{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T18:15:39Z","timestamp":1783620939922,"version":"3.55.0"},"reference-count":66,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"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>Traditional surveillance systems often struggle with the volatility of weekly case data, limiting timely prevention and control efforts. In the Philippines, the standard method for setting outbreak thresholds relies on historical moving averages that are highly affected by extreme values and slow to reflect recent epidemiological shifts. This study assessed the performance of hybrid discrete wavelet transform (DWT)-seasonal autoregressive moving average (SARMA) and DWT-SARMA-long short-term memory (LSTM) models in forecasting weekly case counts and explored their potential in defining dynamic alarm and epidemic thresholds in Quezon City, Philippines.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methodology<\/jats:title>\n                    <jats:p>An ecologic time-trend study was conducted using weekly dengue case counts from 2012 to 2022. The data was decomposed using DWT, and SARMA was applied to the resulting approximate and detail coefficients. The DWT-SARMA model was enhanced by applying an LSTM to the SARMA residuals. The DWT-SARMA-LSTM model demonstrated superior performance, achieving a Mean Absolute Percentage Error (MAPE) of 12.4%, and successfully captured the case peaks and troughs. In contrast, the DWT-SARMA model produced a MAPE of 25.8%. Model-derived thresholds were more adaptive and context-sensitive than the traditional 3-year moving mean threshold, which was skewed by pre-pandemic data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The hybrid DWT-SARMA-LSTM model is an accurate and robust approach for forecasting weekly dengue cases. It provides a more responsive basis for an early warning system than traditional thresholding methods, and has practical value for outbreak detection and resource planning in dynamic public health environments, particularly in resource-limited settings where timely and accurate data are critical.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pntd.0014444","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T17:29:01Z","timestamp":1783618141000},"page":"e0014444","update-policy":"https:\/\/doi.org\/10.1371\/journal.pntd.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Advancing outbreak detection: Hybridizing machine learning with wavelets for weekly dengue case forecasting"],"prefix":"10.1371","volume":"20","author":[{"given":"Angelica Anne","family":"Eligado","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takanori","family":"Hasegawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuta","family":"Hattori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9119-4730","authenticated-orcid":true,"given":"Keiko","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"key":"pntd.0014444.ref001","author":"World Health Organization [Internet]","year":"2022"},{"key":"pntd.0014444.ref002","author":"World Health Organization [Internet]","year":"2024"},{"key":"pntd.0014444.ref003","author":"World Health Organization [Internet]","year":"2012"},{"issue":"7","key":"pntd.0014444.ref004","doi-asserted-by":"crossref","first-page":"1324","DOI":"10.3201\/eid2407.151830","article-title":"Strengthening global public health surveillance through data and benefit sharing","volume":"24","author":"M Edelstein","year":"2018","journal-title":"Emerg Infect Dis"},{"key":"pntd.0014444.ref005","author":"World Health Organization [Internet]","year":"2006"},{"key":"pntd.0014444.ref006","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1186\/1471-2458-13-607","article-title":"Sharing experiences: towards an evidence based model of dengue surveillance and outbreak response in Latin America and Asia","volume":"13","author":"S Badurdeen","year":"2013","journal-title":"BMC Public Health"},{"issue":"9","key":"pntd.0014444.ref007","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pgph.0001691","article-title":"Early warning and response system for dengue outbreaks: moving from research to operational implementation in Mexico","volume":"3","author":"G Sanchez Tejeda","year":"2023","journal-title":"PLOS Glob Public Health"},{"key":"pntd.0014444.ref008","doi-asserted-by":"crossref","first-page":"756832","DOI":"10.1155\/2013\/756832","article-title":"Detecting and responding to a dengue outbreak: evaluation of existing strategies in country outbreak response planning","volume":"2013","author":"J Harrington","year":"2013","journal-title":"J Trop Med"},{"key":"pntd.0014444.ref009","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.epidem.2015.03.002","article-title":"Dengue disease outbreak definitions are implicitly variable","volume":"11","author":"OJ Brady","year":"2015","journal-title":"Epidemics"},{"key":"pntd.0014444.ref010","author":"World Health Organization [Internet]","year":"2009"},{"key":"pntd.0014444.ref011","first-page":"109","article-title":"Current