{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T11:31:07Z","timestamp":1789212667482,"version":"build-2803163510"},"reference-count":48,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR AI"],"abstract":"\n Background<\/jats:title>\n Collecting information on adverse events following immunization from as many sources as possible is critical for promptly identifying potential safety concerns and taking appropriate actions. Febrile convulsions are recognized as an important potential reaction to vaccination in children aged <6 years.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n The primary aim of this study was to evaluate the performance of natural language processing techniques and machine learning (ML) models for the rapid detection of febrile convulsion presentations in emergency departments (EDs), especially with respect to the minimum training data requirements to obtain optimum model performance. In addition, we examined the deployment requirements for a ML model to perform real-time monitoring of ED triage notes.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We developed a pattern matching approach as a baseline and evaluated ML models for the classification of febrile convulsions in ED triage notes to determine both their training requirements and their effectiveness in detecting febrile convulsions. We measured their performance during training and then compared the deployed models\u2019 result on new incoming ED data.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Although the best standard neural networks had acceptable performance and were low-resource models, transformer-based models outperformed them substantially, justifying their ongoing deployment.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Using natural language processing, particularly with the use of large language models, offers significant advantages in syndromic surveillance. Large language models make highly effective classifiers, and their text generation capacity can be used to enhance the quality and diversity of training data.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/54449","type":"journal-article","created":{"date-parts":[[2024,3,30]],"date-time":"2024-03-30T11:12:01Z","timestamp":1711797121000},"page":"e54449","source":"Crossref","is-referenced-by-count":6,"title":["Near Real-Time Syndromic Surveillance of Emergency Department Triage Texts Using Natural Language Processing: Case Study in Febrile Convulsion Detection"],"prefix":"10.2196","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6146-1415","authenticated-orcid":false,"given":"Sedigh","family":"Khademi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6554-9027","authenticated-orcid":false,"given":"Christopher","family":"Palmer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7022-6596","authenticated-orcid":false,"given":"Muhammad","family":"Javed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3498-6256","authenticated-orcid":false,"given":"Gerardo Luis","family":"Dimaguila","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7594-0361","authenticated-orcid":false,"given":"Hazel","family":"Clothier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9905-2035","authenticated-orcid":false,"given":"Jim","family":"Buttery","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9287-8712","authenticated-orcid":false,"given":"Jim","family":"Black","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2024,8,30]]},"reference":[{"issue":"2","key":"ref1","first-page":"389","volume":"127","author":"Duffner, PK","year":"2011","journal-title":"Am J Pediatr"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/fped.2021.801321"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1136\/adc.2003.028449"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1586\/14760584.2013.814781"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3345\/kjp.2014.57.9.384"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.vaccine.2011.05.054"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2010-000016"},{"key":"ref8","unstructured":"Investigation into febrile reactions in young children following 2010 seasonal trivalent influenza vaccinationDepartment of Health, Government of Australia20102024-04-29https:\/\/www.tga.gov.au\/sites\/default\/files\/alerts-medicine-seasonal-flu-100702.pdf"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.c2419"},{"key":"ref10","unstructured":"HorvathMReview of the management of adverse events associated with Panvax and FluvaxDepartment of Health, Government of Australia20112024-04-29https:\/\/www.tga.gov.au\/news\/media-releases\/review-management-adverse-events-associated-panvax-and-fluvax"},{"key":"ref11","unstructured":"StokesBMinisterial review into the public health response into the adverse events to the seasonal influenza vaccineMinister for Health, Government of Australia20102024-04-29https:\/\/www.health.wa.gov.au\/~\/media\/Files\/Corporate\/Reports-and-publications\/PDF\/Stokes_Report.pdf"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s40264-017-0520-7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0224702"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/21645515.2022.2100173"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(11)60834-9"},{"key":"ref16","first-page":"5","volume":"53","author":"Henning, KJ","year":"2004","journal-title":"MMWR Suppl"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/civ264"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1136\/bmjgh-2018-001065"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.vaccine.2020.05.078"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-020-09949-y"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10900-011-9469-0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1055\/s-0039-1691842"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2003.09.007"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.2196\/41331"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2013.04.003"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-021-11132-w"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5210\/ojphi.v6i2.5469"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1111\/acem.12925"},{"key":"ref29","unstructured":"AamerHOfoghiBVerspoorKMSyndromic surveillance on the Victorian chief complaint data set using a hybrid statistical and machine learning techniqueProceedings of the 2016 Health Data Analytics Conference2016HDAC '16October 11-12, 2016Brisbane, Australia"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2011-000465"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2019.103158"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/apsipa.2018.8659710"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajem.2018.06.062"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0174708"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1177\/1833358319857188"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jemermed.2013.05.036"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2022.104963"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2458-11-338"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocab261"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.2196\/17984"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.306.6894.1743"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00492"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3579375.3579401"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.clinicalnlp-1.17"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.2196\/34305"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2018.10.005"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocac121"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.414"}],"container-title":["JMIR AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ai.jmir.org\/2024\/1\/e54449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:41:12Z","timestamp":1782841272000},"score":1,"resource":{"primary":{"URL":"https:\/\/ai.jmir.org\/2024\/1\/e54449"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,30]]},"references-count":48,"URL":"https:\/\/doi.org\/10.2196\/54449","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.54449","asserted-by":"object"}]},"ISSN":["2817-1705"],"issn-type":[{"value":"2817-1705","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,30]]}}}