{"id":"W2137026411","doi":"10.1186/s12911-015-0187-x","title":"Using information theory to identify redundancy in common laboratory tests in the intensive care unit","year":2015,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Clinical Laboratory Practices and Quality Control","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; University of Waterloo","funders":"Southeastern Ontario Academic Medical Organization; University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Queen's University","keywords":"Intensive care unit; Redundancy (engineering); Computer science; Health informatics; Workflow; Medicine; Blood urea nitrogen; Creatinine; Data mining; Intensive care medicine; Statistics; Database; Mathematics; Internal medicine; Pathology; Public health","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.005693857,0.0001378062,0.0003858577,0.0002929705,0.00006599184,0.0001569834,0.0001941095,0.000191067,0.00002519789],"category_scores_gemma":[0.01826628,0.00009043422,0.00003858692,0.000701188,0.00007403376,0.0007225354,0.0001708085,0.000557382,0.00003522164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007735661,"about_ca_system_score_gemma":0.0006140605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002720621,"about_ca_topic_score_gemma":0.0003617743,"domain_scores_codex":[0.9971076,0.0002883064,0.001299665,0.00009298858,0.0009886468,0.000222852],"domain_scores_gemma":[0.9941542,0.004111025,0.000286071,0.0003354861,0.0008186704,0.0002945888],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.003853647,0.0001837335,0.2075236,0.0009208715,0.00003421204,0.0001674028,0.09690218,0.001269744,0.000009593572,0.01106678,0.001776204,0.676292],"study_design_scores_gemma":[0.01267589,0.0007195043,0.1175037,0.00723612,0.0001332702,0.0001787025,0.5614634,0.2590068,0.000006419805,0.01234175,0.0281468,0.0005876629],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9589134,0.0003514069,0.03909156,0.0002476568,0.0001974,0.0004822547,0.00001054698,0.00001585337,0.0006899091],"genre_scores_gemma":[0.9562674,0.00003022381,0.02173038,0.02187233,0.00006805525,0.00001104896,0.00001250673,0.000007041648,0.000001052305],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6757044,"threshold_uncertainty_score":0.9900033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1901451932935321,"score_gpt":0.4996146743206948,"score_spread":0.3094694810271627,"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."}}