Objectives To develop and evaluate forecasting models using the Holt-Winters statistical approach and the long short-term memory (LSTM) deep learning method for weekly seasonal influenza-like illness (ILI) incidences in Saudi Arabia. The study compares model performance and assesses the predictive value added by incorporating region-specific exogenous variables within Middle Eastern epidemiological modeling.
Methods This study compared the performance of Holt-Winters and LSTM models in forecasting weekly ILI cases in Saudi Arabia, using data collected from 2017 to 2022. Time series analysis integrated exogenous variables including climatic conditions and population mobility trends. The Holt-Winters model employed both additive and multiplicative seasonal components. Model performance was evaluated using root mean squared error (RMSE), mean absolute percentage error, and R2.
Results The best-performing model, LSTM with exogenous variables, achieved an RMSE of 28.55, mean absolute error (MAE) of 0.14, R2 of 0.96, and percent bias (PBIAS) of +2.1%, indicating negligible systematic error. The LSTM model without exogenous variables demonstrated slightly lower accuracy (RMSE of 34.07, MAE of 0.18, R2 of 0.93, PBIAS of +5.8%), indicating strong predictive capability but less precision in determining peak ILI cases. The Holt-Winters model effectively captured seasonal and long-term trends, but showed a moderate performance with an RMSE of 82.57, MAE of 0.38, R2 of 0.58, and a high PBIAS of +14.2%, revealing significant unexplained variability during periods of high incidence fluctuation.
Conclusion This study highlights the respective strengths and limitations of statistical and machine learning approaches for ILI forecasting.
Citations
Citations to this article as recorded by
Early-warning prediction of visceral leishmaniasis mortality using a multivariate STL–deep learning hybrid approach on 20 years of monthly time series Fathelrhman El Guma, Maaweya Awadalla, Halah Z. Al Rawi, Bashayer Saeed, Huda M. Alshanbari, Alshaikh A. Shokeralla, Bandar Alosaimi Frontiers in Public Health.2026;[Epub] CrossRef
A hybrid STL–LightGBM framework with probabilistic forecasting for Influenza A incidence in the post-pandemic Saudi Arabia Reham M. Alahmadi, Maaweya Awadalla, Bashayer Saeed, Huda M. Alshanbari, Alshaikh A. Shokeralla, Ali Atif Yassin, Bandar Alosaimi, Fathelrhman El Guma Frontiers in Public Health.2026;[Epub] CrossRef
Bayesian inference for modeling seasonal influenza transmission under control measures Rania Saadeh, Naseam Al-Kuleab, Fathelrhman EL Guma, Alshaikh A. Shokeralla, Suliman Jamiel M. Abdalla, Mohamed A. Abdoon, Mohamed Hafez Results in Control and Optimization.2026; 23: 100714. CrossRef
Machine Learning-Based Prediction of Seasonal Influenza Trends in Saudi Arabia: A Tool for Regional Public Health Planning Alshaikh A. Shokeralla, Fathelrhman El Guma, Ali H. Abdalla, Amal E.Y. Hagsddig, Rahma AbuBakr Musa, M.A.M. Eltaweel, Abdelaziz H. Elawad, Ibrahim Elshamy International Journal of Statistics in Medical Res.2025; 14: 688. CrossRef
As the world grapples with the problem of the coronavirus disease 2019 (COVID-19) pandemic and its devastating effects, scientific groups are working towards solutions to mitigate the effects of the virus. This paper aimed to collate information on COVID-19 prediction models. A systematic literature review is reported, based on a manual search of 1,196 papers published from January to December 2020. Various databases such as Google Scholar, Web of Science, and Scopus were searched. The search strategy was formulated and refined in terms of subject keywords, geographical purview, and time period according to a predefined protocol. Visualizations were created to present the data trends according to different parameters. The results of this systematic literature review show that the study findings are critically relevant for both healthcare managers and prediction model developers. Healthcare managers can choose the best prediction model output for their organization or process management. Meanwhile, prediction model developers and managers can identify the lacunae in their models and improve their data-driven approaches.
