{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T06:27:41Z","timestamp":1787120861413,"version":"build-2736575974"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T00:00:00Z","timestamp":1787097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Diagnosing infections remains challenging. Clinicians rely on scoring systems and experience, but artificial intelligence (AI) is used to support decision-making by integrating clinical data. However, most AI models focus on predicting adverse outcomes (e.g., ICU admission or sepsis) rather than differentiating between infection types.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop predictive models and evaluate their discriminatory performance for classifying infected patients into pneumonia, urinary tract infection (UTI), and other infections, and to assess the incremental value of adding clinical tests to routine variables.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Six Random Forest models were developed on datasets sharing a set of standard variables but differing in the added clinical variables. The models predicted infection type across three categories using a one-vs-rest framework. Data were divided into 70% for model training and 30% for model testing. The decision threshold was set with sensitivity fixed at 0.8, and specificity, negative predictive value, positive predictive value, and accuracy were reported. Variable importance was assessed, and the top five predictors per model were identified.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The model including standard variables and urine data achieved the highest AUC for UTI, whereas the total model achieved the highest AUC for pneumonia. Overall, urine and total models demonstrated the strongest performance. Key predictors included positive chest X-ray findings, abnormal auscultation, suspected pulmonary disease on imaging, neutrophil count, weight, urine culture, and a leukocyte-positive dipstick.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Machine learning models can potentially improve infection classification at ED admission when routine data are supplemented with relevant diagnostics. Optimal combinations of clinically relevant data markedly enhance diagnostic performance.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1894719","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T05:46:35Z","timestamp":1787118395000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AI-based clinical prediction model for early infectious disease classification in the emergency department"],"prefix":"10.3389","volume":"9","author":[{"given":"Sara N.","family":"S\u00f8gaard","sequence":"first","affiliation":[{"name":"Department of Regional Health Research, University of Southern Denmark","place":["Odense, Denmark"]},{"name":"Emergency Department, University Hospital of Southern Denmark","place":["Aabenraa, Denmark"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helene","family":"Skj\u00f8t-Arkil","sequence":"additional","affiliation":[{"name":"Department of Regional Health Research, University of Southern Denmark","place":["Odense, Denmark"]},{"name":"Emergency Department, University Hospital of Southern Denmark","place":["Aabenraa, Denmark"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian B.","family":"Mogensen","sequence":"additional","affiliation":[{"name":"Department of Regional Health Research, University of Southern Denmark","place":["Odense, Denmark"]},{"name":"Emergency Department, University Hospital of Southern Denmark","place":["Aabenraa, Denmark"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theis","family":"Aagaard","sequence":"additional","affiliation":[{"name":"Department of Regional Health Research, University of Southern Denmark","place":["Odense, Denmark"]},{"name":"Emergency Department, University Hospital of Southern Denmark","place":["Aabenraa, Denmark"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Kronborg","sequence":"additional","affiliation":[{"name":"Department of Health Science and Technology, Aalborg University","place":["Gistrup, Denmark"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,19]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"211","DOI":"10.3390\/jimaging10090211","article-title":"AI use in mammography for diagnosing metachronous contralateral breast Cancer","volume":"10","author":"Adachi","year":"2024","journal-title":"J Imaging"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"3401","DOI":"10.1002\/ejhf.3783","article-title":"Artificial intelligence fully automated analysis of handheld echocardiography in real-world patients with suspected heart failure","volume":"27","author":"Campbell","year":"2025","journal-title":"Eur. J. Heart Fail."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1111\/jgs.15679","article-title":"Nonspecific symptoms lack diagnostic accuracy for infection in older patients in the emergency department","volume":"67","author":"Caterino","year":"2019","journal-title":"J. Am. Geriatr. Soc."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"2233541","DOI":"10.1080\/07853890.2023.2233541","article-title":"Artificial intelligence for diagnosis of mild-moderate COVID-19 using haematological markers","volume":"55","author":"Chadaga","year":"2023","journal-title":"Ann. Med."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1452471","DOI":"10.3389\/frai.2025.1452471","article-title":"Evaluating the impact of common clinical confounders on performance of deep-learning-based sepsis risk assessment","volume":"8","author":"Chaganti","year":"2025","journal-title":"Front Artif Intell"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"q902","DOI":"10.1136\/bmj.q902","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/j.ajem.2025.07.056","article-title":"External validation of a widely available, localizable sepsis early detection model in the emergency department setting","volume":"97","author":"Currey","year":"2025","journal-title":"Am. J. Emerg. Med."