{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T19:09:30Z","timestamp":1776539370018,"version":"3.51.2"},"posted":{"date-parts":[[2025,5,16]]},"group-title":"Epidemiology","reference-count":43,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T00:00:00Z","timestamp":1747353600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,5,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Detecting infectious disease outbreaks promptly is crucial for effective public health responses, minimizing transmission, and enabling critical interventions. This study introduces a method that integrates machine learning (ML)-based diagnostic predictions with traditional epidemiological surveillance to enhance biosurveillance systems. Using 4.5 million patient records from 2010 to 2022, ML models were trained to predict, within 24-hour intervals, the likelihood of patients being diagnosed with infectious or unspecified gastrointestinal, respiratory, or neurological diseases. High-confidence predictions were combined with final diagnoses and analyzed using spatiotemporal outbreak detection techniques. Among diseases with five or more outbreaks between 2014 and 2022, 33.3% (41 of 123 outbreaks) were detected earlier, with lead times ranging from 1 to 24 days and an average of 1.33 false positive outbreaks detected annually. This approach demonstrates the potential of integrating ML with conventional methods for faster outbreak detection, provided adequate disease-specific training data is available.<\/jats:p>","DOI":"10.1101\/2025.05.14.25327606","type":"posted-content","created":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T15:55:14Z","timestamp":1747410914000},"source":"Crossref","is-referenced-by-count":5,"title":["AI-Enabled Diagnostic Prediction within Electronic Health Records to Enhance Biosurveillance and Early Outbreak Detection"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0320-280X","authenticated-orcid":false,"given":"Andre R.","family":"Goncalves","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose Cadena","family":"Pico","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeping","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Schlessinger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Greene","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liam","family":"O\u2019suilleabhain","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heather","family":"Clancy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Vollmer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Bates","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Priyadip","family":"Ray","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2025052009150854000_2025.05.14.25327606v1.1","doi-asserted-by":"publisher","DOI":"10.3201\/eid1410.071341"},{"key":"2025052009150854000_2025.05.14.25327606v1.2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0016579"},{"key":"2025052009150854000_2025.05.14.25327606v1.3","doi-asserted-by":"crossref","unstructured":"Kman, N.E. and D.J. Bachmann , Biosurveillance: a review and update. Adv Prev Med, 2012. 2012: p. 301408.","DOI":"10.1155\/2012\/301408"},{"key":"2025052009150854000_2025.05.14.25327606v1.4","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/154.4.385"},{"issue":"1_suppl","key":"2025052009150854000_2025.05.14.25327606v1.5","doi-asserted-by":"crossref","first-page":"72S","DOI":"10.1177\/00333549211018673","article-title":"Emergency Medical Services and Syndromic Surveillance: A Comparison With Traditional Surveillance and Effects on Timeliness","volume":"136","year":"2021","journal-title":"Public Health Rep"},{"key":"2025052009150854000_2025.05.14.25327606v1.6","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2458-5-105"},{"issue":"11","key":"2025052009150854000_2025.05.14.25327606v1.7","doi-asserted-by":"crossref","first-page":"e1003892","DOI":"10.1371\/journal.pcbi.1003892","article-title":"Global disease monitoring and forecasting with Wikipedia","volume":"10","year":"2014","journal-title":"PLoS Comput Biol"},{"key":"2025052009150854000_2025.05.14.25327606v1.