Citations
Citations to this article as recorded by
A simultaneous simulation of human behavior dynamics and epidemic spread: A multi-country study amidst the COVID-19 pandemic Ann Osi, Navid Ghaffarzadegan Mathematical Biosciences.2025; 380: 109368. CrossRef
Hierarchical Time Series Forecasting of COVID-19 Cases Using County-Level Clustering Data Sonaxy Mohanty, Airi Shimamura, Charles D. Nicholson, Andrés D. González, Talayeh Razzaghi Operations Research Forum.2025;[Epub] CrossRef
Detection of covid- 19 on GGO segmented CT image using stacking-based ensemble deep learning V. L. Nisha, D. Menaka Multimedia Tools and Applications.2025; 84(35): 43693. CrossRef
Characterizing pandemic-related publications: a retrospective study using spatial citation network analysis Zhiyang Xiao, Lingyu Fan, Zidong Yu, Xintao Liu Computational Urban Science.2025;[Epub] CrossRef
An overview of reviews on digital health interventions during COVID- 19 era: insights and lessons for future pandemics Foziye Tahmasbi, Esmaeel Toni, Zohreh Javanmard, Niloofar Kheradbin, Somayeh Nasiri, Farahnaz Sadoughi Archives of Public Health.2025;[Epub] CrossRef
COVID-19 risk stratification among older adults: a machine learning approach to identify personal and health-related risk factors Arezoo Abasi, Seyed Abbas Motevalian, Haleh Ayatollahi BMC Public Health.2025;[Epub] CrossRef
Artificial intelligence-based techniques for predicting outcomes in COVID-19 patients Victoria Moghildea, Cristina Trofimov, Ion Grabovschi, Ruslan Baltaga, Serghei Sandru, Sergiu Cobiletchi, Oleg Arnaut Moldovan Journal of Health Sciences.2025; 12(1): 61. CrossRef
Forecasting Upper Bounds for Daily New COVID-19 Infections Using Tolerance Limits Hsiuying Wang Mathematics.2025; 13(18): 2908. CrossRef
Bridging statistics and deep learning: a causal data-fusion framework for epidemic prediction Vasileios E. Papageorgiou, Georgios Petmezas, Aristeidis Georgakis, Nicos Maglaveras, George Tsaklidis Communications in Statistics - Simulation and Comp.2025; : 1. CrossRef
The Telemedicine Demand Index and its Utility in Managing COVID-19 Case Surges Martin Yong Kwong Lee, Kie Beng Goh, Deanna Xiuting Koh, Si Jack Chong, Raymond Swee Boon Chua Telemedicine and e-Health.2024; 30(2): 545. CrossRef
Vaccination compartmental epidemiological models for the delta and omicron SARS-CoV-2 variants J. Cuevas-Maraver, P.G. Kevrekidis, Q.Y. Chen, G.A. Kevrekidis, Y. Drossinos Mathematical Biosciences.2024; 367: 109109. CrossRef
The reporting completeness and transparency of systematic reviews of prognostic prediction models for COVID-19 was poor: a methodological overview of systematic reviews Persefoni Talimtzi, Antonios Ntolkeras, Georgios Kostopoulos, Konstantinos I. Bougioukas, Eirini Pagkalidou, Andreas Ouranidis, Athanasia Pataka, Anna-Bettina Haidich Journal of Clinical Epidemiology.2024; 167: 111264. CrossRef
A comprehensive benchmark for COVID-19 predictive modeling using electronic health records in intensive care Junyi Gao, Yinghao Zhu, Wenqing Wang, Zixiang Wang, Guiying Dong, Wen Tang, Hao Wang, Yasha Wang, Ewen M. Harrison, Liantao Ma Patterns.2024; 5(4): 100951. CrossRef
A study of learning models for COVID-19 disease prediction Sakshi Jain, Pradeep Kumar Roy Journal of Ambient Intelligence and Humanized Comp.2024; 15(4): 2581. CrossRef
AI-powered COVID-19 forecasting: a comprehensive comparison of advanced deep learning methods Muhammad Usman Tariq, Shuhaida Binti Ismail Osong Public Health and Research Perspectives.2024; 15(2): 115. CrossRef
Climate change, its impact on emerging infectious diseases and new technologies to combat the challenge Hongyan Liao, Christopher J. Lyon, Binwu Ying, Tony Hu Emerging Microbes & Infections.2024;[Epub] CrossRef
Digital Technology Ecotone to Revolutionize Health Sector Mario Coccia SSRN Electronic Journal.2024;[Epub] CrossRef
Leveraging advances in data-driven deep learning methods for hybrid epidemic modeling Shi Chen, Daniel Janies, Rajib Paul, Jean-Claude Thill Epidemics.2024; 48: 100782. CrossRef
Assessing the Utility of Prediction Scores PAINT, ISARIC4C, CHIS, and COVID-GRAM at Admission and Seven Days after Symptom Onset for COVID-19 Mortality Alina Doina Tanase, Oktrian FNU, Dan-Mihai Cristescu, Paula Irina Barata, Dana David, Emanuela-Lidia Petrescu, Daliana-Emanuela Bojoga, Teodora Hoinoiu, Alexandru Blidisel Journal of Personalized Medicine.2024; 14(9): 966. CrossRef
