{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T21:36:38Z","timestamp":1789421798503,"version":"build-2803163510"},"reference-count":43,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T00:00:00Z","timestamp":1748908800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Early diagnosis of dengue fever is important for individual treatment and monitoring disease prevalence in the population. To assist diagnosis, previous studies have proposed classification models to detect dengue from symptoms and clinical measurements. However, there has been little exploration of whether existing models can be used to make predictions for new populations. In this study, we assess the generalizability of dengue classification models to new datasets.<\/jats:p>\n                  <jats:p>We trained logistic regression models on five publicly available dengue datasets from previous studies, using three explanatory variables identified as important in prior work: age, white blood cell count, and platelet count. These five datasets were collected at different times in different locations, with a variety of disease rates and patient ages. A model was trained on each dataset, and predictive performance and model calibration was evaluated on both the original (training) dataset, and the other (test) datasets from different studies. By comparing the model\u2019s performance when applied to data from a new location, we are able to assess the model\u2019s generalizability to new populations.<\/jats:p>\n                  <jats:p>We further compared performance with larger models and other classification methods. In-sample area under the receiver operating characteristic curve (AUC) values for the logistic regression models ranged from 0.74 to 0.89, while out-of-sample AUCs ranged from 0.55 to 0.89. Matching age ranges in training\/test datasets increased AUC values and balanced the sensitivity and specificity. Adjusting the predicted probabilities to account for differences in dengue prevalence improved calibration in 20\/28 training-test pairs. Results were similar when other explanatory variables were included and when other classification methods (decision trees and support vector machines) were used. The in-sample performance of the logistic regression model was consistent with previous dengue classifiers, suggesting the chosen model is a good choice in a variety of settings and has decent overall performance. However, adjustments are required to make predictions on new datasets. Practitioners can use existing dengue classifiers in new settings but should be careful with different patient ages and disease rates.<\/jats:p>","DOI":"10.1371\/journal.pone.0323886","type":"journal-article","created":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T13:25:17Z","timestamp":1748957117000},"page":"e0323886","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["Assessing generalizability of a dengue classifier across multiple datasets"],"prefix":"10.1371","volume":"20","author":[{"given":"Bingqian","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanni","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3256-011X","authenticated-orcid":true,"given":"Ciaran","family":"Evans","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,6,3]]},"reference":[{"key":"pone.0323886.ref001","volume-title":"Comprehensive guideline for prevention and control of dengue and dengue haemorrhagic fever","author":"World Health Organization Regional Office for South-East Asia","year":"2011"},{"issue":"5","key":"pone.0323886.ref002","article-title":"Rapid testing requires clinical evaluation for accurate diagnosis of dengue disease: a passive surveillance study in Southern Malaysia","volume":"15","author":"CF Ngim","year":"2021","journal-title":"PLoS Negl Trop Dis"},{"issue":"6","key":"pone.0323886.ref003","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1016\/S1473-3099(16)00026-8","article-title":"The global burden of dengue: an analysis from the Global Burden of Disease Study 2013","volume":"16","author":"JD Stanaway","year":"2016","journal-title":"Lancet Infect Dis"},{"key":"pone.0323886.ref004","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.ijid.2020.07.033","article-title":"Dengue fever as an emerging disease in Afghanistan: epidemiology of the first reported cases","volume":"99","author":"MN Sahak","year":"2020","journal-title":"Int J Infect Dis"},{"issue":"7446","key":"pone.0323886.ref005","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1038\/nature12060","article-title":"The global distribution and burden of dengue","volume":"496","author":"S Bhatt","year":"2013","journal-title":"Nature"},{"key":"pone.0323886.ref006","volume-title":"Dengue and severe dengue","author":"World Health Organization"},{"issue":"6","key":"pone.0323886.ref007","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1016\/S1473-3099(16)00076-1","article-title":"The elusive global burden of