Modeling and Forecasting Monkeypox Cases Using Stochastic Models.

Area of Science:

• Epidemiology
• Computational Biology
• Public Health

Background:

• Monkeypox virus (MPXV) poses a significant public health concern due to its increasing severity and human-to-human transmission.
• Accurate modeling and forecasting of MPXV cases are crucial for effective public health strategies and resource allocation.

Purpose of the Study:

• To compare the predictive performance of a machine learning approach against a traditional time series model for forecasting monkeypox cases.
• To identify the most accurate model for predicting the future trajectory of monkeypox outbreaks.

Main Methods:

• A comparative analysis was conducted using the multilayer perceptron (MLP) model, a machine learning technique, and the Box-Jenkins (ARIMA) methodology.
• Both models were applied to a cumulative monkeypox dataset, and their performance was evaluated using metrics like root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE).

Main Results:

• The ARIMA (7,1,7) model yielded an RMSE of 150.78.
• The MLP model, utilizing a sigmoid activation function with ten hidden neurons, achieved a significantly lower RMSE of 54.40.
• Visualizations confirmed that the MLP model provided a superior fit to the monkeypox case data compared to the ARIMA model.

Conclusions:

• Machine learning models, particularly MLP, demonstrate superior accuracy in predicting monkeypox outbreaks compared to traditional time series methods.
• Future research could explore advanced models like Extreme Learning Machine (ELM) and Support Vector Machines (SVM) for enhanced forecasting.
• Continued monitoring and adherence to public health guidelines are recommended, alongside potential government interventions to mitigate the rising trend of monkeypox cases.