An effective drift-diffusion model for pandemic propagation and uncertainty prediction Clara Bender, Abhimanyu Ghosh, Hamed Vakili, Preetam Ghosh, Avik W. Ghosh Biophysical Reports.2024; 4(4): 100182. CrossRef
An epidemical model with nonlocal spatial infections Su Yang, Weiqi Chu, Panayotis Kevrekidis Proceedings of the European Academy of Sciences an.2024;[Epub] CrossRef
Is It Possible to Predict COVID-19? Stochastic System Dynamic Model of Infection Spread in Kazakhstan Berik Koichubekov, Aliya Takuadina, Ilya Korshukov, Anar Turmukhambetova, Marina Sorokina Healthcare.2023; 11(5): 752. CrossRef
Early triage echocardiography to predict outcomes in patients admitted with COVID‐19: a multicenter study Daniel Peck, Andrea Beaton, Maria Carmo Nunes, Nicholas Ollberding, Allison Hays, Pranoti Hiremath, Federico Asch, Nitin Malik, Christopher Fung, Craig Sable, Bruno Nascimento Echocardiography.2023; 40(5): 388. CrossRef
Static Seeding and Clustering of LSTM Embeddings to Learn From Loosely Time-Decoupled Events Christian G. Manasseh, Razvan Veliche, Jared Bennett, Hamilton Scott Clouse IEEE Access.2023; 11: 64219. CrossRef
Harnessing the power of AI: Advanced deep learning models optimization for accurate SARS-CoV-2 forecasting Muhammad Usman Tariq, Shuhaida Binti Ismail, Muhammad Babar, Ashir Ahmad, Lin Wang PLOS ONE.2023; 18(7): e0287755. CrossRef
Development and validation of COEWS (COVID-19 Early Warning Score) for hospitalized COVID-19 with laboratory features: A multicontinental retrospective study Riku Klén, Ivan A Huespe, Felipe Aníbal Gregalio, Antonio Lalueza Lalueza Blanco, Miguel Pedrera Jimenez, Noelia Garcia Barrio, Pascual Ruben Valdez, Matias A Mirofsky, Bruno Boietti, Ricardo Gómez-Huelgas, José Manuel Casas-Rojo, Juan Miguel Antón-Santos eLife.2023;[Epub] CrossRef
Dynamic transmission modeling of COVID-19 to support decision-making in Brazil: A scoping review in the pre-vaccine era Gabriel Berg de Almeida, Lorena Mendes Simon, Ângela Maria Bagattini, Michelle Quarti Machado da Rosa, Marcelo Eduardo Borges, José Alexandre Felizola Diniz Filho, Ricardo de Souza Kuchenbecker, Roberto André Kraenkel, Cláudia Pio Ferreira, Suzi Alves Cam PLOS Global Public Health.2023; 3(12): e0002679. CrossRef
Predictive Models for Forecasting Public Health Scenarios: Practical Experiences Applied during the First Wave of the COVID-19 Pandemic Jose M. Martin-Moreno, Antoni Alegre-Martinez, Victor Martin-Gorgojo, Jose Luis Alfonso-Sanchez, Ferran Torres, Vicente Pallares-Carratala International Journal of Environmental Research an.2022; 19(9): 5546. CrossRef
Artificial intelligence and clinical deterioration James Malycha, Stephen Bacchi, Oliver Redfern Current Opinion in Critical Care.2022; 28(3): 315. CrossRef
Objectives
From the introduction of HIV into the Republic of Korea in 1985 through 2012, 9,410 HIV-infected Koreans have been identified. Since 2000, there has been a sharp increase in newly diagnosed HIV-infected Koreans. It is necessary to estimate the changes in HIV infection to plan budgets and to modify HIV/AIDS prevention policy. We constructed autoregressive integrated moving average (ARIMA) models to forecast the number of HIV infections from 2013 to 2017. Methods
HIV infection data from 1985 to 2012 were used to fit ARIMA models. Akaike Information Criterion and Schwartz Bayesian Criterion statistics were used to evaluate the constructed models. Estimation was via the maximum likelihood method. To assess the validity of the proposed models, the mean absolute percentage error (MAPE) between the number of observed and fitted HIV infections from 1985 to 2012 was calculated. Finally, the fitted ARIMA models were used to forecast the number of HIV infections from 2013 to 2017. Results
The fitted number of HIV infections was calculated by optimum ARIMA (2,2,1) model from 1985–2012. The fitted number was similar to the observed number of HIV infections, with a MAPE of 13.7%. The forecasted number of new HIV infections in 2013 was 962 (95% confidence interval (CI): 889–1,036) and in 2017 was 1,111 (95% CI: 805–1,418). The forecasted cumulative number of HIV infections in 2013 was 10,372 (95% CI: 10,308–10,437) and in 2017 was14,724 (95% CI: 13,893–15,555) by ARIMA (1,2,3). Conclusion
Based on the forecast of the number of newly diagnosed HIV infections and the current cumulative number of HIV infections, the cumulative number of HIV-infected Koreans in 2017 would reach about 15,000.