and potential statistical methods for monitoring multiple data streams for bio-surveillance.","volume-title":"Statistical Methods in Counter-Terrorism: Game Theory, Modeling, Syndromic Surveillance, and Biometric Authentication","author":"G Shmueli","year":"2005"},{"issue":"6","key":"pntd.0014444.ref012","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1097\/00124784-200107060-00006","article-title":"The emerging science of very early detection of disease outbreaks","volume":"7","author":"MM Wagner","year":"2001","journal-title":"J Public Health Manag Pract"},{"key":"pntd.0014444.ref013","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1079\/9781845939649.0030","article-title":"Mapping the epidemiology of dengue.","volume-title":"Dengue and Dengue Hemorrhagic Fever","author":"OJ Brady","year":"2014"},{"issue":"3","key":"pntd.0014444.ref014","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.tim.2013.12.011","article-title":"Global spread of dengue virus types: mapping the 70 year history","volume":"22","author":"JP Messina","year":"2014","journal-title":"Trends Microbiol"},{"issue":"4","key":"pntd.0014444.ref015","first-page":"479","article-title":"Combination of long-short term memory network and wavelet transform for predicting dengue case density in the National Capital Region, Philippines","volume":"52","author":"IV Necesito","year":"2021","journal-title":"Southeast Asian J Trop Med Public Health"},{"issue":"15","key":"pntd.0014444.ref016","doi-asserted-by":"crossref","first-page":"1423","DOI":"10.1056\/NEJMra1110265","article-title":"Dengue","volume":"366","author":"CP Simmons","year":"2012","journal-title":"N Engl J Med"},{"issue":"31","key":"pntd.0014444.ref017","doi-asserted-by":"crossref","first-page":"11802","DOI":"10.1073\/pnas.0602960103","article-title":"Ecological and immunological determinants of dengue epidemics","volume":"103","author":"HJ Wearing","year":"2006","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"6","key":"pntd.0014444.ref018","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0157971","article-title":"Alarm variables for dengue outbreaks: a multi-centre study in Asia and Latin America","volume":"11","author":"LR Bowman","year":"2016","journal-title":"PLoS One"},{"issue":"6","key":"pntd.0014444.ref019","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.4269\/ajtmh.13-0321","article-title":"The complex relationship between weather and dengue virus transmission in Thailand","volume":"89","author":"KM Campbell","year":"2013","journal-title":"Am J Trop Med Hyg"},{"issue":"11","key":"pntd.0014444.ref020","article-title":"Forecast of dengue incidence using temperature and rainfall","volume":"6","author":"YL Hii","year":"2012","journal-title":"PLoS Negl Trop Dis"},{"issue":"1","key":"pntd.0014444.ref021","doi-asserted-by":"crossref","first-page":"32073","DOI":"10.1038\/s41598-024-83770-0","article-title":"Forecasting dengue in Bangladesh using meteorological variables with a novel feature selection approach","volume":"14","author":"M Al Mobin","year":"2024","journal-title":"Sci Rep"},{"issue":"5","key":"pntd.0014444.ref022","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0196811","article-title":"Early warning and response system (EWARS) for dengue outbreaks: Recent advancements towards widespread applications in critical settings","volume":"13","author":"L Hussain-Alkhateeb","year":"2018","journal-title":"PLoS One"},{"issue":"7","key":"pntd.0014444.ref023","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1002613","article-title":"Nonlinear and delayed impacts of climate on dengue risk in Barbados: a modelling study","volume":"15","author":"R Lowe","year":"2018","journal-title":"PLoS Med"},{"key":"pntd.0014444.ref024","doi-asserted-by":"crossref","first-page":"1323618","DOI":"10.3389\/fpubh.2024.1323618","article-title":"Enabling countries to manage outbreaks: statistical, operational, and contextual analysis of the early warning and response system (EWARS-csd) for dengue outbreaks","volume":"12","author":"M Schlesinger","year":"2024","journal-title":"Front Public Health"},{"key":"pntd.0014444.ref025","article-title":"Analysis\/synthesis of sound signals using a discrete wavelet transform (DWT)","volume-title":"Presented at: 13th International Congress on Acoustics","author":"C Dorize","year":"1989"},{"issue":"2","key":"pntd.0014444.ref026","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1883612.1883613","article-title":"Discrete wavelet transform-based time series analysis and mining","volume":"43","author":"P Chaovalit","year":"2011","journal-title":"ACM Comput Surv"},{"issue":"8","key":"pntd.0014444.ref027","doi-asserted-by":"crossref","DOI":"10.1002\/stc.2762","article-title":"Selecting optimum levels of wavelet multi\u2010resolution analysis for time\u2010varying signals in structural health monitoring","volume":"28","author":"A Silik","year":"2021","journal-title":"Struct Control