{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T21:36:37Z","timestamp":1789421797876,"version":"build-2803163510"},"update-to":[{"DOI":"10.1371\/journal.pntd.0010758","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2023,3,23]],"date-time":"2023-03-23T00:00:00Z","timestamp":1679529600000}}],"reference-count":44,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T00:00:00Z","timestamp":1678665600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100009826","name":"University of Colombo","doi-asserted-by":"publisher","award":["AP\/3\/2\/2017\/CG\/25"],"award-info":[{"award-number":["AP\/3\/2\/2017\/CG\/25"]}],"id":[{"id":"10.13039\/501100009826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008436","name":"National Foundation for Medical Research and Innovation","doi-asserted-by":"publisher","award":["1173666"],"award-info":[{"award-number":["1173666"]}],"id":[{"id":"10.13039\/100008436","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001732","name":"Danmarks Grundforskningsfond","doi-asserted-by":"publisher","award":["DNRF126"],"award-info":[{"award-number":["DNRF126"]}],"id":[{"id":"10.13039\/501100001732","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosntds.org"],"crossmark-restriction":false},"short-container-title":["PLoS Negl Trop Dis"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Background<\/jats:title>\n<jats:p>At least a third of dengue patients develop plasma leakage with increased risk of life-threatening complications. Predicting plasma leakage using laboratory parameters obtained in early infection as means of triaging patients for hospital admission is important for resource-limited settings.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>A Sri Lankan cohort including 4,768 instances of clinical data from N = 877 patients (60.3% patients with confirmed dengue infection) recorded in the first 96 hours of fever was considered. After excluding incomplete instances, the dataset was randomly split into a development and a test set with 374 (70%) and 172 (30%) patients, respectively. From the development set, five most informative features were selected using the minimum description length (MDL) algorithm. Random forest and light gradient boosting machine (LightGBM) were used to develop a classification model using the development set based on nested cross validation. An ensemble of the learners via average stacking was used as the final model to predict plasma leakage.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>Lymphocyte count, haemoglobin, haematocrit, age, and aspartate aminotransferase were the most informative features to predict plasma leakage. The final model achieved the area under the receiver operating characteristics curve, AUC = 0.80 with positive predictive value, PPV = 76.9%, negative predictive value, NPV = 72.5%, specificity = 87.9%, and sensitivity = 54.8% on the test set.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>The early predictors of plasma leakage identified in this study are similar to those identified in several prior studies that used non-machine learning based methods. However, our observations strengthen the evidence base for these predictors by showing their relevance even when individual data points, missing data and non-linear associations were considered. Testing the model on different populations using these low-cost observations would identify further strengths and limitations of the presented model.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pntd.0010758","type":"journal-article","created":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T17:39:18Z","timestamp":1678729158000},"page":"e0010758","update-policy":"https:\/\/doi.org\/10.1371\/journal.pntd.corrections_policy","source":"Crossref","is-referenced-by-count":22,"title":["Development of a machine learning model for early prediction of plasma leakage in suspected dengue patients"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9233-1656","authenticated-orcid":true,"given":"Ramtin","family":"Zargari Marandi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Preston","family":"Leung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chathurani","family":"Sigera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel