{"id":"W2125190682","doi":"10.1111/j.1541-0420.2006.00665.x","title":"Robustness of Prevalence Estimates Derived from Misclassified Data from Administrative Databases","year":2006,"lang":"en","type":"article","venue":"Biometrics","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Montreal General Hospital","funders":"","keywords":"Medical diagnosis; Database; Diagnosis code; Bayesian probability; Robustness (evolution); Computer science; Reimbursement; Data mining; Medicine; Artificial intelligence; Health care; Environmental health; Population","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0001875601,0.0002372848,0.0005157577,0.0004517935,0.00004597927,0.00003140664,0.0006684061,0.00007925057,0.0005571183],"category_scores_gemma":[0.002361617,0.0002140643,0.00006004755,0.002017216,0.0002589501,0.0002800098,0.0004208286,0.000109246,0.00003795553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004943451,"about_ca_system_score_gemma":0.0002585002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001043064,"about_ca_topic_score_gemma":0.0001060641,"domain_scores_codex":[0.9978525,0.00006460054,0.0005134819,0.0007179988,0.0005906323,0.000260794],"domain_scores_gemma":[0.9961397,0.0011946,0.0003231319,0.001953397,0.0002189079,0.0001702849],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009980603,0.002528345,0.7813578,0.0008021631,0.0005474941,0.0002821615,0.00003326162,0.00009116763,0.135605,0.0000686522,0.06933739,0.008348507],"study_design_scores_gemma":[0.001540276,0.0000942415,0.9525716,0.0002703291,0.0003764533,0.0000036895,0.00006314839,0.01104874,0.02970569,0.0000283155,0.004016234,0.0002812605],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.837989,0.00570132,0.02632214,0.0001275604,0.0003095417,0.0004386936,0.1284163,0.0001541801,0.000541231],"genre_scores_gemma":[0.8692943,0.0002168566,0.07419091,0.00004326413,0.0002716034,0.00001067501,0.05581483,0.00003184353,0.0001257291],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1712138,"threshold_uncertainty_score":0.872929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1719976113805118,"score_gpt":0.3665172051345096,"score_spread":0.1945195937539978,"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."}}