{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T17:39:11Z","timestamp":1786556351946,"version":"build-2736575974"},"reference-count":36,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:00:00Z","timestamp":1786492800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/publicdomain\/zero\/1.0\/"}],"funder":[{"DOI":"10.13039\/100000030","name":"Centers for Disease Control and Prevention","doi-asserted-by":"publisher","award":["75D30120P09851"],"award-info":[{"award-number":["75D30120P09851"]}],"id":[{"id":"10.13039\/100000030","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000030","name":"Centers for Disease Control and Prevention","doi-asserted-by":"publisher","award":["75D30122C14640"],"award-info":[{"award-number":["75D30122C14640"]}],"id":[{"id":"10.13039\/100000030","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>\n                    A tool capable of quickly and accurately identifying Lyme disease (LD) cases in endemic areas would have powerful applications in both research and public health. Using data from a single health system in an area with high LD incidence, we evaluated the feasibility and accuracy of data-driven algorithms to accurately identify LD cases based on easily extracted, structured data elements that are available in electronic health records (EHR). We used random forest and decision tree algorithms to explore the importance of various data elements and to investigate how different combinations of data elements accurately classified clinical events as either LD cases or non-cases. The data elements explored included patient demographics, International Classification of Diseases, 10\n                    <jats:sup>th<\/jats:sup>\n                    Revision, (ICD) codes, LD laboratory tests and their results, and antibiotic prescription orders. Our best performing algorithm was a manually constructed decision tree that incorporated information from three presence\/absence variables: an LD ICD code (A69.2x), a positive LD serology test, and a doxycycline order occurring within 30 days of either of the other two elements, which achieved 82% accuracy, 93% sensitivity, 60% adjusted positive predictive value, 68% specificity, and 91% adjusted negative predictive value. Findings from this exploratory effort suggest that data-driven algorithms based on EHR elements hold promise to identify LD cases when detailed chart reviews are impractical. Further efforts may differentiate algorithms between confirmed and probable LD cases, pediatric and adult populations, and utilize text searching to improve accuracy.\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0349121","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T17:21:52Z","timestamp":1786555312000},"page":"e0349121","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring data-driven algorithms to identify Lyme disease cases in electronic health records"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7551-4810","authenticated-orcid":true,"given":"Alexandra M.","family":"Linz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erica","family":"Scotty","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jennifer K.","family":"Meece","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7754-6480","authenticated-orcid":true,"given":"Courtney C.","family":"Nawrocki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kiersten J.","family":"Kugeler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah A.","family":"Hook","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alison F.","family":"Hinckley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna M.","family":"Schotthoefer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,12]]},"reference":[{"key":"pone.0349121.ref001","doi-asserted-by":"crossref","DOI":"10.1093\/infdis\/jiae230","article-title":"Lyme Disease Surveillance and Epidemiology in the United States: A Historical Perspective","volume":"230","author":"P Mead","year":"2024","journal-title":"J Infect Dis"},{"issue":"2","key":"pone.0349121.ref002","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1056\/NEJM200107123450207","article-title":"Lyme Disease","volume":"345","author":"AC Steere","year":"2001","journal-title":"N Engl J Med"},{"key":"pone.0349121.ref003","first-page":"333","article-title":"Lyme Disease in Humans","volume":"42","author":"JD Radolf","year":"2021","journal-title":"Curr Issues Mol Biol"},{"issue":"22","key":"pone.0349121.ref004","first-page":"1","article-title":"Surveillance