{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T10:02:14Z","timestamp":1789984934645,"version":"4.0.1"},"reference-count":59,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":21,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Health Science Reports"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate forecasting of COVID\u201019 cases is essential for effective public health planning and resource allocation. Traditional statistical and deep\u2010learning models often fail to jointly capture linear dynamics, nonlinear patterns, and exogenous drivers of disease transmission. This study proposes a hybrid ARIMA\u2010LSTM forecasting framework incorporating four exogenous variables\u2014daily average temperature, rainfall, vaccination rate, and population density\u2014at both the linear (ARIMAX) and nonlinear (LSTM residual) stages.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Daily confirmed COVID\u201019 cases in Malaysia from January 4 to September 18, 2021 were analyzed. A dual\u2010integration modeling strategy was implemented: an ARIMAX component modeled linear trends and exogenous effects (temperature, rainfall, vaccination rate, and population density), while a Long Short\u2010Term Memory (LSTM) network captured nonlinear residual structures. Four competing models were evaluated: standalone ARIMA, standalone LSTM, hybrid ARIMA\u2010LSTM without exogenous variables, and the proposed hybrid ARIMAX\u2010LSTM with exogenous variables. Performance was assessed using RMSE, MAE, MAPE, and\n                      <jats:italic>R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      , with statistical comparison via the Diebold\u2013Mariano (DM) test.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The proposed hybrid ARIMAX\u2010LSTM model achieved superior predictive accuracy (RMSE\u2009=\u2009948.62; MAE\u2009=\u2009769.49; MAPE\u2009=\u20096.61%;\n                      <jats:italic>R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      \u2009=\u20090.7883), representing approximately 49% lower prediction error than baseline models (RMSE\u2009=\u20091801.90\u20131857.94). The model explained 78.83% of variance compared with &lt;\u20095% for models excluding exogenous variables. Improvements were statistically significant (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001). The hybrid model demonstrated robust performance during epidemic transitions, achieving 3.02% error during a sharp decline phase compared with 20%\u201323% for baseline approaches.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Integrating exogenous variables within both linear and nonlinear components substantially enhances COVID\u201019 forecasting accuracy. The proposed hybrid ARIMAX\u2010LSTM framework provides a reliable tool for epidemic prediction and supports evidence\u2010based public health decision\u2010making. This approach is readily may be extensible to other infectious diseases and time\u2010series forecasting applications.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/hsr2.72684","type":"journal-article","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T10:54:44Z","timestamp":1782125684000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing COVID\u201019 Forecasting Accuracy in Malaysia Using a Hybrid ARIMA\u2010LSTM Model With Exogenous Variables: A Time\u2010Series Predictive Study"],"prefix":"10.1002","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8194-6874","authenticated-orcid":false,"given":"Al","family":"Mahmud","sequence":"first","affiliation":[{"name":"Department of Statistics Shahjalal University of Science &amp; Technology Sylhet Bangladesh"},{"name":"School of Dental Sciences, Health Campus, Universiti Sains Malaysia, Health Campus Kubang Kerian Kelantan Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kamarul Imran","family":"Musa","sequence":"additional","affiliation":[{"name":"Department of Community Medicine School of Medical Sciences, Health Campus, Universiti Sains Malaysia, Health Campus Kubang Kerian Kelantan Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Firdaus Mohamad","family":"Hamzah","sequence":"additional","affiliation":[{"name":"Department of Mathematics Centre for Defense Foundation Studies, Universiti Pertahanan Nasional Malaysia Kuala Lumpur Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4283-3548","authenticated-orcid":false,"given":"Zainab Mat Yudin","family":"Badrin","sequence":"additional","affiliation":[{"name":"School of Dental Sciences, Health Campus, Universiti Sains Malaysia, Health Campus Kubang Kerian Kelantan Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamad Arif Awang","family":"Nawi","sequence":"additional","affiliation":[{"name":"Biostatistics Unit School of Dental Sciences, Health Campus, Universiti Sains Malaysia, Health Campus Kubang Kerian Kelantan Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"e_1_2_17_2_1","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2023.1125246"},{"key":"e_1_2_17_3_1","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/5578284"},{"key":"e_1_2_17_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(21)02796-3"},{"key":"e_1_2_17_5_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12879-024-09298-w"},{"key":"e_1_2_17_6_1","doi-asserted-by":"publisher","DOI":"10.51594\/imsrj.v4i4.999"},{"key":"e_1_2_17_7_1","first-page":"18","volume-title":"Machine Learning Applications for COVID\u201019 Outbreak Management","author":"Heidari A.","year":"2022"},{"key":"e_1_2_17_8_1","first-page":"2","volume-title":"COVID 19 Pandemic, Socio\u2010Economic Behaviour and Infection Characteristics: An Inter\u2010Country Predictive Study Using Deep Learning","author":"Basu