Forecasting the Spread of COVID-19 and ICU Requirements

Abstract

Since December 2019, the world is fighting against coronavirus disease (COVID-19). This disease is caused by a novel coronavirus termed as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). This work focuses on the applications of machine learning algorithms in the context of COVID-19. Firstly, regression analysis is performed to model the number of confirmed cases and death cases. Our experiments show that autoregressive integrated moving average (ARIMA) can reliably model the increase in the number of confirmed cases and can predict future cases. Secondly, a number of classifiers are used to predict whether a COVID-19 patient needs to be admitted to an intensive care unit (ICU) or semi-ICU. For this, classification algorithms are applied to a dataset having 5644 samples. Using this dataset, the most significant attributes are selected using features selection by ExtraTrees classifier, and Proteina C reativa (mg/dL) is found to be the highest-ranked feature. In our experiments, random forest, logistic regression, support vector machine, XGBoost, stacking and voting classifiers are applied to the top 10 selected attributes of the dataset. Results show that random forest and hard voting classifiers achieve the highest classification accuracy values near 98%, and the highest recall value of 98% in predicting the need for admission into ICU/semi ICU units.

A review on epidemiology, genomic characteristics, spread, and treatments of COVID-19

“…Early detection is required for reducing the spread of COVID-19 [ 84 ]. Therefore some machine learning methods [ [85] , [86] , [87] , [88] , [89] , [90] , [91] ] can be helpful for predicting COVID-19.…”

Federated learning: Applications, challenges and future directions

“…Classification algorithms in machine learning [70] learn how to categorize or annotate a given collection of occurrences with labels or classes. For example, the classification tasks of COVID-19 detections [71][72][73][74][75][76][77][78][79][80][81][82][83][84], cancer diagnoses [85][86][87][88][89][90][91][92][93][94] and autism spectrum disorder (ASD) [84,[95][96][97] are considered in a FL setting in healthcare. Other classification tasks studied include emotion recognition and human activity [98][99][100] and prediction of patient hospitalization [101,102].…”

A Novel SNOW3G-M Algorithm and Medical

“…Finally, the proposed SNOW3G-M algorithm was compared with the SNOW3G traditional algorithm in Table 5. The proposed snow3G-M algorithm has several benefits, especially in medical uses, because of its speed in encrypting data, and this thus leads to a speedy transmission of data between the sender and recipient over the network, where the doctor monitors the patient's condition and gives him instructions via phone call, in addition to using several applications to register to obtain vaccines against COVID-19 around the world [27][28][29][30][31].…”