for Lyme Disease - United States, 2008-2015","volume":"66","author":"AM Schwartz","year":"2017","journal-title":"Morb Mortal Wkly Rep Surveill Summ"},{"issue":"9","key":"pone.0349121.ref005","doi-asserted-by":"crossref","first-page":"1625","DOI":"10.3201\/eid2109.150417","article-title":"Incidence of clinician-diagnosed Lyme disease, United States, 2005-2010","volume":"21","author":"CA Nelson","year":"2015","journal-title":"Emerg Infect Dis"},{"issue":"2","key":"pone.0349121.ref006","doi-asserted-by":"crossref","first-page":"616","DOI":"10.3201\/eid2702.202731","article-title":"Estimating the Frequency of Lyme Disease Diagnoses, United States, 2010-2018","volume":"27","author":"KJ Kugeler","year":"2021","journal-title":"Emerg Infect Dis"},{"issue":"2","key":"pone.0349121.ref007","doi-asserted-by":"crossref","first-page":"499","DOI":"10.3201\/eid2702.202728","article-title":"Use of commercial claims data for evaluating trends in Lyme disease diagnoses, United States, 2010-2018","volume":"27","author":"AM Schwartz","year":"2021","journal-title":"Emerg Infect Dis"},{"key":"pone.0349121.ref008","doi-asserted-by":"crossref","first-page":"1620","DOI":"10.1111\/j.1475-6773.2005.00444.x","article-title":"Measuring diagnoses: ICD code accuracy","volume":"40","author":"KJ O\u2019Malley","year":"2005","journal-title":"Health Serv Res"},{"issue":"9","key":"pone.0349121.ref009","doi-asserted-by":"crossref","first-page":"1772","DOI":"10.3201\/eid2909.221931","article-title":"Validation of Claims-Based Algorithm for Lyme Disease, Massachusetts, USA","volume":"29","author":"NM Cocoros","year":"2023","journal-title":"Emerg Infect Dis"},{"issue":"7","key":"pone.0349121.ref010","doi-asserted-by":"crossref","first-page":"1374","DOI":"10.3201\/eid3007.230942","article-title":"Electronic health record data for Lyme disease surveillance, Massachusetts, USA, 2017-2018","volume":"30","author":"K Nagavedu","year":"2024","journal-title":"Emerg Infect Dis"},{"issue":"4","key":"pone.0349121.ref011","doi-asserted-by":"crossref","DOI":"10.1093\/ofid\/ofaf109","article-title":"Validation of Algorithms to Detect Acute and Disseminated Lyme Disease in U.S. Administrative Claims Data","volume":"12","author":"SA Kluberg","year":"2025","journal-title":"Open Forum Infect Dis"},{"issue":"2","key":"pone.0349121.ref012","doi-asserted-by":"crossref","DOI":"10.1093\/ofid\/ofae758","article-title":"Epidemiology of Lyme Disease as Identified Through Electronic Health Records in a Large Midwestern Health System, 2016\u20132019","volume":"12","author":"KJ Kugeler","year":"2025","journal-title":"Open Forum Infect Dis"},{"issue":"1","key":"pone.0349121.ref013","first-page":"196","article-title":"A comparative study on decision tree and random forest using R tool","volume":"4","author":"T Prajwala","year":"2015","journal-title":"Int J Adv Res Comput Commun Eng"},{"key":"pone.0349121.ref014","doi-asserted-by":"crossref","first-page":"100041","DOI":"10.1016\/j.ibmed.2021.100041","article-title":"Appropriate use of machine learning in healthcare","volume":"5","author":"B Ozaydin","year":"2021","journal-title":"Intelligence-Based Medicine"},{"key":"pone.0349121.ref015","author":"Centers for Disease Control and Prevention","year":"2001"},{"issue":"6","key":"pone.0349121.ref016","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1038\/s41557-021-00716-z","article-title":"Best practices in machine learning for chemistry","volume":"13","author":"N Artrith","year":"2021","journal-title":"Nat Chem"},{"issue":"4","key":"pone.0349121.ref017","article-title":"Mapping ICD-10 and ICD-10-CM codes to phecodes: workflow development and initial evaluation","volume":"7","author":"P Wu","year":"2019","journal-title":"JMIR Medical Informatics"},{"key":"pone.0349121.ref018","year":"2020"},{"key":"pone.0349121.ref019","year":"2019"},{"issue":"43","key":"pone.0349121.ref020","doi-asserted-by":"crossref","first-page":"1686","DOI":"10.21105\/joss.01686","article-title":"Welcome to the Tidyverse","volume":"4","author":"H Wickham","year":"2019","journal-title":"JOSS"},{"issue":"31","key":"pone.0349121.ref021","first-page":"590","article-title":"Recommendations for test performance and interpretation from the Second National Conference on Serologic Diagnosis of Lyme Disease","volume":"44","author":"Centers for Disease Control and Prevention CDC","year":"1995","journal-title":"MMWR Morb Mortal Wkly Rep"},{"issue":"1","key":"pone.0349121.ref022","doi-asserted-by":"crossref","DOI":"10.1093\/cid\/ciaa1215","article-title":"Clinical Practice Guidelines by the Infectious Diseases Society of America (IDSA), American Academy of Neurology (AAN), and American College of Rheumatology (ACR): 2020 Guidelines for the Prevention, Diagnosis and Treatment of Lyme Disease","volume":"72","author":"PM Lantos","year":"2021","journal-title":"Clin Infect Dis"},{"key":"pone.0349121.ref023","unstructured":"Liaw A, Wiener M. Classification and Regression by RandomForest. 