{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T15:07:22Z","timestamp":1793113642333,"version":"4.5.0"},"reference-count":36,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T00:00:00Z","timestamp":1642118400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"crossref","award":["2017ZX10305501-009"],"award-info":[{"award-number":["2017ZX10305501-009"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Special Foundation of Basic Science and Technology Resources Survey from Ministry of Science and Technology of China","award":["2017FY101201"],"award-info":[{"award-number":["2017FY101201"]}]},{"name":"Special Foundation of Basic Science and Technology Resources Survey from Ministry of Science and Technology of China","award":["2017FY101207"],"award-info":[{"award-number":["2017FY101207"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>This study intends to build and compare two kinds of forecasting models at different time scales for hemorrhagic fever incidence in China.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory Neural Network (LSTM) were adopted to fit monthly, weekly and daily incidence of hemorrhagic fever in China from 2013 to 2018. The two models, combined and uncombined with rolling forecasts, were used to predict the incidence in 2019 to examine their stability and applicability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      ARIMA (2, 1, 1) (0, 1, 1)\n                      <jats:sub>12<\/jats:sub>\n                      , ARIMA (1, 1, 3) (1, 1, 1)\n                      <jats:sub>52<\/jats:sub>\n                      and ARIMA (5, 0, 1) were selected as the best fitting ARIMA model for monthly, weekly and daily incidence series, respectively. The LSTM model with 64 neurons and Stochastic Gradient Descent (SGDM) for monthly incidence, 8 neurons and Adaptive Moment Estimation (Adam) for weekly incidence, and 64 neurons and Root Mean Square Prop (RMSprop) for daily incidence were selected as the best fitting LSTM models. The values of root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) of the models combined with rolling forecasts in 2019 were lower than those of the direct forecasting models for both ARIMA and LSTM. It was shown from the forecasting performance in 2019 that ARIMA was better than LSTM for monthly and weekly forecasting while the LSTM was better than ARIMA for daily forecasting in rolling forecasting models.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Both ARIMA and LSTM could be used to build a prediction model for the incidence of hemorrhagic fever. Different models might be more suitable for the incidence prediction at different time scales. The findings can provide a good reference for future selection of prediction models and establishments of early warning systems for hemorrhagic fever.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0262009","type":"journal-article","created":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T14:30:44Z","timestamp":1642170644000},"page":"e0262009","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":42,"title":["Comparison of ARIMA and LSTM for prediction of hemorrhagic fever at different time scales in China"],"prefix":"10.1371","volume":"17","author":[{"given":"Rui","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hejia","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiulan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6541-8692","authenticated-orcid":true,"given":"Songwang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,1,14]]},"reference":[{"issue":"4","key":"pone.0262009.ref001","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1016\/j.ccc.2005.06.007","article-title":"Hemorrhagic fever viruses","volume":"21","author":"DC Pigott","year":"2005","journal-title":"Crit Care Clin"},{"issue":"4","key":"pone.0262009.ref002","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/s12250-013-3327-4","article-title":"Crimean-Congo hemorrhagic fever: an overview","volume":"28","author":"S. Onc\u00fc","year":"2013","journal-title":"Virol Sin"},{"key":"pone.0262009.ref003","unstructured":"Statistical bulletin of China\u2019s health development. Available from: http:\/\/www.nhc.gov.cn\/guihuaxxs\/s10743\/201806\/44e3cdfe11fa4c7f928c879d435b6a18.shtml."},{"issue":"4","key":"pone.0262009.ref004","doi-asserted-by":"crossref","first-page":"279","DOI":"10.7883\/yoken.JJID.2014.567","article-title":"Using an Autoregressive Integrated Moving Average Model to Predict the Incidence of Hemorrhagic Fever with Renal Syndrome in Zibo, China, 2004\u20132014","volume":"69","author":"T Wang","year":"2016","journal-title":"Jpn J Infect Dis"},{"issue":"12","key":"pone.0262009.ref005","doi-asserted-by":"crossref","first-page":"e0008939","DOI":"10.1371\/journal.pntd.0008939","article-title":"Prediction of hot spot areas of hemorrhagic fever with renal syndrome in Hunan Province based on an information quantity model and logistical regression model","volume":"14","author":"Z Chen","year":"2020","journal-title":"PLoS Negl Trop