{"id":"W4388725462","doi":"10.1370/afm.22.s1.4964","title":"CPCSSN Data Quality: An Opportunity for Enhancing Canadian Primary Care Data","year":2023,"lang":"en","type":"article","venue":"Healthcare informatics","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Comparability; Standardization; Context (archaeology); Computer science; Data quality; Data mining; Missing data; Medicine; Geography; Mathematics; Engineering; Operations management","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0100908,0.0002499887,0.0005409142,0.0004464548,0.002833006,0.00004797125,0.001833018,0.0005385329,0.0001101664],"category_scores_gemma":[0.003350855,0.0002387071,0.00003241517,0.000571709,0.00005523958,0.002068501,0.0008800378,0.001201912,0.0006618196],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009135682,"about_ca_system_score_gemma":0.01821191,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.08391969,"about_ca_topic_score_gemma":0.5551512,"domain_scores_codex":[0.9941375,0.0005139917,0.002724401,0.0003172524,0.0007174857,0.001589365],"domain_scores_gemma":[0.9913146,0.001125854,0.0007952254,0.00362981,0.0007302311,0.002404268],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001181733,0.00002709867,0.0101826,0.08136211,0.00004012187,0.000006542947,0.1380033,0.00002737736,0.000001208194,0.006266695,0.4301309,0.3338339],"study_design_scores_gemma":[0.0008402817,0.0001372191,0.006051698,0.0009125219,0.0000183032,0.00000249108,0.1212647,0.0421886,6.830606e-7,0.0003438189,0.8278945,0.0003451809],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.2496561,0.001679904,0.05486429,0.2311131,0.03308007,0.04289803,0.2040321,0.00964181,0.1730347],"genre_scores_gemma":[0.2550059,0.001621814,0.02170999,0.1678936,0.003022064,0.0006768273,0.5486032,0.0001648663,0.00130169],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.4712315,"threshold_uncertainty_score":0.9984652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7987633485323571,"score_gpt":0.5912708250019004,"score_spread":0.2074925235304567,"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."}}