Dawson","family":"Murray","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Praveen","family":"Weeratunga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deepika","family":"Fernando","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaturaka","family":"Rodrigo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Senaka","family":"Rajapakse","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cameron Ross","family":"MacPherson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2023,3,13]]},"reference":[{"key":"pntd.0010758.ref001","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":"pntd.0010758.ref002","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":"pntd.0010758.ref003","doi-asserted-by":"crossref","first-page":"E12363","DOI":"10.1073\/pnas.1813819115","article-title":"Virus-inclusive single-cell RNA sequencing reveals the molecular signature of progression to severe dengue","volume":"115","author":"F Zanini","year":"2018","journal-title":"Proc Natl Acad Sci U S A"},{"key":"pntd.0010758.ref004","first-page":"183","article-title":"Early Detection of Plasma Leakage in Dengue Hemorrhagic Fever.","volume":"50","author":"EJ Nelwan","year":"2018","journal-title":"Acta Med Indones."},{"key":"pntd.0010758.ref005","author":"World Health Organization","year":"2020","journal-title":"Dengue and severe dengue"},{"key":"pntd.0010758.ref006","doi-asserted-by":"crossref","first-page":"1082","DOI":"10.1186\/s12879-021-06793-2","article-title":"Plasma leakage in dengue: a systematic review of prospective observational studies.","volume":"21","author":"C Rodrigo","year":"2021","journal-title":"BMC Infect Dis"},{"key":"pntd.0010758.ref007","volume-title":"World Bank Data on Sri Lanka","author":"World Bank","year":"2022"},{"key":"pntd.0010758.ref008","volume-title":"Current health expenditure\u2014Sri Lanka","author":"World Bank","year":"2018"},{"key":"pntd.0010758.ref009","doi-asserted-by":"crossref","first-page":"e0004466","DOI":"10.1371\/journal.pntd.0004466","article-title":"Costs of Dengue Control Activities and Hospitalizations in the Public Health Sector during an Epidemic Year in Urban Sri Lanka.","volume":"10","author":"N Thalagala","year":"2016","journal-title":"PLoS Negl Trop Dis"},{"key":"pntd.0010758.ref010","doi-asserted-by":"crossref","first-page":"682","DOI":"10.3201\/eid2604.190435","article-title":"Severe Dengue Epidemic, Sri Lanka, 2017","volume":"26","author":"HA Tissera","year":"2020","journal-title":"Emerg Infect Dis"},{"key":"pntd.0010758.ref011","doi-asserted-by":"crossref","first-page":"e0258388","DOI":"10.1371\/journal.pone.0258388","article-title":"Direct costs of managing in-ward dengue patients in Sri Lanka: A prospective study.","volume":"16","author":"C Sigera","year":"2021","journal-title":"PLoS One"},{"key":"pntd.0010758.ref012","doi-asserted-by":"crossref","first-page":"e0008960","DOI":"10.1371\/journal.pntd.0008960","article-title":"Assessing the risk of dengue severity using demographic information and laboratory test results with machine learning.","volume":"14","author":"S-W Huang","year":"2020","journal-title":"PLoS Negl Trop Dis."},{"key":"pntd.0010758.ref013","doi-asserted-by":"crossref","first-page":"2861","DOI":"10.1109\/TBME.2019.2897285","article-title":"Severe Dengue Prognosis Using Human Genome Data and Machine Learning","volume":"66","author":"C Davi","year":"2019","journal-title":"IEEE Trans Biomed Eng"},{"key":"pntd.0010758.ref014","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/s13073-022-01034-w","article-title":"An 8-gene machine learning model improves clinical prediction of severe dengue progression","volume":"14","author":"YE Liu","year":"2022","journal-title":"Genome Med"},{"key":"pntd.0010758.ref015","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.coviro.2020.06.008","article-title":"Risk factors and biomarkers of severe dengue.","volume":"43","author":"AP Rathore","year":"2020","journal-title":"Curr Opin Virol."