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1097\/PTS.0000000000001409","article-title":"Incorporating machine learning driven factors in the design of electronic-triggers to detect diagnostic errors in the emergency department","volume":"22","author":"Enayati","year":"2025","journal-title":"J. Patient Saf."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1097\/CCM.0000000000000037","article-title":"Sepsis visits and antibiotic utilization in U.S. emergency departments","volume":"42","author":"Filbin","year":"2014","journal-title":"Crit. Care Med."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1186\/1471-2296-11-78","article-title":"Predicting acute uncomplicated urinary tract infection in women: a systematic review of the diagnostic accuracy of symptoms and signs","volume":"11","author":"Giesen","year":"2010","journal-title":"BMC Fam. Pract."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"e0174708","DOI":"10.1371\/journal.pone.0174708","article-title":"Creating an automated trigger for sepsis clinical decision support at emergency department triage using machine learning","volume":"12","author":"Horng","year":"2017","journal-title":"PLoS One"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1080","DOI":"10.1111\/j.1553-2712.2010.00872.x","article-title":"Identifying infected emergency department patients admitted to the hospital ward at risk of clinical deterioration and intensive care unit transfer","volume":"17","author":"Kennedy","year":"2010","journal-title":"Acad. Emerg. Med."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"e70321","DOI":"10.1002\/dad2.70321","article-title":"Incremental value of plasma biomarkers in predicting clinical decline among cognitively unimpaired older adults: results from the A4 trial","volume":"18","author":"Khorsand","year":"2025","journal-title":"Alzheimer\u2019s Dement"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1136\/bmjebm-2024-112920","article-title":"Diagnostic accuracy of dipsticks for urinary tract infections in acutely hospitalised patients: a prospective population-based observational cohort study","volume":"30","author":"Kristensen","year":"2025","journal-title":"BMJ Evid Based Med"},{"key":"ref15","first-page":"1","article-title":"Evidence-based guidelines for evaluation and antimicrobial therapy for common emergency department infections","volume":"14","author":"Nassisi","year":"2012","journal-title":"Emerg. Med. Pract."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1177\/01945998221083502","article-title":"Advances in artificial intelligence to diagnose otitis media: state of the art review","volume":"168","author":"Ngombu","year":"2023","journal-title":"Otolaryngol. Head Neck Surg."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"808","DOI":"10.3233\/SHTI240534","article-title":"An overview of explainable AI studies in the prediction of Sepsis onset and Sepsis mortality","volume":"316","author":"Nicolaou","year":"2024","journal-title":"Stud. Health Technol. Inform."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1186\/s13049-015-0184-1","article-title":"The formation and design of the TRIAGE study--baseline data on 6005 consecutive patients admitted to hospital from the emergency department","volume":"23","author":"Plesner","year":"2015","journal-title":"Scand. J. Trauma Resusc. Emerg. Med."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1016\/j.emc.2018.06.012","article-title":"Antimicrobial stewardship in the emergency department","volume":"36","author":"Pulia","year":"2018","journal-title":"Emerg. Med. Clin. North Am."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"361","DOI":"10.3238\/arztebl.2010.0361","article-title":"The diagnosis of urinary tract infection: a systematic review","volume":"107","author":"Schmiemann","year":"2010","journal-title":"Dtsch. Arztebl. Int."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"e090259","DOI":"10.1136\/bmjopen-2024-090259","article-title":"Clinical characteristics and diagnostic accuracy of preliminary diagnoses in adults with infections in Danish emergency departments: a multicentre combined cross-sectional and diagnostic study","volume":"14","author":"Skj\u00f8t-Arkil","year":"2024","journal-title":"BMJ Open"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e049606","DOI":"10.1136\/bmjopen-2021-049606","article-title":"Improved diagnostics of infectious diseases in emergency departments: a protocol of a multifaceted multicentre diagnostic study","volume":"11","author":"Skj\u00f8t-Arkil","year":"2021","journal-title":"BMJ Open"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1812692","DOI":"10.3389\/frai.2026.1812692","article-title":"Prediction of infection in the emergency department\u2014a machine learning model","volume":"9","author":"S\u00f8gaard","year":"2026","journal-title":"Front. Artif. Intell."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"79","DOI":"10.7150\/ijms.77205","article-title":"Artificial intelligence in clinical decision support systems for oncology","volume":"20","author":"Wang","year":"2023","journal-title":"Int. J. Med. Sci."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1038\/s43856-025-01061-9","article-title":"Evaluating acute image ordering for real-world patient cases via language model alignment with radiological guidelines","volume":"5","author":"Yao","year":"2025","journal-title":"Commun. Med. (Lond.)"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"104176","DOI":"10.1016\/j.ijmedinf.2020.104176","article-title":"The development an artificial intelligence algorithm for early sepsis diagnosis in the intensive care unit","volume":"141","author":"Yuan","year":"2020","journal-title":"Int. J. Med. Inform."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1894719\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T05:46:36Z","timestamp":1787118396000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1894719\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,19]]},"references-count":26,"alternative-id":["10.3389\/frai.2026.1894719"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1894719","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,19]]},"article-number":"1894719"}}