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

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.

Machine Learning–Based Prediction of Growth in Confirmed COVID-19 Infection Cases in 114 Countries Using Metrics of Nonpharmaceutical Interventions and Cultural Dimensions: Model Development and Validation (Preprint)

“…Their results suggest that these predictors are relevant for COVID-19 mortality rate modelling. Similar to our work, Saba et al [16] implemented multiple machine learning models to forecast COVID-19 cases based on NPI implementation. However, their work differs in that it only includes lockdown type as an NPI feature (and does not consider cultural dimensions), the study is limited to 9 countries, and the reported case numbers are predicted instead of the change in case numbers.…”

“…Machine learning has been used in applications to combat the COVID-19 pandemic, such as in patient monitoring and genome sequencing [63][64][65][66]. Recent studies have also used various statistical and machine learning techniques for short-term forecasting of infection rates for the COVID-19 pandemic [13,15,16,30,33] using reported transmission and mortality statistics, population geographical movement data, and media activity. Pinter et al [13] combined multilayer perceptron with fuzzy inference to predict reported infection and mortality numbers in Hungary with only case number features from May to August 2020.…”

“…Many epidemiological models that forecast future infection numbers have therefore suggested the role of NPIs in reducing infection rates [2,4,7,12], which can aid the implementation of national strategies and policy decision-making. Recent research incorporates publicly available data with machine learning for use cases such as reported infection case number forecasting [13][14][15][16]. Although these studies have used various features, such as existing infection statistics [13], weather [14], media and internet activity [15], and lockdown type [16], to predict infection case numbers, no study has yet examined the combination of NPIs and cultural dimensions in predicting infection growth.…”

“…Recent research incorporates publicly available data with machine learning for use cases such as reported infection case number forecasting [13][14][15][16]. Although these studies have used various features, such as existing infection statistics [13], weather [14], media and internet activity [15], and lockdown type [16], to predict infection case numbers, no study has yet examined the combination of NPIs and cultural dimensions in predicting infection growth. In this paper, we include the implementation of NPIs at the national level as features (ie, independent variables) in predicting the national growth of the number of confirmed infection cases.…”

Applications of Artificial Intelligence, Machine Learning, Big Data and the Internet of Things to the COVID-19 Pandemic: A Scientometric Review Using Text Mining

“…Other well-known algorithms have been tested, such as ARIMA (auto-regressive integrated moving average model) [66] and support vector machine (SVM), which are mainly used for the forecasting of time series data [67,68]. Several of these models have been applied as predictors of daily infections under different types of lockdown, thus helping in government decision making [69,70]. ML techniques have been successfully used to plan public policies [71].…”