},{"key":"pntd.0010758.ref016","doi-asserted-by":"crossref","first-page":"2029","DOI":"10.1007\/s00705-020-04720-5","article-title":"Identification of dengue patients with high risk of severe disease, using early clinical and laboratory features, in a resource-limited setting","volume":"165","author":"MA Niriella","year":"2020","journal-title":"Arch Virol"},{"key":"pntd.0010758.ref017","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.trsl.2021.02.001","article-title":"Expression dynamics of vascular endothelial markers: endoglin and syndecan-1 in predicting dengue disease outcome.","volume":"232","author":"V Mariappan","year":"2021","journal-title":"Transl Res"},{"key":"pntd.0010758.ref018","doi-asserted-by":"crossref","DOI":"10.1186\/s12859-018-2264-5","article-title":"Random forest versus logistic regression: A large-scale benchmark experiment.","volume":"19","author":"R Couronn\u00e9","year":"2018","journal-title":"BMC Bioinformatics"},{"key":"pntd.0010758.ref019","article-title":"LightGBM: A highly efficient gradient boosting decision tree","author":"G Ke","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pntd.0010758.ref020","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12879-019-4304-9","article-title":"Risk prediction for severe disease and better diagnostic accuracy in early dengue infection; The Colombo dengue study.","volume":"19","author":"PC Sigera","year":"2019","journal-title":"BMC Infect Dis"},{"key":"pntd.0010758.ref021","first-page":"1","article-title":"Dengue and post-infection fatigue: findings from a prospective cohort\u2014the Colombo Dengue Study","author":"PC Sigera","year":"2020","journal-title":"Trans R Soc Trop Med Hyg"},{"key":"pntd.0010758.ref022","doi-asserted-by":"crossref","DOI":"10.3390\/app12136681","article-title":"Explanations of Machine Learning Models in Repeated Nested Cross-Validation: An Application in Age Prediction Using Brain Complexity Features.","volume":"12","author":"R Scheda","year":"2022","journal-title":"Appl Sci"},{"key":"pntd.0010758.ref023","first-page":"13480","article-title":"Debiasing MDI Feature Importance and SHAP Values in Tree Ensembles","author":"M. Loecher","year":"2022","journal-title":"Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics)."},{"key":"pntd.0010758.ref024","first-page":"228","article-title":"The minimum description length based decision tree pruning","author":"I. Kononenko","year":"1998","journal-title":"Pacific Rim International Conference on Artificial Intelligence"},{"key":"pntd.0010758.ref025","article-title":"Decision curve analysis: A novel method for evaluating prediction models.","author":"AJ Vickers","year":"2006","journal-title":"Med Decis Mak."},{"key":"pntd.0010758.ref026","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the Areas under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric Approach","volume":"44","author":"ER DeLong","year":"1988","journal-title":"Biometrics"},{"key":"pntd.0010758.ref027","doi-asserted-by":"crossref","first-page":"786","DOI":"10.21105\/joss.00786","article-title":"iml: An R package for interpretable machine learning.","volume":"3","author":"C Molnar","year":"2018","journal-title":"J Open Source Softw"},{"key":"pntd.0010758.ref028","first-page":"100","article-title":"Algorithm AS 136: A k-means clustering algorithm","volume":"28","author":"JA Hartigan","year":"1979","journal-title":"J R Stat Soc Ser c (applied Stat."},{"key":"pntd.0010758.ref029","unstructured":"Friedel CC, R\u00fcckert U, Kramer S. Cost curves for abstaining classifiers. Proceedings of the ICML 2006 workshop on ROC Analysis in Machine Learning Pittsburgh, PA. 2006."},{"key":"pntd.0010758.ref030","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.cegh.2018.10.006","article-title":"Prediction of plasma leakage phase of dengue in resource limited settings.","volume":"7","author":"HMMTB Herath","year":"2019","journal-title":"Clin Epidemiol Glob Heal"},{"key":"pntd.0010758.ref031","first-page":"1","article-title":"Atypical lymphocyte count correlates with the severity of dengue infection.","volume":"14","author":"CSH Clarice","year":"2019","journal-title":"PLoS One"},{"key":"pntd.0010758.ref032","doi-asserted-by":"crossref","first-page":"1396","DOI":"10.1093\/trstmh\/trab064","article-title":"Admission ultrasonography as a predictive tool for thrombocytopenia and disease severity in dengue infection","volume":"115","author":"CD Donaldson","year":"2021","journal-title":"Trans R Soc Trop Med Hyg"},{"key":"pntd.0010758.ref033","first-page":"2017","article-title":"Mathematical Modelling of Immune Parameters in the Evolution of Severe Dengue.","author":"MK Premaratne","year":"2017","journal-title":"Comput Math Methods Med"},{"key":"pntd.0010758.ref034","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pntd.0008056","article-title":"Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia.","volume":"14","author":"N Zhao","year":"2020","journal-title":"PLoS Negl Trop Dis."