.0028291,0.001158486,0.003681059,0.002772695,0.001224486,0.0006420509],"category_scores_gemma":[0.1846033,0.0007524216,0.001365815,0.00371594,0.001466024,0.004128583,0.00395602,0.001426389,0.0002063939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00356513,"about_ca_system_score_gemma":0.007739001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01257778,"about_ca_topic_score_gemma":0.0100543,"domain_scores_codex":[0.9415664,0.0393416,0.004655627,0.007274341,0.006097481,0.001064542],"domain_scores_gemma":[0.8378254,0.1023721,0.01593135,0.02501152,0.01618867,0.002670979],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003629645,0.00154021,0.2396186,0.000965493,0.001306509,0.0002778046,0.002282844,0.2814248,0.01834614,0.006614573,0.008661061,0.4353324],"study_design_scores_gemma":[0.0005599458,0.0008269571,0.04216463,0.000133091,0.0002104053,0.0001126981,0.0005231848,0.9357128,0.01047295,0.006610132,0.002604791,0.00006852495],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6490047,0.001403439,0.3298751,0.003657483,0.0001035997,0.001673518,0.002140823,0.009361112,0.002780319],"genre_scores_gemma":[0.6776425,0.0001338955,0.3196223,0.0002605772,0.00004455727,0.0003570054,0.001581476,0.0001601987,0.0001974094],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.08165553,"threshold_uncertainty_score":0.4318409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07893946645619035,"score_gpt":0.5384986410175016,"score_spread":0.4595591745613112,"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."}}