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.annemergmed.2011.08.004"},{"issue":"3","key":"2025052009150854000_2025.05.14.25327606v1.9","doi-asserted-by":"crossref","first-page":"416","DOI":"10.3201\/eid1203.050573","article-title":"Medication sales and syndromic surveillance, France","volume":"12","year":"2006","journal-title":"Emerg Infect Dis"},{"key":"2025052009150854000_2025.05.14.25327606v1.10","doi-asserted-by":"publisher","DOI":"10.1038\/nature07634"},{"key":"2025052009150854000_2025.05.14.25327606v1.11","doi-asserted-by":"publisher","DOI":"10.1126\/science.1248506"},{"key":"2025052009150854000_2025.05.14.25327606v1.12","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-publhealth-031914-122747"},{"key":"2025052009150854000_2025.05.14.25327606v1.13","first-page":"5","article-title":"What is syndromic surveillance?","volume":"53","year":"2004","journal-title":"MMWR Suppl"},{"key":"2025052009150854000_2025.05.14.25327606v1.14","doi-asserted-by":"publisher","DOI":"10.1097\/DMP.0b013e31819f4483"},{"key":"2025052009150854000_2025.05.14.25327606v1.15","unstructured":"(NSSP), N.S.S.P. BioSense Platform. 2024 9\/6\/2024]; Available from: https:\/\/www.cdc.gov\/nssp\/php\/about\/about-nssp-and-the-biosense-platform.html."},{"issue":"6","key":"2025052009150854000_2025.05.14.25327606v1.16","doi-asserted-by":"crossref","first-page":"e26303","DOI":"10.2196\/26303","article-title":"Electronic Surveillance System for the Early Notification of Community-Based Epidemics (ESSENCE): Overview, Components, and Public Health Applications","volume":"7","year":"2021","journal-title":"JMIR Public Health Surveill"},{"key":"2025052009150854000_2025.05.14.25327606v1.17","doi-asserted-by":"publisher","DOI":"10.1197\/jamia.M1345"},{"issue":"3","key":"2025052009150854000_2025.05.14.25327606v1.18","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1093\/cid\/ciab946","article-title":"Whole-Genome Sequencing Surveillance and Machine Learning of the Electronic Health Record for Enhanced Healthcare Outbreak Detection","volume":"75","year":"2022","journal-title":"Clin Infect Dis"},{"issue":"5","key":"2025052009150854000_2025.05.14.25327606v1.19","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1017\/ice.2019.84","volume":"40","author":"Automated data Mining of the electronic health record for investigation of healthcare-associated outbreaks - CORRIGENDUM","year":"2019","journal-title":"Infect Control Hosp Epidemiol"},{"key":"2025052009150854000_2025.05.14.25327606v1.20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0100845"},{"issue":"1","key":"2025052009150854000_2025.05.14.25327606v1.21","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1186\/s12879-016-2175-x","article-title":"Influenza epidemic surveillance and prediction based on electronic health record data from an out-of-hours general practitioner cooperative: model development and validation on 2003-2015 data","volume":"17","year":"2017","journal-title":"BMC Infect Dis"},{"key":"2025052009150854000_2025.05.14.25327606v1.22","doi-asserted-by":"crossref","first-page":"105251","DOI":"10.1016\/j.jcv.2022.105251","article-title":"Early detection of COVID-19 outbreaks using textual analysis of electronic medical records","volume":"155","year":"2022","journal-title":"J Clin Virol"},{"issue":"2","key":"2025052009150854000_2025.05.14.25327606v1.23","first-page":"145","article-title":"A near real-time electronic health record-based COVID-19 surveillance system: An experience from a developing country","volume":"53","year":"2024","journal-title":"Health Inf Manag"},{"key":"2025052009150854000_2025.05.14.25327606v1.24","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2020-048211"},{"issue":"3","key":"2025052009150854000_2025.05.14.25327606v1.25","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1089\/hs.2015.0063","article-title":"A Conceptual Architecture for National Biosurveillance: Moving Beyond Situational Awareness to Enable Digital Detection of Emerging Threats","volume":"14","year":"2016","journal-title":"Health Secur"},{"issue":"5","key":"2025052009150854000_2025.05.14.25327606v1.26","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1513\/AnnalsATS.202104-451OC","article-title":"Evaluation