Citations
Citations to this article as recorded by
Multidimensional Trends and AI-Based Forecasts of HIV Incidence in Korea, 1985–2024 Seungho Baek, Haneol Cho, Chansoo Kim, Yeonju Kim Journal of Epidemiology and Global Health.2026;[Epub] CrossRef
A Detailed Study of ABC‐Type Fractal–Fractional Dynamical Model of HIV/AIDS Mansour A. Abdulwasaa, Esam Y. Salah, Mohammed S. Abdo, Bhausaheb Sontakke, Sahar Ahmed Idris, Mohammed Amood Al-Kamarany, Kuo Shou Chiu Computational and Mathematical Methods.2025;[Epub] CrossRef
CONSIDERATIONS ON THE EFFICIENCY OF TIME SERIES ANALYSIS IN FORECASTING NEW INFLUENZA CASES IN THE 2024-2025 SEASON Cristina-Gena Dascălu, Doriana Agop Forna , Magda Ecaterina Antohe Romanian Journal of Oral Rehabilitation.2025; 17(1): 923. CrossRef
Intelligent Health Care and Diseases Management System: Multi-Day-Ahead Predictions of COVID-19 Ahed Abugabah, Farah Shahid Mathematics.2023; 11(4): 1051. CrossRef
Prevalence of HIV in Kazakhstan 2010–2020 and Its Forecasting for the Next 10 Years Kamilla Mussina, Shirali Kadyrov, Ardak Kashkynbayev, Sauran Yerdessov, Gulnur Zhakhina, Yesbolat Sakko, Amin Zollanvari, Abduzhappar Gaipov HIV/AIDS - Research and Palliative Care.2023; Volume 15: 387. CrossRef
Integration models of demand forecasting and inventory control for coconut sugar using the ARIMA and EOQ modification methods Siti Wardah, Nunung Nurhasanah, Wiwik Sudarwati Jurnal Sistem dan Manajemen Industri.2023; 7(2): 127. CrossRef
Deep learning-based forecasting model for COVID-19 outbreak in Saudi Arabia Ammar H. Elsheikh, Amal I. Saba, Mohamed Abd Elaziz, Songfeng Lu, S. Shanmugan, T. Muthuramalingam, Ravinder Kumar, Ahmed O. Mosleh, F.A. Essa, Taher A. Shehabeldeen Process Safety and Environmental Protection.2021; 149: 223. CrossRef
Forecasting future HIV infection cases: evidence from Indonesia Maria Dyah Kurniasari, Andrian Dolfriandra Huruta, Hsiu Ting Tsai, Cheng-Wen Lee Social Work in Public Health.2021; 36(1): 12. CrossRef
Forecasting Confirmed Malaria Cases in Northwestern Province of Zambia: A Time Series Analysis Using 2014–2020 Routine Data Dhally M. Menda, Mukumbuta Nawa, Rosemary K. Zimba, Catherine M. Mulikita, Jim Mwandia, Henry Mwaba, Karen Sichinga, Hamidreza Karimi-Sari Advances in Public Health.2021; 2021: 1. CrossRef
An Adaptive Variational Mode Decomposition Technique with Differential Evolution Algorithm and Its Application Analysis Yuanxin Wang, Chaoqun Duan Shock and Vibration.2021;[Epub] CrossRef
A comparative study on the prediction of the BP artificial neural network model and the ARIMA model in the incidence of AIDS Zeming Li, Yanning Li BMC Medical Informatics and Decision Making.2020;[Epub] CrossRef
Forecasting the Monthly Reported Cases of Human Immunodeficiency Virus (HIV) at Minna Niger State, Nigeria Nwanne Christiana Umunna, Samuel Olayemi Olanrewaju Open Journal of Statistics.2020; 10(03): 494. CrossRef
Hybrid Decomposition Time-Series Forecasting by DirRec Strategy: Electric Load Forecasting Using Machine-Learning Branislav Vuksanovic, Davoud Rahimi Ardali International Journal of Computer and Electrical E.2019; 11(1): 1. CrossRef
