{"id":"W3129362847","doi":"10.2196/26719","title":"Automated Travel History Extraction From Clinical Notes for Informing the Detection of Emergent Infectious Disease Events: Algorithm Development and Validation","year":2021,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. Department of Homeland Security","keywords":"Computer science; Unstructured data; Preparedness; Public health; Artificial intelligence; Veterans Affairs; Information extraction; Machine learning; Data extraction; Public health surveillance; Medical record; Infectious disease (medical specialty); Health care; MEDLINE; Data mining; Medicine; Disease; Big data","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":[0.001248397,0.0001473097,0.0003798924,0.00007743028,0.0001684335,0.00001782362,0.00004400958,0.00007845229,0.00002102656],"category_scores_gemma":[0.001457799,0.0001236883,0.00007057685,0.0001632039,0.00006799838,0.0001833318,0.00003892141,0.0001438883,0.000002107254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002433614,"about_ca_system_score_gemma":0.001647526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008938198,"about_ca_topic_score_gemma":0.0001775304,"domain_scores_codex":[0.9980839,0.0002743441,0.0007616822,0.0003485823,0.000257689,0.0002737888],"domain_scores_gemma":[0.9980258,0.000471235,0.0003691614,0.0002666951,0.0003300353,0.0005370877],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001852778,0.0002661721,0.2941236,0.0004192739,0.00009247204,0.000003905443,0.0004922011,0.00000133816,0.0001491209,0.00001505582,0.0005516681,0.7036999],"study_design_scores_gemma":[0.001434913,0.0001086276,0.8723124,0.00003606017,0.000005335862,0.00001117943,0.0001451963,0.007302588,0.00004694219,0.00001746321,0.1184611,0.0001181613],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9593766,0.004539846,0.03112541,0.002541793,0.0007837624,0.001186318,0.0002291046,0.0001813201,0.00003584021],"genre_scores_gemma":[0.9948784,0.001070391,0.001713515,0.000838748,0.0001616105,0.0001984878,0.001063458,0.00001906993,0.000056318],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7035818,"threshold_uncertainty_score":0.5043861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05354231615682493,"score_gpt":0.3569600022206557,"score_spread":0.3034176860638307,"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."}}