of Incident 7-Day Infection and Sepsis Hospitalizations in an Integrated Health System","volume":"19","year":"2022","journal-title":"Ann Am Thorac Soc"},{"key":"2025052009150854000_2025.05.14.25327606v1.27","doi-asserted-by":"publisher","DOI":"10.1097\/MLR.0b013e3181589bb6"},{"key":"2025052009150854000_2025.05.14.25327606v1.28","doi-asserted-by":"publisher","DOI":"10.1097\/MLR.0b013e3182881c8e"},{"issue":"12","key":"2025052009150854000_2025.05.14.25327606v1.29","doi-asserted-by":"crossref","first-page":"e1916769","DOI":"10.1001\/jamanetworkopen.2019.16769","article-title":"Multiyear Rehospitalization Rates and Hospital Outcomes in an Integrated Health Care System","volume":"2","year":"2019","journal-title":"JAMA Netw Open"},{"key":"2025052009150854000_2025.05.14.25327606v1.30","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMsa2001090"},{"key":"2025052009150854000_2025.05.14.25327606v1.31","doi-asserted-by":"crossref","unstructured":"Alsentzer, E. , et al., Publicly available clinical BERT embeddings. arXiv preprint arXiv:1904.03323, 2019.","DOI":"10.18653\/v1\/W19-1909"},{"key":"2025052009150854000_2025.05.14.25327606v1.32","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"2025052009150854000_2025.05.14.25327606v1.33","unstructured":"Devlin, J. , Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018."},{"key":"2025052009150854000_2025.05.14.25327606v1.34","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"2025052009150854000_2025.05.14.25327606v1.35","doi-asserted-by":"crossref","first-page":"160035","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","year":"2016","journal-title":"Sci Data"},{"key":"2025052009150854000_2025.05.14.25327606v1.36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.02028"},{"issue":"1","key":"2025052009150854000_2025.05.14.25327606v1.37","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1038\/s41746-018-0029-1","article-title":"Scalable and accurate deep learning with electronic health records","volume":"1","year":"2018","journal-title":"NPJ digital medicine"},{"issue":"1","key":"2025052009150854000_2025.05.14.25327606v1.38","doi-asserted-by":"crossref","first-page":"19543","DOI":"10.1038\/s41598-021-98071-z","article-title":"Budget constrained machine learning for early prediction of adverse outcomes for COVID-19 patients","volume":"11","year":"2021","journal-title":"Sci Rep"},{"issue":"8","key":"2025052009150854000_2025.05.14.25327606v1.39","doi-asserted-by":"crossref","first-page":"4258","DOI":"10.1109\/JBHI.2022.3171673","article-title":"Dynamic Sepsis Prediction for Intensive Care Unit Patients Using XGBoost-Based Model With Novel Time-Dependent Features","volume":"26","year":"2022","journal-title":"Ieee Journal of Biomedical and Health Informatics"},{"key":"2025052009150854000_2025.05.14.25327606v1.40","doi-asserted-by":"publisher","DOI":"10.1080\/03610929708831995"},{"key":"2025052009150854000_2025.05.14.25327606v1.41","doi-asserted-by":"publisher","DOI":"10.1002\/sim.2818"},{"issue":"13","key":"2025052009150854000_2025.05.14.25327606v1.42","doi-asserted-by":"crossref","first-page":"2185","DOI":"10.1002\/sim.5675","article-title":"Fast subset scan for multivariate event detection","volume":"32","year":"2013","journal-title":"Statistics in medicine"},{"issue":"2","key":"2025052009150854000_2025.05.14.25327606v1.43","doi-asserted-by":"crossref","first-page":"e12110","DOI":"10.2196\/12110","article-title":"Detection of spatiotemporal prescription opioid hot spots with network scan statistics: multistate analysis","volume":"5","year":"2019","journal-title":"JMIR public health and surveillance"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.05.14.25327606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:36:09Z","timestamp":1768509369000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.05.14.25327606"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,16]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1101\/2025.05.14.25327606","relation":{},"subject":[],"published":{"date-parts":[[2025,5,16]]},"subtype":"preprint"}}