{"id":"W2808081817","doi":"10.2196/medinform.8204","title":"Validation of a Natural Language Processing Algorithm for Detecting Infectious Disease Symptoms in Primary Care Electronic Medical Records in Singapore","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Medical Research Council; Medical Research Council","keywords":"Infectious disease (medical specialty); Medicine; Medical record; Computer science; Electronic medical record; Primary care; Disease; Algorithm; Natural language processing; Artificial intelligence; Family medicine; Pathology; Internal medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02962507,0.0006089776,0.0007335232,0.003263496,0.0007303234,0.002193119,0.001281132,0.001062816,0.00102319],"category_scores_gemma":[0.06986297,0.0003034906,0.0009280266,0.001251905,0.0008569971,0.001267532,0.001502469,0.0006008799,0.0007683896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00153531,"about_ca_system_score_gemma":0.003810881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008899624,"about_ca_topic_score_gemma":0.008939772,"domain_scores_codex":[0.9828182,0.006328239,0.005082466,0.002782461,0.002677319,0.00031122],"domain_scores_gemma":[0.9276797,0.03964245,0.005199421,0.004553659,0.02216322,0.0007616016],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002586084,0.0009551523,0.5529477,0.003409582,0.001015839,0.002170547,0.005861125,0.01810422,0.03839966,0.0007840943,0.01105193,0.3627141],"study_design_scores_gemma":[0.001027978,0.002843215,0.5414371,0.0007971479,0.0009428193,0.002770725,0.004014358,0.35875,0.06723297,0.001408737,0.01858621,0.0001887479],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9526778,0.0007211039,0.03489742,0.0005545603,0.0001208358,0.001819095,0.00485882,0.002175178,0.002175275],"genre_scores_gemma":[0.8620687,0.0002480184,0.1219562,0.0002565819,0.00004246057,0.0007728509,0.01375333,0.00007089356,0.0008311129],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02962507,"threshold_uncertainty_score":0.1566742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005343844386947216,"score_gpt":0.2964574960043729,"score_spread":0.2911136516174257,"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."}}