{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007750068,0.000190969,0.0004587691,0.0003111319,0.00005138145,0.00001992308,0.0002037082,0.0002143591,0.00006395314],"category_scores_gemma":[0.001659996,0.000165958,0.00008921241,0.0005836199,0.0002210806,0.0003146508,0.0001059117,0.0005995719,0.000006234355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005004956,"about_ca_system_score_gemma":0.002035532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003378262,"about_ca_topic_score_gemma":0.0001930356,"domain_scores_codex":[0.9971986,0.00006091113,0.0009683137,0.0001726942,0.001102596,0.0004968462],"domain_scores_gemma":[0.9986479,0.0001683654,0.0002876172,0.0002654698,0.0002402298,0.0003904616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002494424,0.0002063086,0.02475788,0.002907603,0.00002525871,0.0000491077,0.007141002,0.000001557286,0.00002407842,0.000006322765,0.00009870693,0.9645327],"study_design_scores_gemma":[0.02351387,0.002003018,0.1130513,0.01347261,0.0001974095,0.000260234,0.01001274,0.831901,0.001501683,0.000167036,0.002786373,0.001132774],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9942662,0.0006733252,0.003095872,0.0001027331,0.0001691931,0.0009932923,0.00004638496,0.0001180413,0.0005349972],"genre_scores_gemma":[0.996162,0.00002382949,0.001765838,0.0007712037,0.0002868603,0.000141871,0.0008095144,0.00002588097,0.00001301535],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9633999,"threshold_uncertainty_score":0.6767573,"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."}}