Health Monit"},{"issue":"1","key":"pntd.0014444.ref028","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1186\/s41182-025-00723-7","article-title":"Assessing dengue forecasting methods: a comparative study of statistical models and machine learning techniques in Rio de Janeiro, Brazil","volume":"53","author":"X Chen","year":"2025","journal-title":"Trop Med Health"},{"key":"pntd.0014444.ref029","doi-asserted-by":"crossref","first-page":"104811","DOI":"10.1016\/j.bspc.2023.104811","article-title":"Wavelet transforms for feature engineering in EEG data processing: an application on Schizophrenia","volume":"85","author":"B Gosala","year":"2023","journal-title":"Biomed Signal Process Control"},{"key":"pntd.0014444.ref030","first-page":"3215681","article-title":"Wavelet scattering transform for ECG beat classification","volume":"2020","author":"Z Liu","year":"2020","journal-title":"Comput Math Methods Med"},{"key":"pntd.0014444.ref031","author":"B Dillard"},{"issue":"5","key":"pntd.0014444.ref032","doi-asserted-by":"crossref","DOI":"10.1002\/hsr2.1245","article-title":"Performance of discrete wavelet transform-based method in the detection of influenza outbreaks in Iran: An ecological study","volume":"6","author":"S Minaeian","year":"2023","journal-title":"Health Sci Rep"},{"issue":"3","key":"pntd.0014444.ref033","doi-asserted-by":"crossref","first-page":"114","DOI":"10.4103\/2221-6189.283889","article-title":"Aberration detection of pertussis from the Mazandaran province, Iran, from 2012 to 2018: application of discrete wavelet transform","volume":"9","author":"Y Alimohamadi","year":"2020","journal-title":"J Acute Dis"},{"issue":"3","key":"pntd.0014444.ref034","doi-asserted-by":"crossref","first-page":"345","DOI":"10.3390\/axioms2030345","article-title":"Wavelet-based monitoring for biosurveillance","volume":"2","author":"G Shmueli","year":"2013","journal-title":"Axioms"},{"issue":"13","key":"pntd.0014444.ref035","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e33848","article-title":"Comparative performance of hybrid model based on discrete wavelet transform and ARIMA models in prediction incidence of COVID-19","volume":"10","author":"K Holakouie-Naieni","year":"2024","journal-title":"Heliyon"},{"issue":"29","key":"pntd.0014444.ref036","doi-asserted-by":"crossref","first-page":"72391","DOI":"10.1007\/s11042-024-18528-x","article-title":"Time series analysis and prediction of COVID-19 patients using discrete wavelet transform and auto-regressive integrated moving average model","volume":"83","author":"SY Ilu","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"pntd.0014444.ref037","doi-asserted-by":"crossref","first-page":"109866","DOI":"10.1016\/j.chaos.2020.109866","article-title":"Development of new hybrid model of discrete wavelet decomposition and autoregressive integrated moving average (ARIMA) models in application to one month forecast the casualties cases of COVID-19","volume":"135","author":"S Singh","year":"2020","journal-title":"Chaos Solitons Fractals"},{"key":"pntd.0014444.ref038","article-title":"The performance of LSTM and BiLSTM in forecasting time series.","volume-title":"17th IEEE International Conference on Machine Learning and Applications (ICMLA)","author":"S Siami-Namini","year":"2018"},{"issue":"8","key":"pntd.0014444.ref039","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"S Hochreiter","year":"1997","journal-title":"Neural Comput"},{"issue":"4","key":"pntd.0014444.ref040","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0282621","article-title":"Using discrete wavelet transform for optimizing COVID-19 new cases and deaths prediction worldwide with deep neural networks","volume":"18","author":"EG Sperandio Nascimento","year":"2023","journal-title":"PLoS One"},{"issue":"1","key":"pntd.0014444.ref041","doi-asserted-by":"crossref","first-page":"1788","DOI":"10.1186\/s12889-023-16720-6","article-title":"LSTM-based recurrent neural network provides effective short term flu forecasting","volume":"23","author":"AB Amendolara","year":"2023","journal-title":"BMC Public Health"},{"issue":"8","key":"pntd.0014444.ref042","doi-asserted-by":"crossref","first-page":"1596","DOI":"10.3390\/ijerph15081596","article-title":"Predicting infectious disease using deep learning and big data","volume":"15","author":"S Chae","year":"2018","journal-title":"Int J Environ Res Public Health"},{"issue":"3","key":"pntd.0014444.ref043","first-page":"797","article-title":"Deep learning approach to forecasting dengue cases in Davao City using long short-term memory (LSTM)","volume":"151","author":"KB Ligue","year":"2021","journal-title":"Phil J Sci"},{"issue":"3","key":"pntd.0014444.ref044","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0299953","article-title":"Forecasting weekly dengue incidence in Sri Lanka: modified autoregressive integrated moving average modeling approach","volume":"19","author":"N Karasinghe","year":"2024","journal-title":"PLoS