AUTHOR=Das Haridas K. 

TITLE=Exploring the dynamics of monkeypox transmission with data-driven methods and a deterministic model

JOURNAL=Frontiers in Epidemiology

VOLUME=Volume 4 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/epidemiology/articles/10.3389/fepid.2024.1334964

DOI=10.3389/fepid.2024.1334964

ISSN=2674-1199

ABSTRACT=This paper aims to analyze global Monkeypox (Mpox) univariate time series data and provides a more comprehensive analysis of disease outbreaks across the world, including the USA, Brazil, and three continents: North America, South America, and Europe. To investigate, we developed a deterministic model that incorporates traditional compartmental models and also implemented deep learning techniques (1D- convolutional neural network (CNN), long-short term memory(LSTM), bidirectional LSTM (BiLSTM), hybrid CNN-LSTM, and CNN-BiLSTM) as well as statistical time series models (autoregressive integrated moving average (ARIMA) and exponential smoothing) on the Mpox data. The novelty of this study is that it delves into the Mpox time series data by implementing the data-driven and mathematical models concurrently — an aspect not typically addressed in the existing literature. The study is also important because implementing these models concurrently improved the reliability of our predictions for the infectious disease. The deterministic model's primary finding is that vaccination rates can flatten the curve of infected dynamics and influence the basic reproduction number. Through model analysis, we determined that increased vaccination among the susceptible human population is crucial to effectively control disease transmission. We also employed the least square method to estimate the essential epidemiological parameters in the proposed deterministic model. Even when there was an outbreak, our study also revealed the potential for epidemic control by adjusting the key epidemiological parameters, namely the baseline contact rate and the proportion of contacts within the human population. In other words, reducing the contact rate in high-risk groups can help alleviate the disease in regions or communities when there is an outbreak. Next, we analyzed data-driven models that contribute to a comprehensive understanding of disease dynamics in different locations. Additionally, we deployed our models to provide short-term (eight-week) predictions across various geographical locations, which produced reliable results in all eight models. In summary, this study utilized a comprehensive framework to investigate univariate time series prediction, and it showed that Mpox is in its die-out situation, aligning with the real data.