{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T22:08:30Z","timestamp":1788300510078,"version":"build-2803163510"},"reference-count":21,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T00:00:00Z","timestamp":1769644800000},"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. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Infections caused by multidrug-resistant organisms (MDROs) continue to pose serious challenges for hospital infection control, often resulting in longer hospitalizations, increased patient morbidity, and higher healthcare costs. While time series forecasting has gained traction as a tool for anticipating MDROs trends, there remains a lack of real-world studies comparing the effectiveness of different modeling approaches using hospital-based data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to evaluate and compare the predictive performance of four time series models\u2014SARIMA, ETS, Prophet, and NNETAR\u2014using monthly MDROs infection data collected from a tertiary hospital in China between 2014 and 2023, with the goal of forecasting trends for 2024.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Monthly MDROs infection rates from January 2014 to December 2023 were analyzed using R software. Stationarity was assessed through unit root tests, and appropriate differencing was applied as needed. Each model was fitted to the training dataset and used to forecast infection rates for the year 2024. Model accuracy was assessed by comparing forecasted values with actual 2024 data using root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), symmetric mean absolute percentage error (sMAPE), and mean absolute scaled error (MASE).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the models, SARIMA produced the most consistent and reliable forecasts (RMSE\u202f=\u202f0.0469, MAE\u202f=\u202f0.0424, MAPE\u202f=\u202f20.74%, sMAPE\u202f=\u202f21.27%, MASE\u202f=\u202f0.932), with residuals satisfying tests for independence and normality. Although the ETS model achieved lower numerical point errors (RMSE\u202f=\u202f0.0367, MAE\u202f=\u202f0.0305, MAPE\u202f=\u202f14.46%, sMAPE\u202f=\u202f14.81%, MASE\u202f=\u202f0.670), its residual diagnostics raised concerns regarding robustness. The Prophet (RMSE\u202f=\u202f0.0499, MAE\u202f=\u202f0.0439, MAPE\u202f=\u202f20.41%, sMAPE\u202f=\u202f22.15%, MASE\u202f=\u202f0.563) and NNETAR (RMSE\u202f=\u202f0.0697, MAPE\u202f=\u202f30.60%, sMAPE\u202f=\u202f30.60%, MASE\u202f=\u202f0.072) models captured certain aspects of the data dynamics but showed lower overall robustness compared with SARIMA.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Based on its overall robustness and diagnostic consistency, SARIMA is recommended for short- to medium-term forecasting of MDROs infection trends. The other models, while less reliable on their own, may still be valuable for validating trends and conducting sensitivity analyses to support hospital infection control planning.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1687658","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T06:42:36Z","timestamp":1769668956000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Forecasting multidrug-resistant organisms infection trends in a Chinese tertiary hospital (2014\u20132024): a comparative study of SARIMA, ETS, Prophet, and NNETAR models"],"prefix":"10.3389","volume":"14","author":[{"given":"Haiyan","family":"Chen","sequence":"first","affiliation":[{"name":"School of Basic Medical Sciences and School of Public Health, Faculty of Medicine, Yangzhou University","place":["Yangzhou, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luojing","family":"Zhou","sequence":"additional","affiliation":[{"name":"Northern Jiangsu People\u2019s Hospital","place":["Yangzhou, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,29]]},"reference":[{"key":"ref1","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1186\/s13756-020-00737-2","article-title":"One health in hospitals: how understanding the dynamics of people, animals, and the hospital built-environment can be used to better inform interventions for antimicrobial-resistant gram-positive infections","volume":"9","author":"Dalton","year":"2020","journal-title":"Antimicrob Resist Infect Control"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1111\/1475-6773.13135","article-title":"The incremental cost of infections associated with multidrug-resistant organism the inpatient hospital setting\u2014a national estimate","volume":"54","author":"Johnston","year":"2019","journal-title":"Health Serv Res"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1016\/j.cmi.2024.07.005","article-title":"Prediction