Related Experiment Video
Updated: Jul 10, 2025
10:46
A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data
Published on: December 9, 2015
10.7K
Modeling Global Monkeypox Infection Spread Data: A Comparative Study of Time Series Regression and Machine Learning
Vishwajeet Singh1, Saif Ali Khan2, Subhash Kumar Yadav3
1Directorate of Online Education, Manipal Academy of Higher Education (MAHE), Manipal, Karnataka, 576104, India.
Current Microbiology
|November 25, 2023
Summary
This study analyzed monkeypox (MPOX) spread using statistical and machine learning models. Random Forest outperformed ARIMA in most countries, highlighting the need for tailored modeling for effective public health strategies.
Area of Science:
- Epidemiology
- Infectious Diseases
- Public Health
Background:
- Emerging viral infections, like monkeypox (MPOX), pose significant global health threats.
- The COVID-19 pandemic underscored the need for robust surveillance and prediction of viral disease outbreaks.
- Understanding MPOX transmission dynamics is crucial for effective public health interventions.
Purpose of the Study:
- To analyze and predict the spread of monkeypox in high-incidence countries.
- To compare the performance of statistical and machine learning models in forecasting MPOX transmission.
- To inform policy-making for monkeypox containment and control.
Main Methods:
- Utilized distribution fitting, ARIMA modeling, and Random Forest machine learning.
- Applied country-specific datasets from the top ten MPOX-affected nations.
- Evaluated model accuracy using Root Mean Square Error (RMSE).
Main Results:
- Random Forest model demonstrated superior predictive accuracy in six out of ten countries studied.
- ARIMA modeling provided better predictions in the remaining four countries.
- Model performance varied by country, indicating the need for context-specific approaches.
Conclusions:
- The choice of modeling technique significantly impacts the accuracy of monkeypox spread prediction.
- Tailoring epidemiological models to country-specific data is essential for effective public health policy.
- Integrating multiple modeling approaches enhances understanding and control of MPOX outbreaks.
