Determination of COVID-19 Patients Using Machine Learning Algorithms

Marium Malik,Muhammad Waseem Iqbal,Syed Khuram Shahzad,Babar Ayub Khan,Muhammad Raza Naqvi,Muhammad Tahir Mushtaq,Muhammad Usman Tahir,Maira Kamran

doi:10.32604/iasc.2022.018753

Abstract

Coronavirus disease (COVID-19), also known as Severe acute respiratory syndrome (SARS-COV2) and it has imposed deep concern on public health globally. Based on its fast-spreading breakout among the people exposed to the wet animal market in Wuhan city of China, the city was indicated as its origin. The symptoms, reactions, and the rate of recovery shown in the coronavirus cases worldwide have been varied . The number of patients is still rising exponentially, and some countries are now battling the third wave. Since the most effective treatment of this disease has not been discovered so far, early detection of potential COVID-19 patients can help isolate them socially to decrease the spread and flatten the curve. In this study, we explore state-of-the-art research on coronavirus disease to determine the impact of this illness among various age groups. Moreover, we analyze the performance of the Decision tree (DT), K-nearest neighbors (KNN), Naïve bayes (NB), Support vector machine (SVM), and Logistic regression (LR) to determine COVID-19 in the patients based on their symptoms. A dataset obtained from a public repository was collected and pre-processed, before applying the selected Machine learning (ML) algorithms on them. The results demonstrate that all the ML algorithms incorporated perform well in determining COVID-19 in potential patients. NB and DT classifiers show the best performance with an accuracy of 93.70%, whereas other algorithms, such as SVM, KNN, and LR, demonstrate an accuracy of 93.60%, 93.50%, and 92.80% respectively. Hence, we determine that ML models have a significant role in detecting COVID-19 in patients based on their symptoms.

Highlights

The COVID-19 is a harmful and detrimental illness impacting the entire world
We analyze the performance of the Decision tree (DT), K-nearest neighbors (KNN), Naïve bayes (NB), Support vector machine (SVM), and Logistic regression (LR) to determine COVID-19 in the patients based on their symptoms
NB and DT classifiers show the best performance with an accuracy of 93.70%, whereas other algorithms, such as SVM, KNN, and LR, demonstrate an accuracy of 93.60%, 93.50%, and 92.80% respectively

Summary

Introduction

The COVID-19 is a harmful and detrimental illness impacting the entire world. The earliest cases were found in a city named Wuhan of China, in the last week of December 2019, followed by a rapid spread globally. Since the vaccines are not yet mature, other techniques like early detection of the disease can be effective to decrease the spread. Artificial intelligence (AI) approaches, including machine learning approaches [2] and deep learning algorithms [3], play an essential role in prediction for this disease like outbreak prediction [4,5], high-risk patients’ identification [6], COVID-19 analysis with clinical features [7], spread probability analysis [8], ways to combat this disease [9], and death risk in patients. Old-aged people, especially the ones with underlying illnesses like cardiovascular disorder, diabetes, persistent lung infection, and cancer are witnessed to be primarily harmed by this severe disease. There are signs that the demographics and profile of patients passing in China or one part of the world may not be equivalent to that in the other parts of the world, so it is valuable for individuals of any age to take extraordinary safety measures

Objectives

Results

Conclusion