},{"key":"pntd.0010758.ref035","first-page":"1","article-title":"Facilitating fine-grained intra-urban dengue forecasting by integrating urban environments measured from street-view images.","volume":"10","author":"K Liu","year":"2021","journal-title":"Infect Dis Poverty"},{"key":"pntd.0010758.ref036","doi-asserted-by":"crossref","first-page":"e1009979","DOI":"10.1371\/journal.pcbi.1009979","article-title":"Short-term and long-term epidemiological impacts of sustained vector control in various dengue endemic settings: A modelling study.","volume":"18","author":"H Sun","year":"2022","journal-title":"PLOS Comput Biol."},{"key":"pntd.0010758.ref037","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12911-021-01493-y","article-title":"Identification of significant climatic risk factors and machine learning models in dengue outbreak prediction.","volume":"21","author":"F Yavari Nejad","year":"2021","journal-title":"BMC Med Inform Decis Mak"},{"key":"pntd.0010758.ref038","first-page":"1","article-title":"Trajectories of hepatic and coagulation dysfunctions related to a rapidly fatal outcome among hospitalized patients with dengue fever in Tainan, 2015.","volume":"13","author":"CY Yeh","year":"2019","journal-title":"PLoS Negl Trop Dis"},{"key":"pntd.0010758.ref039","first-page":"1","article-title":"Assessment of the Risk of Severe Dengue Using Intrahost Viral Population in Dengue Virus Serotype 2 Patients via Machine Learning.","volume":"12","author":"SJ Hung","year":"2022","journal-title":"Front Cell Infect Microbiol"},{"key":"pntd.0010758.ref040","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12864-022-08390-2","article-title":"Network meta-analysis of transcriptome expression changes in different manifestations of dengue virus infection","volume":"23","author":"C Winter","year":"2022","journal-title":"BMC Genomics"},{"key":"pntd.0010758.ref041","doi-asserted-by":"crossref","first-page":"100034","DOI":"10.1016\/j.dche.2022.100034","article-title":"Model stacking to improve prediction and variable importance robustness for soft sensor development","author":"M Barton","year":"2022","journal-title":"Digit Chem Eng"},{"key":"pntd.0010758.ref042","doi-asserted-by":"crossref","first-page":"e0226910","DOI":"10.1371\/journal.pone.0226910","article-title":"A novel model for malaria prediction based on ensemble algorithms.","volume":"14","author":"M Wang","year":"2019","journal-title":"PLoS One"},{"key":"pntd.0010758.ref043","doi-asserted-by":"crossref","first-page":"1128","DOI":"10.4269\/ajtmh.2007.77.1128","article-title":"Characterization of a dengue patient cohort in Recife, Brazil","volume":"77","author":"MT Cordeiro","year":"2007","journal-title":"Am J Trop Med Hyg"},{"key":"pntd.0010758.ref044","article-title":"Epidemiology Unit","author":"Distribution of Notification(H399) Dengue Cases by Month","journal-title":"Ministry of Health, Sri Lanka"}],"updated-by":[{"DOI":"10.1371\/journal.pntd.0010758","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2023,3,23]],"date-time":"2023-03-23T00:00:00Z","timestamp":1679529600000}}],"container-title":["PLOS Neglected Tropical Diseases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pntd.0010758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,23]],"date-time":"2023-03-23T18:30:30Z","timestamp":1679596230000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pntd.0010758"}},"subtitle":[],"editor":[{"given":"Mabel","family":"Carabali","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,3,13]]},"references-count":44,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,3,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pntd.0010758","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pntd.0010758","asserted-by":"object"}]},"ISSN":["1935-2735"],"issn-type":[{"value":"1935-2735","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,13]]}}}