{"id":"W3011721738","doi":"10.1101/2020.03.16.20036962","title":"Assessing the quality of clinical and administrative data extracted from hospitals: The General Medicine Inpatient Initiative (GEMINI) experience","year":2020,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Health Science Centre; Trillium Health Centre; Institute for Clinical Evaluative Sciences; University Health Network; University of Toronto; Health Sciences Centre; Mount Sinai Hospital; Queen's University; St. Michael's Hospital","funders":"","keywords":"Data quality; Gold standard (test); Computer science; Medicine; Quality (philosophy); Quality management; Medical record; Data mining; Database; Missing data; Data collection; Medical physics; Statistics; Machine learning; Operations management; Surgery; Internal medicine; Mathematics","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"],"consensus_categories":["open_science"],"category_scores_codex":[0.02315095,0.0003658306,0.001236488,0.00006654995,0.0002663868,0.0005672788,0.005879423,0.0002120197,0.0003124478],"category_scores_gemma":[0.05719379,0.0001732919,0.0001419467,0.0004515155,0.002964987,0.0007299809,0.009411947,0.001111528,0.00001494758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001466771,"about_ca_system_score_gemma":0.0003385142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008691905,"about_ca_topic_score_gemma":0.0002052991,"domain_scores_codex":[0.9854502,0.005924055,0.003748748,0.001811149,0.002809738,0.0002561115],"domain_scores_gemma":[0.9705588,0.0202103,0.003581664,0.004939932,0.0004916848,0.0002176599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003927074,0.0006728112,0.6321533,0.0001478588,0.001029332,0.00007825629,0.1258102,0.00002172997,0.0002786852,0.01403659,0.0489285,0.17645],"study_design_scores_gemma":[0.0003783269,0.0001181316,0.9147174,0.000140078,0.00009422711,4.461348e-7,0.04289689,0.001661629,0.00009568638,0.02713723,0.01252419,0.0002357141],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9631934,0.0005196058,0.007943956,0.02184321,0.001636189,0.0007784778,0.001622857,0.00002908455,0.002433279],"genre_scores_gemma":[0.9944278,0.000309924,0.001686306,0.002370356,0.0005634742,0.00005521659,0.0005202672,0.00001302957,0.0000536258],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2825641,"threshold_uncertainty_score":0.9997483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8098649904626021,"score_gpt":0.6374224943190503,"score_spread":0.1724424961435518,"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."}}