Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Jul;84(7):1462-1474.
doi: 10.1002/jemt.23702. Epub 2021 Feb 1.

Machine learning techniques to detect and forecast the daily total COVID-19 infected and deaths cases under different lockdown types

Tanzila Saba  1 , Ibrahim Abunadi  1 , Mirza Naveed Shahzad  2 , Amjad Rehman Khan  1
Affiliations

Machine learning techniques to detect and forecast the daily total COVID-19 infected and deaths cases under different lockdown types

Tanzila Saba et al. Microsc Res Tech. 2021 Jul.

Abstract

COVID-19 has impacted the world in many ways, including loss of lives, economic downturn and social isolation. COVID-19 was emerged due to the SARS-CoV-2 that is highly infectious pandemic. Every country tried to control the COVID-19 spread by imposing different types of lockdowns. Therefore, there is an urgent need to forecast the daily confirmed infected cases and deaths in different types of lockdown to select the most appropriate lockdown strategies to control the intensity of this pandemic and reduce the burden in hospitals. Currently are imposed three types of lockdown (partial, herd, complete) in different countries. In this study, three countries from every type of lockdown were studied by applying time-series and machine learning models, named as random forests, K-nearest neighbors, SVM, decision trees (DTs), polynomial regression, Holt winter, ARIMA, and SARIMA to forecast daily confirm infected cases and deaths due to COVID-19. The models' accuracy and effectiveness were evaluated by error based on three performance criteria. Actually, a single forecasting model could not capture all data sets' trends due to the varying nature of data sets and lockdown types. Three top-ranked models were used to predict the confirmed infected cases and deaths, the outperformed models were also adopted for the out-of-sample prediction and obtained very close results to the actual values of cumulative infected cases and deaths due to COVID-19. This study has proposed the auspicious models for forecasting and the best lockdown strategy to mitigate the causalities of COVID-19.

Keywords: COVID-19; healthcare; lockdown; lungs infection; machine learning models; public health; time series.

PubMed Disclaimer

Conflict of interest statement

Authors declare that they have no competing interests.

Figures

FIGURE 1
FIGURE 1
Nine selected countries, each three from the partial, herd, and complete lockdown
FIGURE 2
FIGURE 2
Day by day number of cumulative confirmed cases per million population in each of the nine countries
FIGURE 3
FIGURE 3
Day by day number of cumulative deaths per million population in each of the nine countries
FIGURE 4
FIGURE 4
Flowchart to forecast the daily cumulative infected and death cases due to COVID‐19
FIGURE 5
FIGURE 5
Legend for Figures 6, 7, 8
FIGURE 6
FIGURE 6
Prediction with three best models of the daily number of cumulative confirmed infected cases and deaths due to COVID‐19 in Bulgaria, Greece, and Russia, where partial lockdown was imposed
FIGURE 7
FIGURE 7
Prediction with three best models of the daily number of cumulative confirmed infected cases and deaths due to COVID‐19 in Hubei (China), Iran, and India, where complete lockdown imposed
FIGURE 8
FIGURE 8
Prediction with three best models of the daily number of cumulative confirmed infected cases and deaths due to COVID‐19 in Iceland, Netherland, and Sweden, where herd lockdown imposed
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Al‐Ameen, Z. , Sulong, G. , Rehman, A. , Al‐Dhelaan, A. , Saba, T. , & Al‐Rodhaan, M. (2015). An innovative technique for contrast enhancement of computed tomography images using normalized gamma‐corrected contrast‐limited adaptive histogram equalization. EURASIP Journal on Advances in Signal Processing, 2015, 32. 10.1186/s13634-015-0214-1 - DOI
    1. Azuaje, F. (2003). Genomic data sampling and its effect on classification performance assessment. BMC Bioinformatics, 4, 5. - PMC - PubMed
    1. Bandyopadhyay, S. K. , & Dutta, S. (2020). Machine learning approach for confirmation of COVID‐19 cases: Positive, negative, death and release. medRxiv.
    1. Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32.
    1. Chatfield, C. , & Yar, M. (1988). Holt‐winters forecasting: Some practical issues. Journal of the Royal Statistical Society Series D (The Statistician), 37, 129–140.

LinkOut - more resources