{"id":"W3132608056","doi":"10.1016/j.conctc.2021.100749","title":"Improving data quality in observational research studies: Report of the Cure Glomerulonephropathy (CureGN) network","year":2021,"lang":"en","type":"article","venue":"Contemporary Clinical Trials Communications","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Hôpital Maisonneuve-Rosemont","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Observational study; Data quality; Center of excellence; Computer science; Quality (philosophy); Data collection; Data science; Excellence; Medicine; Database; Operations management; Engineering; Pathology","routes":{"ca_aff":true,"ca_fund":false,"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":["metaresearch","sts","open_science","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3295589,0.0002034589,0.002066738,0.0001035195,0.0005077029,0.0000521511,0.004141319,0.0007122357,0.00005401302],"category_scores_gemma":[0.7739085,0.00014784,0.0005980287,0.002396578,0.003461342,0.0002772272,0.01104323,0.007244683,0.00001644565],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001450086,"about_ca_system_score_gemma":0.01139913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000457924,"about_ca_topic_score_gemma":0.003102896,"domain_scores_codex":[0.9273857,0.05442558,0.01263468,0.001538637,0.003323613,0.0006918217],"domain_scores_gemma":[0.06768035,0.8698311,0.005045804,0.04283352,0.01393701,0.0006722143],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009503545,0.003523407,0.8399519,0.0007473665,0.0009667677,0.0002169592,0.0003443432,0.00001113574,0.0006776956,0.085681,0.060222,0.006707051],"study_design_scores_gemma":[0.01135404,0.0005643239,0.5221741,0.007016154,0.0003211247,0.00008454904,0.0050176,0.002019237,0.0002203134,0.2452264,0.2054026,0.0005995563],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1064834,0.1176503,0.0007043623,0.7459783,0.003018189,0.006926023,0.0005566253,0.0001479481,0.01853479],"genre_scores_gemma":[0.9424888,0.03010282,0.01991262,0.002523123,0.0008955357,0.0001802602,0.0008992372,0.0000492041,0.002948385],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8597053,"threshold_uncertainty_score":0.9992507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9906619144517624,"score_gpt":0.7993528084878837,"score_spread":0.1913091059638787,"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."}}