Prediction of COVID-19 Pandemic in Bangladesh: Dual Application of Susceptible-Infective-Recovered (SIR) and Machine Learning Approach

Iqramul Haq; Md Ismail Hossain; Ahmed Abdus Saleh Saleheen; Md Iqbal Hossain Nayan; Mafruha Sultana Mila

doi:10.1155/2022/8570089

Prediction of COVID-19 Pandemic in Bangladesh: Dual Application of Susceptible-Infective-Recovered (SIR) and Machine Learning Approach

Interdiscip Perspect Infect Dis. 2022 Apr 26:2022:8570089. doi: 10.1155/2022/8570089. eCollection 2022.

Authors

Iqramul Haq¹, Md Ismail Hossain², Ahmed Abdus Saleh Saleheen², Md Iqbal Hossain Nayan³, Mafruha Sultana Mila²

Affiliations

¹ Department of Agricultural Statistics, Sher-e-Bangla Agricultural University, Dhaka 1207, Bangladesh.
² Department of Statistics, Jagannath University, Dhaka 1100, Bangladesh.
³ Quality Services and Compliance, Square Pharmaceutical Limited, Dhaka, Bangladesh.

Abstract

The outbreak of COVID-19 is a global problem today, and, to reduce infectious cases and increase recovered cases, it is relevant to estimate the future movement and pattern of the disease. To identify the hotspot for COVID-19 in Bangladesh, we performed a cluster analysis based on the hierarchical k-means approach. A well-known epidemiological model named "susceptible-infectious-recovered (SIR)" and an additive regression model named "Facebook PROPHET Procedure" were used to predict the future direction of COVID-19 using data from IEDCR. Here we compare the results of the optimized SIR model and a well-known machine learning algorithm (PROPHET algorithm) for the forecasting trend of the COVID-19 pandemic. The result of the cluster analysis demonstrates that Dhaka city is now a hotspot for the COVID-19 pandemic. The basic reproduction ratio value was 2.1, which indicates that the infection rate would be greater than the recovery rate. In terms of the SIR model, the result showed that the virus might be slightly under control only after August 2022. Furthermore, the PROPHET algorithm observed an altered result from SIR, implying that all confirmed, death, and recovered cases in Bangladesh are increasing on a daily basis. As a result, it appears that the PROPHET algorithm is appropriate for pandemic data with a growing trend. Based on the findings, the study recommended that the pandemic is not under control and ensured that if Bangladesh continues the current pattern of infectious rate, the spread of the pandemic in Bangladesh next year will increase.