Dis"},{"issue":"1","key":"pone.0262009.ref006","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1186\/s12874-020-01130-8","article-title":"SARFIMA model prediction for infectious diseases: application to hemorrhagic fever with renal syndrome and comparing with SARIMA","volume":"20","author":"C Qi","year":"2020","journal-title":"BMC Med Res Methodol"},{"issue":"11","key":"pone.0262009.ref007","doi-asserted-by":"crossref","first-page":"e0207518","DOI":"10.1371\/journal.pone.0207518","article-title":"A new Seasonal Difference Space-Time Autoregressive Integrated Moving Average (SD-STARIMA) model and spatiotemporal trend prediction analysis for Hemorrhagic Fever with Renal Syndrome (HFRS).","volume":"13","author":"Y Zhao","year":"2018","journal-title":"PLoS One"},{"issue":"1","key":"pone.0262009.ref008","doi-asserted-by":"crossref","first-page":"828","DOI":"10.1186\/s12879-019-4457-6","article-title":"Forecasting incidence of hand, foot and mouth disease using BP neural networks in Jiangsu province, China","volume":"19","author":"W Liu","year":"2019","journal-title":"BMC Infect Dis"},{"issue":"6","key":"pone.0262009.ref009","doi-asserted-by":"crossref","first-page":"e0198313","DOI":"10.1371\/journal.pone.0198313","article-title":"Assessment of autoregressive integrated moving average (ARIMA), generalized linear autoregressive moving average (GLARMA), and random forest (RF) time series regression models for predicting influenza A virus frequency in swine in Ontario, Canada","volume":"13","author":"T Petukhova","year":"2018","journal-title":"PLoS One"},{"issue":"1","key":"pone.0262009.ref010","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1186\/1471-2105-15-276","article-title":"Comparison of ARIMA and Random Forest time series models for prediction of avian influenza H5N1 outbreaks","volume":"15","author":"MJ Kane","year":"2014","journal-title":"BMC Bioinformatics"},{"issue":"6","key":"pone.0262009.ref011","doi-asserted-by":"crossref","first-page":"e025773","DOI":"10.1136\/bmjopen-2018-025773","article-title":"Comparison of autoregressive integrated moving average model and generalised regression neural network model for prediction of haemorrhagic fever with renal syndrome in China: a time-series study","volume":"9","author":"YW Wang","year":"2019","journal-title":"BMJ Open"},{"key":"pone.0262009.ref012","doi-asserted-by":"crossref","first-page":"105340","DOI":"10.1016\/j.dib.2020.105340","article-title":"Application of the ARIMA model on the COVID-2019 epidemic dataset","volume":"29","author":"D Benvenuto","year":"2020","journal-title":"Data Brief."},{"key":"pone.0262009.ref013","doi-asserted-by":"crossref","first-page":"1429462","DOI":"10.1155\/2019\/1429462","article-title":"Epidemic Situation of Brucellosis in Jinzhou City of China and Prediction Using the ARIMA Model","volume":"2019","author":"L Wang","year":"2019","journal-title":"Can J Infect Dis Med Microbiol"},{"issue":"6","key":"pone.0262009.ref014","doi-asserted-by":"crossref","first-page":"e0156768","DOI":"10.1371\/journal.pone.0156768","article-title":"Application of a Combined Model with Autoregressive Integrated Moving Average (ARIMA) and Generalized Regression Neural Network (GRNN) in Forecasting Hepatitis Incidence in Heng County, China","volume":"11","author":"W Wei","year":"2016","journal-title":"PLoS One"},{"issue":"9","key":"pone.0262009.ref015","doi-asserted-by":"crossref","first-page":"e0201987","DOI":"10.1371\/journal.pone.0201987","article-title":"Comparison of ARIMA and GM(1,1) models for prediction of hepatitis B in China","volume":"13","author":"YW Wang","year":"2018","journal-title":"PLoS One"},{"issue":"2","key":"pone.0262009.ref016","doi-asserted-by":"crossref","first-page":"e0149401","DOI":"10.1371\/journal.pone.0149401","article-title":"Time Series Modelling of Syphilis Incidence in China from 2005 to 2012","volume":"11","author":"X Zhang","year":"2016","journal-title":"PLoS One"},{"issue":"3","key":"pone.0262009.ref017","doi-asserted-by":"crossref","first-page":"e9450","DOI":"10.1371\/journal.pone.0009450","article-title":"Modeling and predicting seasonal influenza transmission in warm regions using climatological parameters","volume":"5","author":"RP Soebiyanto","year":"2010","journal-title":"PLoS One."},{"issue":"3","key":"pone.0262009.ref018","doi-asserted-by":"crossref","first-page":"e0116832","DOI":"10.1371\/journal.pone.0116832","article-title":"Forecast model analysis for the morbidity of tuberculosis in Xinjiang, China","volume":"10","author":"YL Zheng","year":"2015","journal-title":"PLoS One."