{"id":"W2050091824","doi":"10.1136/bmj.c4226","title":"Importance of accurately identifying disease in studies using electronic health records","year":2010,"lang":"en","type":"article","venue":"BMJ","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":161,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; Ottawa Hospital; University of Ottawa; University of Toronto; Statistics Canada","funders":"","keywords":"Health records; Electronic health record; Disease; Data science; Computer science; Data mining; Medicine; Health care; Political science; Pathology","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":[0.0005063451,0.0001128082,0.0003067669,0.0001317792,0.0000377933,0.00001217316,0.00008187573,0.00001907474,0.00007814704],"category_scores_gemma":[0.0002846101,0.0001052421,0.00006407012,0.0002515577,0.0000757454,0.0001383085,0.00006611252,0.0001928231,0.000005006845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002037683,"about_ca_system_score_gemma":0.0009033098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001717733,"about_ca_topic_score_gemma":0.001279666,"domain_scores_codex":[0.998751,0.00002913439,0.0004421594,0.0002237833,0.0002173128,0.0003365932],"domain_scores_gemma":[0.9992236,0.00003415088,0.0002273428,0.0003522256,0.00005512886,0.0001075392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007637215,0.0005945477,0.9568217,0.005162019,0.0004319993,0.0003657196,0.0008991878,0.0002285892,0.00316251,0.01177232,0.01122954,0.008568147],"study_design_scores_gemma":[0.002503235,0.0001673511,0.9835432,0.001019222,0.0001815461,0.00001250725,0.002001145,0.002317125,0.0001726957,0.005985135,0.001809949,0.0002868938],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9925698,0.002927891,0.00003112277,0.002682837,0.000293985,0.0006418283,0.000004431188,0.00003658401,0.0008115096],"genre_scores_gemma":[0.9984888,0.0004235088,0.0003818324,0.0002616859,0.0001579943,0.00002582143,0.00001103272,0.0000159452,0.0002333214],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0267215,"threshold_uncertainty_score":0.4291646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1610533120942863,"score_gpt":0.4712441419890614,"score_spread":0.3101908298947751,"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."}}