{"id":"W3106195149","doi":"10.1093/jamia/ocaa225","title":"Assessing the quality of clinical and administrative data extracted from hospitals: the General Medicine Inpatient Initiative (GEMINI) experience","year":2020,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Health Science Centre; Trillium Health Centre; Institute for Clinical Evaluative Sciences; Health Sciences Centre; Mount Sinai Hospital; University of Toronto; University Health Network; Queen's University; St. Michael's Hospital","funders":"University of Toronto","keywords":"Data quality; Data extraction; Computer science; Gold standard (test); Quality (philosophy); Quality management; Data collection; Data mining; Database; Medicine; MEDLINE; Statistics; Operations management; Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02694858,0.000119626,0.0007019647,0.00003633516,0.0002021425,0.000225763,0.002738889,0.00006304524,0.00007633808],"category_scores_gemma":[0.1491516,0.00004728966,0.0001203662,0.0006692563,0.001335533,0.001258269,0.0010173,0.0007150454,0.000003145027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004691573,"about_ca_system_score_gemma":0.000364506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001493874,"about_ca_topic_score_gemma":0.00002511587,"domain_scores_codex":[0.9884688,0.002604991,0.003922367,0.0001422903,0.004705845,0.0001557224],"domain_scores_gemma":[0.9619874,0.02015221,0.01586803,0.0008826755,0.0008382773,0.0002714251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002569458,0.0002846608,0.3493963,0.00002616668,0.00085094,0.00000566268,0.1505964,0.00004194603,0.00004271953,0.001629136,0.1403435,0.3565255],"study_design_scores_gemma":[0.0007154464,0.0003637339,0.8092613,0.00008574195,0.0001034789,0.000002012929,0.1616699,0.01556265,0.00003207186,0.002208291,0.009897513,0.0000979286],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9196126,0.00004643229,0.009087991,0.06996868,0.0004803486,0.000164372,0.0001031436,0.000003931286,0.0005325031],"genre_scores_gemma":[0.9816279,0.0002190234,0.001448368,0.01626003,0.0004141408,0.00000180825,0.00001450673,0.000003390338,0.00001081245],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4598649,"threshold_uncertainty_score":0.9339893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.540661436719735,"score_gpt":0.5948575964308802,"score_spread":0.05419615971114522,"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."}}