{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2574152,0.001316183,0.001246244,0.003007238,0.001862935,0.002671924,0.003232153,0.002674826,0.001143187],"category_scores_gemma":[0.6004146,0.0006399119,0.001783103,0.002569666,0.003276584,0.002305349,0.003714221,0.002196533,0.0008546395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001851905,"about_ca_system_score_gemma":0.004142078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005188079,"about_ca_topic_score_gemma":0.003690392,"domain_scores_codex":[0.7164604,0.2235934,0.02042571,0.01297916,0.02481557,0.001725827],"domain_scores_gemma":[0.4762829,0.3540056,0.04815674,0.08221386,0.03777039,0.001570553],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008970807,0.0004589456,0.7878923,0.0007860545,0.001555352,0.0002527839,0.002310861,0.01124549,0.002694635,0.01559728,0.008254567,0.1680546],"study_design_scores_gemma":[0.001028872,0.001754373,0.6148339,0.003092312,0.001356347,0.001235251,0.002629385,0.1904031,0.02636564,0.1079077,0.04904389,0.0003492073],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.180165,0.0008737493,0.7968742,0.004299404,0.0009644664,0.006009912,0.002044058,0.0007770472,0.007992113],"genre_scores_gemma":[0.5738668,0.0001756285,0.4147848,0.002710725,0.0002746007,0.005628981,0.00165237,0.0001370383,0.0007690526],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7425848,"threshold_uncertainty_score":0.9157392,"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."}}