models for diagnosis and prognosis of the colonization or infection of multidrug-resistant organisms in adults: a systematic review, critical appraisal, and meta-analysis","volume":"30","author":"Liu","year":"2024","journal-title":"Clin Microbiol Infect"},{"key":"ref5","first-page":"2024","volume-title":"Seasonal time series analysis: Why sarima outshines arima[J]","author":"Majka","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1303","DOI":"10.1016\/j.ijforecast.2022.06.004","article-title":"fETSmcs: feature-based ETS model component selection","volume":"39","author":"Qi","year":"2023","journal-title":"Int J Forecast"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1080\/03610918.2020.1854302","article-title":"Employing long short-term memory and Facebook prophet model in air temperature forecasting","volume":"52","author":"Toharudin","year":"2023","journal-title":"Commun Stat Simul Comput"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/978-3-031-21007-5_6","article-title":"Modelling and prediction of rainfall in the north-central region of Nigeria using ARIMA and NNETAR model","volume-title":"Climate change impacts on Nigeria: environment and sustainable development","author":"Chukwueloka","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"22","DOI":"10.24191\/jcrinn.v6i3.225","article-title":"The comparison between ARIMA and ARFIMA model to forecast kijang Emas (gold) prices in Malaysia using MAE, RMSE and MAPE","volume":"6","author":"Mahmad Azan","year":"2021","journal-title":"J Comp Res Innov"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"e28195","DOI":"10.2196\/28195","article-title":"Forecasting COVID-19 hospital census: a multivariate time-series model based on local infection incidence","volume":"7","author":"Nguyen","year":"2021","journal-title":"JMIR Public Health Surveill"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1186\/s12911-018-0616-8","article-title":"Time series model for forecasting the number of new admission inpatients","volume":"18","author":"Zhou","year":"2018","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1080\/0740817X.2014.999180","article-title":"Time series forecasting for nonlinear and non-stationary processes: a review and comparative study","volume":"47","author":"Cheng","year":"2015","journal-title":"IIE Trans"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1081\/ETC-120015385","article-title":"On the asymptotics of ADF tests for unit roots","volume":"21","author":"Chang","year":"2002","journal-title":"Econ Rev"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/UBMK50275.2020.9219448","article-title":"Drug sales prediction with ACF and PACF supported ARIMA method","author":"Demir","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"80","DOI":"10.47194\/ijgor.v3i3.168","article-title":"Time series model analysis using autocorrelation function (ACF) and partial autocorrelation function (PACF) for E-wallet transactions during a pandemic","volume":"3","author":"Yakubu","year":"2022","journal-title":"Int J Global Oper Res"},{"key":"ref16","volume-title":"Robustness of the Ljung-Box test and its rank equivalent[J]","author":"Burns","year":"2002"},{"key":"ref17","author":"Triebe","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"153","DOI":"10.2307\/1403464","article-title":"Maximum likelihood: an introduction","volume":"58","author":"Le Cam","year":"1990","journal-title":"Int Stat Rev"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1016\/B978-0-444-51862-0.50018-6","article-title":"AIC, BIC and recent advances in model selection","volume-title":"Philosophy of statistics","author":"Chakrabarti","year":"2011"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1186\/s12889-021-11200-1","article-title":"The impact of COVID-19 pandemic on the health-seeking behaviour of an Asian population with acute respiratory infections in a densely populated community","volume":"21","author":"Tan","year":"2021","journal-title":"BMC Public Health"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"87","DOI":"10.12746\/swrccc.v9i37.805","article-title":"Normality tests","volume":"9","author":"Yang","year":"2021","journal-title":"Southwest Respir Crit Care Chron"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1687658\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:16:04Z","timestamp":1771924564000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1687658\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,29]]},"references-count":21,"alternative-id":["10.3389\/fpubh.2026.1687658"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1687658","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,29]]},"article-number":"1687658"}}