{"id":"W4387133168","doi":"10.23889/ijpds.v8i5.2177","title":"Understanding data provenance when using electronic medical records for research: Lessons learned from the Deliver Primary Healthcare Information (DELPHI) database","year":2023,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Lawson Health Research Institute","keywords":"Data quality; Database; Health care; Computer science; Identifier; Record linkage; Delphi; Data science; Medicine; Metric (unit); Engineering; Operations management","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6436808,0.0008546432,0.001260398,0.005441259,0.008570424,0.0148386,0.005559283,0.003725974,0.003784177],"category_scores_gemma":[0.6620346,0.001409194,0.001601155,0.005522994,0.01425932,0.01690058,0.02083318,0.006766953,0.0006710213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01826783,"about_ca_system_score_gemma":0.06826885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02270922,"about_ca_topic_score_gemma":0.02584736,"domain_scores_codex":[0.2738955,0.6514758,0.03400504,0.007337511,0.02826858,0.005017695],"domain_scores_gemma":[0.1896098,0.6808964,0.02171794,0.03453052,0.06723045,0.006014929],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002762054,0.0002839627,0.0340022,0.006402616,0.0002122454,0.0008062092,0.5744756,0.002418308,0.001372005,0.05460255,0.02572193,0.2994262],"study_design_scores_gemma":[0.0001859182,0.0007356562,0.02193422,0.03176228,0.0001976469,0.001183398,0.5016289,0.01334705,0.002596441,0.1897129,0.2362471,0.0004685821],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.157974,0.006399134,0.4698507,0.3082805,0.001874792,0.01884756,0.001365185,0.0005647902,0.03484337],"genre_scores_gemma":[0.5207663,0.003567781,0.4383653,0.02130863,0.0004529,0.01342841,0.0005585983,0.0002779262,0.001274193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3563192,"threshold_uncertainty_score":0.439405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8682030873622053,"score_gpt":0.6389304617001106,"score_spread":0.2292726256620947,"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."}}