{"id":"W2334183420","doi":"10.1097/mlr.0000000000000324","title":"Validation of Diagnostic Groups Based on Health Care Utilization Data Should Adjust for Sampling Strategy","year":2015,"lang":"en","type":"article","venue":"Medical Care","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Diagnosis code; False positive paradox; Sampling (signal processing); Population; Health care; Diagnostic accuracy; Statistics; Environmental health; Computer science; Internal medicine; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0003119187,0.0001307521,0.0003164803,0.00007262894,0.0000496744,0.00001025177,0.000136882,0.0001257543,0.00009506527],"category_scores_gemma":[0.004091307,0.000101659,0.0000558154,0.0001304678,0.00003554615,0.00004500238,0.00003640548,0.0001049329,0.000004684518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002439295,"about_ca_system_score_gemma":0.0008185885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000183295,"about_ca_topic_score_gemma":0.0001708161,"domain_scores_codex":[0.9982972,0.00006393569,0.000321114,0.0003276202,0.000798037,0.0001921077],"domain_scores_gemma":[0.9978501,0.0008255366,0.0001021932,0.0005105558,0.0003276849,0.0003839723],"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":[0.0007796719,0.002214274,0.181853,0.004765414,0.0001793729,0.00006878909,0.007507391,0.002392833,0.000009215897,0.001153993,0.04977474,0.7493013],"study_design_scores_gemma":[0.1068602,0.06032297,0.376838,0.01994168,0.00464404,0.00006682748,0.1671621,0.1003475,0.02323264,0.0007941717,0.1371448,0.002645004],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8799259,0.03633985,0.03930289,0.02906243,0.002034955,0.007530456,0.003376356,0.0003374291,0.002089711],"genre_scores_gemma":[0.9833622,0.0001199259,0.0007115562,0.001673056,0.000225137,0.00009088308,0.0137919,0.00002285917,0.000002476155],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7466563,"threshold_uncertainty_score":0.4897972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5522848477692748,"score_gpt":0.4895632277901571,"score_spread":0.06272161997911768,"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."}}