One"},{"issue":"20","key":"pntd.0014444.ref045","doi-asserted-by":"crossref","first-page":"13555","DOI":"10.3390\/ijerph192013555","article-title":"Forecasting weekly dengue cases by integrating google earth engine-based risk predictor generation and google colab-based deep learning modeling in Fortaleza and the Federal District, Brazil","volume":"19","author":"Z Li","year":"2022","journal-title":"Int J Environ Res Public Health"},{"issue":"9","key":"pntd.0014444.ref046","doi-asserted-by":"crossref","first-page":"1369","DOI":"10.1289\/ehp.1509981","article-title":"Three-month real-time dengue forecast models: an early warning system for outbreak alerts and policy decision support in Singapore","volume":"124","author":"Y Shi","year":"2016","journal-title":"Environ Health Perspect"},{"key":"pntd.0014444.ref047","doi-asserted-by":"crossref","first-page":"113170","DOI":"10.1016\/j.chaos.2023.113170","article-title":"A deep learning based hybrid architecture for weekly dengue incidences forecasting","volume":"168","author":"X Zhao","year":"2023","journal-title":"Chaos Solitons Fractals"},{"key":"pntd.0014444.ref048","author":"Philippine Statistics Authority [Internet]","year":"2020"},{"key":"pntd.0014444.ref049","author":"Philippine Statistics Authority [Internet]","year":"2021"},{"key":"pntd.0014444.ref050","first-page":"22","author":"Department of Health [Internet]"},{"key":"pntd.0014444.ref051","author":"Department of Health [Internet]","year":"2018"},{"key":"pntd.0014444.ref052","author":"Department of Health [Internet]","year":"2019"},{"key":"pntd.0014444.ref053","first-page":"22","article-title":"PyWavelets: A Python package for wavelet transform","volume":"9","author":"G Lee","year":"2019","journal-title":"SoftwareX"},{"key":"pntd.0014444.ref054","doi-asserted-by":"crossref","first-page":"57","DOI":"10.25080\/Majora-92bf1922-011","article-title":"Statsmodels: Econometric and statistical modeling with Python.","volume-title":"Proceedings of the 9th Python in Science Conference","author":"S Seabold","year":"2010"},{"key":"pntd.0014444.ref055","author":"F Chollet","year":"2015"},{"issue":"55","key":"pntd.0014444.ref056","first-page":"2178","article-title":"pmdarima: ARIMA estimators for Python","volume":"5","author":"A Smith","year":"2020","journal-title":"J Open Source Softw"},{"key":"pntd.0014444.ref057","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/j.procs.2015.04.167","article-title":"Time series forecasting using hybrid ARIMA and wavelet models","volume":"48","author":"I Khandelwal","year":"2015","journal-title":"Procedia Comput Sci"},{"key":"pntd.0014444.ref058","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1016\/j.renene.2021.12.100","article-title":"Short-term offshore wind power forecasting - A hybrid model based on Discrete Wavelet Transform (DWT), Seasonal Autoregressive Integrated Moving Average (SARIMA), and deep-learning-based Long Short-Term Memory (LSTM)","volume":"185","author":"W Zhang","year":"2022","journal-title":"Renew Energy"},{"key":"pntd.0014444.ref059","author":"DP Kingma","year":"2014"},{"key":"pntd.0014444.ref060","author":"Department of Health [Internet]","year":"2023"},{"key":"pntd.0014444.ref061","author":"Department of Health [Internet]"},{"key":"pntd.0014444.ref062","volume-title":"Forecasting: principles and practice","author":"R Hyndman","year":"2021"},{"issue":"6","key":"pntd.0014444.ref063","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1080\/09603120400012868","article-title":"Climatological variables and the incidence of dengue fever in Barbados","volume":"14","author":"C Depradine","year":"2004","journal-title":"Int J Environ Health Res"},{"issue":"5","key":"pntd.0014444.ref064","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1080\/09603120701849836","article-title":"Climate influence on dengue epidemics in Puerto Rico","volume":"18","author":"MR Jury","year":"2008","journal-title":"Int J Environ Health Res"},{"issue":"2","key":"pntd.0014444.ref065","doi-asserted-by":"crossref","first-page":"20","DOI":"10.37757\/MR2015.V17.N2.6","article-title":"Spatial models for prediction and early warning of Aedes aegypti proliferation from data on climate change and variability in Cuba","volume":"17","author":"PL Ortiz","year":"2015","journal-title":"MEDICC Rev"},{"key":"pntd.0014444.ref066","volume-title":"DOST builds on AI national strategy","year":"2025"}],"container-title":["PLOS Neglected Tropical Diseases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pntd.0014444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T17:29:10Z","timestamp":1783618150000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pntd.0014444"}},"subtitle":[],"editor":[{"given":"Sitara Swarna Rao","family":"Ajjampur","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,9]]},"references-count":66,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pntd.0014444","relation":{},"ISSN":["1935-2735"],"issn-type":[{"value":"1935-2735","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,9]]}}}