dengue","volume":"16","author":"A Wilder-Smith","year":"2016","journal-title":"Lancet Infect Dis"},{"issue":"10","key":"pone.0323886.ref008","doi-asserted-by":"crossref","first-page":"1625","DOI":"10.1016\/j.jiph.2023.08.001","article-title":"Dengue overview: an updated systemic review","volume":"16","author":"MB Khan","year":"2023","journal-title":"J Infect Public Health"},{"issue":"5","key":"pone.0323886.ref009","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1007\/s00281-017-0625-1","article-title":"Immune-mediated cytokine storm and its role in severe dengue","volume":"39","author":"A Srikiatkhachorn","year":"2017","journal-title":"Semin Immunopathol"},{"key":"pone.0323886.ref010","article-title":"Dengue fever","volume":"351","author":"SAM Kularatne","year":"2015","journal-title":"BMJ"},{"issue":"4","key":"pone.0323886.ref011","article-title":"Sensitivity and specificity of a novel classifier for the early diagnosis of dengue","volume":"9","author":"NM Tuan","year":"2015","journal-title":"PLoS Negl Trop Dis"},{"key":"pone.0323886.ref012","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1179\/2046904712Z.00000000052","article-title":"The revised WHO dengue case classification: Does the system need to be modified?","volume":"32","author":"SRS Hadinegoro","year":"2012","journal-title":"Paediatr Int Child Health"},{"issue":"1","key":"pone.0323886.ref013","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1179\/2047773215Y.0000000003","article-title":"WHO dengue case classification 2009 and its usefulness in practice: an expert consensus in the Americas","volume":"109","author":"O Horstick","year":"2015","journal-title":"Pathog Glob Health"},{"issue":"2","key":"pone.0323886.ref014","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.ijid.2003.03.003","article-title":"Dengue diagnosis, advances and challenges","volume":"8","author":"MG Guzm\u00e1n","year":"2004","journal-title":"Int J Infect Dis"},{"issue":"9966","key":"pone.0323886.ref015","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1016\/S0140-6736(14)60572-9","article-title":"Dengue","volume":"385","author":"MG Guzman","year":"2015","journal-title":"Lancet"},{"key":"pone.0323886.ref016","volume-title":"Dengue: Guidelines for diagnosis, treatment, prevention and control","author":"World Health Organization and Special Programme for Research and Training in Tropical Diseases and World Health Organization Department of Control of Neglected Tropical Diseases and World Health Organization Epidemic and Pandemic Alert","year":"2009"},{"key":"pone.0323886.ref017","volume-title":"Dengue virus antigen detection","author":"Centers for Disease Control and Prevention","year":"2019"},{"issue":"6","key":"pone.0323886.ref018","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1016\/j.cmi.2019.01.002","article-title":"Rapid diagnostic tests for determining dengue serostatus: A systematic review and key informant interviews","volume":"25","author":"R Luo","year":"2019","journal-title":"Clin Microbiol Infect"},{"issue":"6","key":"pone.0323886.ref019","article-title":"Rapid immunochromatographic tests for the diagnosis of dengue: A systematic review and meta-analysis. Cad Saude Publ","volume":"36","author":"VE Mata","year":"2020"},{"issue":"1","key":"pone.0323886.ref020","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.jcv.2009.11.001","article-title":"Early diagnosis of dengue in travelers: Comparison of a novel real-time RT-PCR, NS1 antigen detection and serology","volume":"47","author":"E Huhtamo","year":"2010","journal-title":"J Clin Virol"},{"issue":"9","key":"pone.0323886.ref021","article-title":"Value of routine dengue diagnostic tests in urine and saliva specimens","volume":"9","author":"A-C Andries","year":"2015","journal-title":"PLoS Negl Trop Dis"},{"issue":"10","key":"pone.0323886.ref022","article-title":"Dengue viral infection in Indonesia: Epidemiology, diagnostic challenges, and mutations from an observational cohort study","volume":"13","author":"IMS Utama","year":"2019","journal-title":"PLoS Negl Trop Dis"},{"issue":"5","key":"pone.0323886.ref023","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0010414","article-title":"A prospective observational study of community-acquired bacterial bloodstream infections in Metro Manila, the Philippines","volume":"16","author":"N Saito","year":"2022","journal-title":"PLoS Negl Trop Dis"},{"issue":"3","key":"pone.0323886.ref024","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0000196","article-title":"Decision tree algorithms predict the diagnosis and outcome of dengue fever in the early phase of illness","volume":"2","author":"L Tanner","year":"2008","journal-title":"PLoS Negl Trop Dis"},{"issue":"10","key":"pone.0323886.ref025","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0006799","article-title":"Use of structural equation models to predict dengue illness phenotype","volume":"12","author":"S Park","year":"2018","journal-title":"PLoS Negl