Clinical and Laboratory Approach to Diagnose COVID-19 Using Machine Learning

Abstract

Coronavirus 2 (SARS-CoV-2), often known by the name COVID-19, is a type of acute respiratory syndrome that has had a significant influence on both economy and health infrastructure worldwide. This novel virus is diagnosed utilising a conventional method known as the RT-PCR (Reverse Transcription Polymerase Chain Reaction) test. This approach, however, produces a lot of false-negative and erroneous outcomes. According to recent studies, COVID-19 can also be diagnosed using X-rays, CT scans, blood tests and cough sounds. In this article, we use blood tests and machine learning to predict the diagnosis of this deadly virus. We also present an extensive review of various existing machine-learning applications that diagnose COVID-19 from clinical and laboratory markers. Four different classifiers along with a technique called Synthetic Minority Oversampling Technique (SMOTE) were used for classification. Shapley Additive Explanations (SHAP) method was utilized to calculate the gravity of each feature and it was found that eosinophils, monocytes, leukocytes and platelets were the most critical blood parameters that distinguished COVID-19 infection for our dataset. These classifiers can be utilized in conjunction with RT-PCR tests to improve sensitivity and in emergency situations such as a pandemic outbreak that might happen due to new strains of the virus. The positive results indicate the prospective use of an automated framework that could help clinicians and medical personnel diagnose and screen patients.

Keywords: Artificial Intelligence; Blood tests; COVID-19; Machine Learning; RT-PCR.

Fig. 1

Integral learning steps required for the development of ML classifiers

Fig. 2

Null values present in attributes

Fig. 3

Pearson co-relation matrix

Fig. 4

An example of synthetic sampling by SMOTE overall flow diagram is given below [34]

Fig. 5

Block diagram describing the proposed method for the classification of COVID-19 based on blood sample data

Fig. 6

AUROC curves of the various ML algorithms as follows: a Initial RF model; b RF model after pre-processing; c RF model after hyperparameter tuning; d Model after SMOTE Analysis; e Optimized RF model; f Logistic Regression; g KNN; h XGBoost

Fig. 7

Feature importance using SHAP

Fig. 8

Feature importance using random forest

Fig. 9

Marginal effect of Leukocytes, Monocytes and Platelets on COVID-19 outcome