2002;2\/3:18\u201322."},{"issue":"1","key":"pone.0349121.ref024","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"pone.0349121.ref025","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1186\/1471-2105-12-77","article-title":"pROC: an open-source package for R and S+ to analyze and compare ROC curves","volume":"12","author":"X Robin","year":"2011","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"pone.0349121.ref026","doi-asserted-by":"crossref","first-page":"1322","DOI":"10.1186\/s12879-024-10195-5","article-title":"Optimizing identification of Lyme disease diagnoses in commercial insurance claims data, United States, 2016-2019","volume":"24","author":"CC Nawrocki","year":"2024","journal-title":"BMC Infect Dis"},{"issue":"2","key":"pone.0349121.ref027","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1111\/zph.12446","article-title":"Exploring an alternative approach to Lyme disease surveillance in Maryland","volume":"65","author":"H Rutz","year":"2018","journal-title":"Zoonoses Public Health"},{"issue":"7","key":"pone.0349121.ref028","doi-asserted-by":"crossref","DOI":"10.3201\/eid3107.250009","article-title":"Lyme disease testing practices, Wisconsin, USA, 2016\u20132019","volume":"31","author":"KJ Kugeler","year":"2025","journal-title":"Emerg Infect Dis"},{"key":"pone.0349121.ref029","author":"Centers for Disease Control and Prevention","year":"2021"},{"key":"pone.0349121.ref030","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1177\/00333549251314419","article-title":"Sex- and Age-Specific Lyme Disease Testing Patterns in the United States, 2019 and 2022","volume":"140","author":"Y Li","year":"2025","journal-title":"Public Health Reports"},{"key":"pone.0349121.ref031","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.compbiomed.2018.12.007","article-title":"Automated detection of erythema migrans and other confounding skin lesions via deep learning","volume":"105","author":"PM Burlina","year":"2019","journal-title":"Comput Biol Med"},{"key":"pone.0349121.ref032","doi-asserted-by":"crossref","first-page":"103977","DOI":"10.1016\/j.compbiomed.2020.103977","article-title":"AI-based detection of erythema migrans and disambiguation against other skin lesions","volume":"125","author":"PM Burlina","year":"2020","journal-title":"Comput Biol Med"},{"key":"pone.0349121.ref033","doi-asserted-by":"crossref","first-page":"105682","DOI":"10.1016\/j.ijmedinf.2024.105682","article-title":"Expert opinion elicitation for assisting deep learning based Lyme disease classifier with patient data","volume":"193","author":"SI Hossain","year":"2025","journal-title":"Int J Med Inform"},{"key":"pone.0349121.ref034","author":"SI Hossain","year":"2021"},{"issue":"6","key":"pone.0349121.ref035","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1093\/cid\/ciad307","article-title":"Cholesterol Contributes to Risk, Severity, and Machine Learning-Driven Diagnosis of Lyme Disease","volume":"77","author":"IS Forrest","year":"2023","journal-title":"Clinical Infectious Diseases"},{"issue":"1","key":"pone.0349121.ref036","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1186\/s12911-023-02315-z","article-title":"Leveraging machine learning approaches for predicting potential Lyme disease cases and incidence rates in the United States using Twitter","volume":"23","author":"S Boligarla","year":"2023","journal-title":"BMC Med Inform Decis Mak"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0349121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T17:21:59Z","timestamp":1786555319000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0349121"}},"subtitle":[],"editor":[{"given":"Jorge","family":"Cervantes","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,12]]},"references-count":36,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,12]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0349121","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,12]]}}}