Trop Dis"},{"issue":"1","key":"pone.0323886.ref026","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0010061","article-title":"Machine learning and deep learning techniques to support clinical diagnosis of arboviral diseases: a systematic review","volume":"16","author":"SR da Silva Neto","year":"2022","journal-title":"PLoS Negl Trop Dis"},{"issue":"1","key":"pone.0323886.ref027","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0007927","article-title":"An observational prospective cohort study of the epidemiology of hospitalized patients with acute febrile illness in Indonesia","volume":"14","author":"M Gasem","year":"2020","journal-title":"PLoS Negl Trop Dis"},{"issue":"4","key":"pone.0323886.ref028","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1111\/j.1467-9868.2010.00740.x","article-title":"Stability selection","volume":"72","author":"N Meinshausen","year":"2010","journal-title":"J R Stat Soc Ser B: Stat Methodol"},{"issue":"1","key":"pone.0323886.ref029","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1186\/s12879-016-1849-8","article-title":"Early diagnosis of dengue disease severity in a resource-limited Asian country","volume":"16","author":"P Cavailler","year":"2016","journal-title":"BMC Infect Dis"},{"issue":"11","key":"pone.0323886.ref030","article-title":"Comparing machine learning with case-control models to identify confirmed dengue cases","volume":"14","author":"T-S Ho","year":"2020","journal-title":"PLoS Negl Trop Dis"},{"issue":"8","key":"pone.0323886.ref031","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0000769","article-title":"Prediction of dengue disease severity among pediatric Thai patients using early clinical laboratory indicators","volume":"4","author":"JA Potts","year":"2010","journal-title":"PLoS Negl Trop Dis"},{"key":"pone.0323886.ref032","volume-title":"R: A language and environment for statistical computing","author":"R Core Team","year":"2022"},{"key":"pone.0323886.ref033","unstructured":"Kubat M, Matwin S. Addressing the curse of imbalanced training sets: one-sided selection. In: Proceedings of the fourteenth international conference on machine learning; 1997. p. 179\u201386."},{"issue":"3","key":"pone.0323886.ref034","first-page":"849","article-title":"Strategies for learning in class imbalance problems. Pattern Recogn","volume":"36","author":"R Barandela","year":"2003"},{"issue":"9","key":"pone.0323886.ref035","article-title":"Discriminative learning under covariate shift","volume":"10","author":"S Bickel","year":"2009","journal-title":"J Mach Learn Res"},{"key":"pone.0323886.ref036","doi-asserted-by":"crossref","first-page":"131","DOI":"10.7551\/mitpress\/7921.003.0013","article-title":"Covariate shift by kernel mean matching.","volume-title":"Dataset Shift in Machine Learning","author":"A Gretton","year":"2008"},{"issue":"1","key":"pone.0323886.ref037","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1162\/089976602753284446","article-title":"Adjusting the outputs of a classifier to new a priori probabilities: A simple procedure","volume":"14","author":"M Saerens","year":"2002","journal-title":"Neural Comput"},{"key":"pone.0323886.ref038","doi-asserted-by":"crossref","first-page":"3","DOI":"10.7551\/mitpress\/7921.003.0004","article-title":"When training and test sets are different: characterizing learning transfer.","volume-title":"Dataset shift in machine learning","author":"A. Storkey","year":"2008"},{"key":"pone.0323886.ref039","first-page":"3122","article-title":"Detecting and correcting for label shift with black box predictors.","volume-title":"Proceedings of the international conference on machine learning","author":"Z Lipton","year":"2018"},{"key":"pone.0323886.ref040","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The elements of statistical learning: Data mining, inference, and prediction","author":"T Hastie","year":"2009"},{"key":"pone.0323886.ref041","volume-title":"bestglm: Best subset GLM and regression utilities","author":"A McLeod","year":"2020"},{"key":"pone.0323886.ref042","volume-title":"Rpart: Recursive partitioning and regression trees","author":"T Therneau","year":"2022"},{"key":"pone.0323886.ref043","volume-title":"e1071: Misc functions of the department of statistics, probability theory group (formerly: e1071)","author":"D Meyer","year":"2023"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0323886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T13:25:50Z","timestamp":1748957150000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0323886"}},"subtitle":[],"editor":[{"given":"Harapan","family":"Harapan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,6,3]]},"references-count":43,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6,3]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0323886","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.07.17.549435","asserted-by":"object"}]},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,3]]}}}