},{"key":"pone.0262009.ref019","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1186\/1472-6947-13-56","article-title":"A hybrid seasonal prediction model for tuberculosis incidence in China","volume":"13","author":"S Cao","year":"2013","journal-title":"BMC Med Inform Decis Mak"},{"key":"pone.0262009.ref020","doi-asserted-by":"crossref","first-page":"e194","DOI":"10.1017\/S095026881900075X","article-title":"Application of a long short-term memory neural network: a burgeoning method of deep learning in forecasting HIV incidence in Guangxi, China.","volume":"147","author":"G Wang","year":"2019","journal-title":"Epidemiol Infect"},{"issue":"3","key":"pone.0262009.ref021","doi-asserted-by":"crossref","first-page":"1251","DOI":"10.1109\/JBHI.2018.2840690","article-title":"An ARIMA Model With Adaptive Orders for Predicting Blood Glucose Concentrations and Hypoglycemia","volume":"23","author":"J Yang","year":"2019","journal-title":"IEEE J Biomed Health Inform"},{"issue":"1","key":"pone.0262009.ref022","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1186\/s12913-017-2407-9","article-title":"Hospital daily outpatient visits forecasting using a combinatorial model based on ARIMA and SES models","volume":"17","author":"L Luo","year":"2017","journal-title":"BMC Health Serv Res"},{"issue":"8","key":"pone.0262009.ref023","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 Computation"},{"issue":"13","key":"pone.0262009.ref024","article-title":"An AutoEncoder and LSTM-Based Traffic Flow Prediction Method","volume":"19","author":"W Wei","year":"2019","journal-title":"Sensors (Basel)."},{"issue":"2","key":"pone.0262009.ref025","article-title":"Improving Post-Filtering of Artificial Speech Using Pre-Trained LSTM Neural Networks","volume":"4","author":"M. Coto-Jim\u00e9nez","year":"2019","journal-title":"Biomimetics (Basel)."},{"issue":"5","key":"pone.0262009.ref026","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/s10916-019-1243-3","article-title":"LSTM Model for Prediction of Heart Failure in Big Data","volume":"43","author":"G Maragatham","year":"2019","journal-title":"J Med Syst"},{"issue":"1","key":"pone.0262009.ref027","doi-asserted-by":"crossref","first-page":"17928","DOI":"10.1038\/s41598-019-54495-2","article-title":"A method for hand-foot-mouth disease prediction using GeoDetector and LSTM model in Guangxi, China","volume":"9","author":"J Gu","year":"2019","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0262009.ref028","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1186\/s12889-016-3455-5","article-title":"Forecast analysis of any opportunistic infection among HIV positive individuals on antiretroviral therapy in Uganda","volume":"16","author":"J Rubaihayo","year":"2016","journal-title":"BMC Public Health"},{"issue":"6","key":"pone.0262009.ref029","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1109\/TCYB.2013.2272642","article-title":"Joint embedding learning and sparse regression: a framework for unsupervised feature selection","volume":"44","author":"C Hou","year":"2014","journal-title":"IEEE Trans Cybern"},{"issue":"8","key":"pone.0262009.ref030","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":"13","key":"pone.0262009.ref031","doi-asserted-by":"crossref","first-page":"1680","DOI":"10.1017\/S0950268818002030","article-title":"Spatiotemporal analysis and forecasting model of hemorrhagic fever with renal syndrome in mainland China","volume":"146","author":"L Sun","year":"2018","journal-title":"Epidemiol Infect"},{"issue":"8","key":"pone.0262009.ref032","doi-asserted-by":"crossref","first-page":"697","DOI":"10.1007\/s11427-013-4518-9","article-title":"An emerging hemorrhagic fever in China caused by a novel bunyavirus SFTSV","volume":"56","author":"X Zhang","year":"2013","journal-title":"Sci China Life Sci"},{"issue":"2","key":"pone.0262009.ref033","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/S0966-842X(01)02288-0","article-title":"Epidemic dengue\/dengue hemorrhagic fever as a public health, social and economic problem in the 21st century","volume":"10","author":"DJ Gubler","year":"2002","journal-title":"Trends in microbiology"},{"key":"pone.0262009.ref034","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1016\/j.ijid.2015.02.010","article-title":"Transmission of haemorrhagic fever with renal syndrome in China and the role of climate factors: a review","volume":"33","author":"A Hansen","year":"2015","journal-title":"Int J Infect Dis"},{"key":"pone.0262009.ref035","volume-title":"Time Series Analysis With Applications in R","author":"JD Cryer","year":"2010"},{"issue":"1","key":"pone.0262009.ref036","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1111\/j.1467-9892.1980.tb00297.x","article-title":"An introduction to long-memory time series models and fractional differencing","volume":"1","author":"C Granger","year":"2010","journal-title":"Journal of Time Series Analysis"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0262009","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T14:31:28Z","timestamp":1642170688000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0262009"}},"subtitle":[],"editor":[{"given":"Esteban","family":"Tlelo-Cuautle","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,1,14]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,1,14]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0262009","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-151318\/v1","asserted-by":"object"}]},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,14]]}}}