Exploring an Ensemble of Methods that Combines Fuzzy Cognitive Maps and Neural Networks in Solving the Time Series Prediction Problem of Gas Consumption in Greece Konstantinos I. Papageorgiou, Katarzyna Poczeta, Elpiniki Papageorgiou, Vassilis C. Gerogiannis, George Stamoulis Algorithms.2019; 12(11): 235. CrossRef
APLIKASI METODE DOUBLE EXPONENTIAL SMOOTHING HOLT DAN ARIMA UNTUK MERAMALKAN VOLUNTARY COUNSELING AND TESTING (VCT) ODHA DI PROVINSI JAWA TIMUR Suci Retno Ningtiyas The Indonesian Journal of Public Health.2019; 13(2): 158. CrossRef
Research into the high-precision marine integrated navigation method using INS and star sensors based on time series forecasting BPNN Qiu Ying Wang, Kaiyue Liu, Zhiguo Sun, Minghui Zhang Optik.2018; 172: 494. CrossRef
Real-time predictive seasonal influenza model in Catalonia, Spain Luca Basile, Manuel Oviedo de la Fuente, Nuria Torner, Ana Martínez, Mireia Jané, Jeffrey Shaman PLOS ONE.2018; 13(3): e0193651. CrossRef
Using an Autoregressive Integrated Moving Average Model to Predict the Incidence of Hemorrhagic Fever with Renal Syndrome in Zibo, China, 2004–2014 Tao Wang, Yunping Zhou, Ling Wang, Zhenshui Huang, Feng Cui, Shenyong Zhai Japanese Journal of Infectious Diseases.2016; 69(4): 279. CrossRef
Time series analysis of influenza incidence in Chinese provinces from 2004 to 2011 Xin Song, Jun Xiao, Jiang Deng, Qiong Kang, Yanyu Zhang, Jinbo Xu Medicine.2016; 95(26): e3929. CrossRef
Modelling the prevalence of hepatitis C virus amongst blood donors in Libya: An investigation of providing a preventive strategy Mohamed A Daw World Journal of Virology.2016; 5(1): 14. CrossRef
Forecast analysis of any opportunistic infection among HIV positive individuals on antiretroviral therapy in Uganda John Rubaihayo, Nazarius M. Tumwesigye, Joseph Konde-Lule, Fredrick Makumbi BMC Public Health.2016;[Epub] CrossRef
The Use of an Autoregressive Integrated Moving Average Model for Prediction of the Incidence of Dysentery in Jiangsu, China Kewei Wang, Wentao Song, Jinping Li, Wu Lu, Jiangang Yu, Xiaofeng Han Asia Pacific Journal of Public Health.2016; 28(4): 336. CrossRef
Prevalence of hemorrhagic fever with renal syndrome in Yiyuan County, China, 2005–2014 Tao Wang, Jie Liu, Yunping Zhou, Feng Cui, Zhenshui Huang, Ling Wang, Shenyong Zhai BMC Infectious Diseases.2015;[Epub] CrossRef
Application of an autoregressive integrated moving average model for predicting injury mortality in Xiamen, China Yilan Lin, Min Chen, Guowei Chen, Xiaoqing Wu, Tianquan Lin BMJ Open.2015; 5(12): e008491. CrossRef
Back propagation neural network with adaptive differential evolution algorithm for time series forecasting Lin Wang, Yi Zeng, Tao Chen Expert Systems with Applications.2015; 42(2): 855. CrossRef
Direct Medical Costs of Hospitalizations for Cardiovascular Diseases in Shanghai, China Shengnan Wang, Max Petzold, Junshan Cao, Yue Zhang, Weibing Wang Medicine.2015; 94(20): e837. CrossRef
Changing Patterns of HIV Epidemic in 30 Years in East Asia S. Pilar Suguimoto, Teeranee Techasrivichien, Patou Masika Musumari, Christina El-saaidi, Bhekumusa Wellington Lukhele, Masako Ono-Kihara, Masahiro Kihara Current HIV/AIDS Reports.2014; 11(2): 134. CrossRef
What is Next for HIV/AIDS in Korea? Hae-Wol Cho, Chaeshin Chu Osong Public Health and Research Perspectives.2013; 4(6): 291. CrossRef
First
Prev