S.","year":"2023"},{"key":"e_1_2_17_9_1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.3195"},{"key":"e_1_2_17_10_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph182111109"},{"key":"e_1_2_17_11_1","article-title":"Improving COVID\u201019 Forecasting Using eXogenous Variables","volume":"2107","author":"Toutiaee M.","year":"2021","journal-title":"arXiv"},{"key":"e_1_2_17_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2018.09.157"},{"key":"e_1_2_17_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.110121"},{"key":"e_1_2_17_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00477-020-01827-8"},{"key":"e_1_2_17_15_1","doi-asserted-by":"publisher","DOI":"10.3390\/a13100249"},{"key":"e_1_2_17_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph182111073"},{"key":"e_1_2_17_17_1","doi-asserted-by":"publisher","DOI":"10.2478\/dim-2020-0012"},{"key":"e_1_2_17_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378073"},{"key":"e_1_2_17_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05434-0"},{"key":"e_1_2_17_20_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-022-01755-x"},{"key":"e_1_2_17_21_1","doi-asserted-by":"publisher","DOI":"10.1093\/ije\/dyab021"},{"key":"e_1_2_17_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2020.105340"},{"key":"e_1_2_17_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10198-021-01347-4"},{"key":"e_1_2_17_24_1","doi-asserted-by":"crossref","unstructured":"R.Ghostine M.Gharamti S.Hassrouny andI.Hoteit \u201cAn Extended SEIR Model With Vaccination for Forecasting the COVID\u201019 Pandemic in Saudi Arabia Using an Ensemble Kalman Filter \u201d2021.","DOI":"10.3390\/math9060636"},{"key":"e_1_2_17_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.109864"},{"key":"e_1_2_17_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3058537"},{"key":"e_1_2_17_27_1","doi-asserted-by":"publisher","DOI":"10.3390\/math8060890"},{"key":"e_1_2_17_28_1","article-title":"Examining COVID\u201019 Forecasting Using Spatio\u2010Temporal Graph Neural Networks","volume":"2007","author":"Kapoor A.","year":"2020","journal-title":"arXiv"},{"key":"e_1_2_17_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.110058"},{"key":"e_1_2_17_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_2_17_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.110212"},{"key":"e_1_2_17_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107161"},{"key":"e_1_2_17_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.110336"},{"key":"e_1_2_17_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.110137"},{"key":"e_1_2_17_35_1","doi-asserted-by":"publisher","DOI":"10.1101\/2020.03.23.20041608"},{"key":"e_1_2_17_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-04867-x"},{"key":"e_1_2_17_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2022.01.011"},{"key":"e_1_2_17_38_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"e_1_2_17_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIVC52351.2021.9526957"},{"key":"e_1_2_17_40_1","doi-asserted-by":"publisher","DOI":"10.1198\/073500102753410444"},{"key":"e_1_2_17_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-2070(96)00719-4"},{"key":"e_1_2_17_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jiph.2020.06.001"},{"key":"e_1_2_17_43_1","volume-title":"Time Series Analysis: Forecasting and Control","author":"Box G. E. P.","year":"2015"},{"key":"e_1_2_17_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.109853"},{"key":"e_1_2_17_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.109864"},{"key":"e_1_2_17_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.110227"},{"key":"e_1_2_17_47_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_17_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.idm.2020.02.002"},{"key":"e_1_2_17_49_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.abb3221"},{"key":"e_1_2_17_50_1","doi-asserted-by":"publisher","DOI":"10.21315\/mjms2021.28.2.1"},{"key":"e_1_2_17_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(21)02183-8"},{"key":"e_1_2_17_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2020.138810"},{"key":"e_1_2_17_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2020.138201"},{"key":"e_1_2_17_54_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-020-1104-0"},{"key":"e_1_2_17_55_1","doi-asserted-by":"crossref","unstructured":"S.Siami\u2010Namini N.Tavakoli andA. S.Siami Namin \u201cA Comparison of ARIMA and LSTM in Forecasting Time Series \u201d Proceedings \u2010 17th IEEE International Conference on Machine Learning and Applications ICMLA 2018 (IEEE 2018): 1394\u20131401 https:\/\/doi.org\/10.1109\/ICMLA.2018.00227.","DOI":"10.1109\/ICMLA.2018.00227"},{"key":"e_1_2_17_56_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/65.2.297"},{"key":"e_1_2_17_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"e_1_2_17_58_1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.3195"},{"key":"e_1_2_17_59_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_17_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45014-9_1"}],"container-title":["Health Science Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/hsr2.72684","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/hsr2.72684","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/hsr2.72684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T09:17:06Z","timestamp":1789982226000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/hsr2.72684"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":59,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1002\/hsr2.72684"],"URL":"https:\/\/doi.org\/10.1002\/hsr2.72684","archive":["Portico"],"relation":{},"ISSN":["2398-8835","2398-8835"],"issn-type":[{"value":"2398-8835","type":"print"},{"value":"2398-8835","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"2025-04-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e72684"}}