Comparison of growth, time series, and hybrid models for HIV infectious disease incidence in adults in Saudi Arabia
8 affiliations
- 1Research Center, Almoosa Health Group
- 2Department of Health Professions Education, National University of Medical Sciences
- 3Department of Medical and Surgical Nursing, College of Nursing, Princess Norah Bint Abdurrahman University
- 4Faculty of Medical and Health Sciences, Liwa University
- 5Department of Botany, Allama Iqbal Open University
- 6Adult Infectious Diseases Fellowship Program Director at Almoosa Specialist Hospital
- 7Almoosa Health Group
- 8Medical-Surgical Nursing Department, College of Nursing, Princess Nourah bint Abdulrahman University
Abstract
Background and aim HIV (Human Immunodeficiency Virus) is a virus that causes the immune system to be damaged, which results in reducing the body’s ability to defend against infections and illnesses. This study aims to model new HIV cases among adults in KSA using selected growth, time series, and hybrid models. Methods The study utilized official data on new HIV/AIDS cases among adults (15–49) from the World Bank website for the period 1990–2024. Various growth, conventional time series and hybrid models were proposed and used to model the series. The accuracy measures like RMSE, MAE, MAPE, MASE, and SMAPE were used to compare models, and the DM test was applied to assess the consistency between model predictions. Results were considered statistically significant if p < 0.05 and all the analyses and visualizations were performed in R-Studio. Results The time-series data of newly infected HIV cases among adults (ages 15–49) from 1990 to 2024 showed the mean number of cases was approximately 502 ± 323. Among the hybrid frameworks evaluated, Exponential-ETS emerged as the superior model, attaining the lowest RMSE value of 91.500, outperforming all competing specifications. The forecast for 2025 using the hybrid model projects new cases at 1,553.91 (95% CI: 1,272.23–1,828.94), rising to 2,157.74 (95% CI: 1,497.40–2,866.45) by 2029. However, the projected annual increment is lower than the surge observed in 2019–2024. Conclusion This study concluded that the hybrid model provides the most robust forecasting framework for HIV incidence in KSA. The 5-year projections indicated a continued upward trend, but with a decelerated rate of growth compared to the sharp surge observed in 2019–2024. This deceleration suggests progress towards Vision 2030 goals of reducing the burden of infectious diseases through strengthened health infrastructure, expanded screening programs, and improved public health awareness.
Related
- The pitfalls of incidence-based time series regression for inferring the effects of weather on infectious diseases
- Benchmarking time series foundation models for multi-country infectious disease forecasting: a retrospective evaluation across over 70 diseases
- Population-level measles RT–PCR cycle threshold values and their relationships with disease severity, transmission, and incidence metrics: a time series analysis of the 2025–2026 outbreak in Mexico
- Incidence of venous thromboembolism with intraoperative tranexamic acid use in breast surgery patients on estrogen-containing medications: a case series
- A methodological exploration of monthly incidence rate of hepatitis B in China: a time series and machine learning analysis
BibTeX
@article{daniyal2026comparison,
title = {{Comparison of growth, time series, and hybrid models for HIV infectious disease incidence in adults in Saudi Arabia}},
author = {Muhammad Daniyal and Nadia Shabnam and Hanan Alyami and Ali Jaber Alqahtani and Madiha Shakeel and Mohammed Sharaf Alabdullah and Batool Mohammed Alhassan and Abbas Al Mutair and Hibah Abdulrahim Bahri},
journal = {BMC Infectious Diseases},
year = {2026},
month = jul,
doi = {10.1186/s12879-026-14050-7},
url = {https://doi.org/10.1186/s12879-026-14050-7},
note = {CC BY},
}
RIS
TY - JOUR
TI - Comparison of growth, time series, and hybrid models for HIV infectious disease incidence in adults in Saudi Arabia
AU - Muhammad Daniyal
AU - Nadia Shabnam
AU - Hanan Alyami
AU - Ali Jaber Alqahtani
AU - Madiha Shakeel
AU - Mohammed Sharaf Alabdullah
AU - Batool Mohammed Alhassan
AU - Abbas Al Mutair
AU - Hibah Abdulrahim Bahri
PY - 2026
DA - 2026/07/01
JO - BMC Infectious Diseases
DO - 10.1186/s12879-026-14050-7
UR - https://doi.org/10.1186/s12879-026-14050-7
AB - Background and aim HIV (Human Immunodeficiency Virus) is a virus that causes the immune system to be damaged, which results in reducing the body’s ability to defend against infections and illnesses. This study aims to model new HIV cases among adults in KSA using selected growth, time series, and hybrid models. Methods The study utilized official data on new HIV/AIDS cases among adults (15–49) from the World Bank website for the period 1990–2024. Various growth, conventional time series and hybrid models were proposed and used to model the series. The accuracy measures like RMSE, MAE, MAPE, MASE, and SMAPE were used to compare models, and the DM test was applied to assess the consistency between model predictions. Results were considered statistically significant if p < 0.05 and all the analyses and visualizations were performed in R-Studio. Results The time-series data of newly infected HIV cases among adults (ages 15–49) from 1990 to 2024 showed the mean number of cases was approximately 502 ± 323. Among the hybrid frameworks evaluated, Exponential-ETS emerged as the superior model, attaining the lowest RMSE value of 91.500, outperforming all competing specifications. The forecast for 2025 using the hybrid model projects new cases at 1,553.91 (95% CI: 1,272.23–1,828.94), rising to 2,157.74 (95% CI: 1,497.40–2,866.45) by 2029. However, the projected annual increment is lower than the surge observed in 2019–2024. Conclusion This study concluded that the hybrid model provides the most robust forecasting framework for HIV incidence in KSA. The 5-year projections indicated a continued upward trend, but with a decelerated rate of growth compared to the sharp surge observed in 2019–2024. This deceleration suggests progress towards Vision 2030 goals of reducing the burden of infectious diseases through strengthened health infrastructure, expanded screening programs, and improved public health awareness.
SN - 1471-2334
ER -