Accurate detection of Covid-19 patients based on Feature Correlated Naïve Bayes (FCNB) classification strategy

Abstract

The outbreak of Coronavirus (COVID-19) has spread between people around the world at a rapid rate so that the number of infected people and deaths is increasing quickly every day. Accordingly, it is a vital process to detect positive cases at an early stage for treatment and controlling the disease from spreading. Several medical tests had been applied for COVID-19 detection in certain injuries, but with limited efficiency. In this study, a new COVID-19 diagnosis strategy called Feature Correlated Naïve Bayes (FCNB) has been introduced. The FCNB consists of four phases, which are; Feature Selection Phase (FSP), Feature Clustering Phase (FCP), Master Feature Weighting Phase (MFWP), and Feature Correlated Naïve Bayes Phase (FCNBP). The FSP selects only the most effective features among the extracted features from laboratory tests for both COVID-19 patients and non-COVID-19 people by using the Genetic Algorithm as a wrapper method. The FCP constructs many clusters of features based on the selected features from FSP by using a novel clustering technique. These clusters of features are called Master Features (MFs) in which each MF contains a set of dependent features. The MFWP assigns a weight value to each MF by using a new weight calculation method. The FCNBP is used to classify patients based on the weighted Naïve Bayes algorithm with many modifications as the correlation between features. The proposed FCNB strategy has been compared to recent competitive techniques. Experimental results have proven the effectiveness of the FCNB strategy in which it outperforms recent competitive techniques because it achieves the maximum (99%) detection accuracy.

Keywords: COVID-19; Classification; Correlation; FCNB; Feature selection.

Fig. 1

COVID-19 epidemic curve with and without protective measures

Fig. 2

Different COVID-19 diagnosis techniques

Fig. 3

The proposed FCNB classification strategy

Fig. 4

The steps of FSGA implementation

Fig. 5

The followed steps for the first iteration of FSGA

Fig. 6

The followed steps for the second iteration of FSGA

Fig. 7

The main steps for clustering the features to construct Master Features

Fig. 8

The initial construction of the clusters

Fig. 9

The steps of assigning each isolated feature to its nearest cluster or to a new dummy cluster

Fig. 10

The steps of implementing the proposed feature correlation methodology

Fig. 11

The total number of cases according to age

Fig. 12

The total number of COVID-19 cases according to age and gender

Fig. 13

The presentation of COVID-19 cases and un COVID-19 cases distribution

Fig. 14

Accuracy of different feature selection techniques

Fig. 15

Error of different feature selection techniques

Fig. 16

Precision of different feature selection techniques

Fig. 17

Recall of different feature selection techniques

Fig. 18

Macro-average precision of different feature selection techniques

Fig. 19

Macro-average recall of different feature selection techniques

Fig. 20

Micro-average precision of different feature selection techniques

Fig. 21

Micro-average recall of different feature selection techniques

Fig. 22

F-measure of different feature selection techniques

Fig. 23

Run time of different feature selection techniques

Fig. 24

Accuracy of different COVID-19 classification techniques\

Fig. 25

Error of different COVID-19 classification techniques

Fig. 26

Precision of different COVID-19 classification techniques

Fig. 27

Recall of different COVID-19 classification techniques

Fig. 28

Macro-average for precision of different COVID-19 classification techniques

Fig. 29

Macro-average for recall of different COVID-19 classification techniques

Fig. 30

Micro-average precision of different COVID-19 classification techniques

Fig. 31

Micro-average recall of different COVID-19 classification techniques

Fig. 32

F-measure of different COVID-19 classification techniques

Fig. 33

Run time of the different classification techniques