Importance of combining laboratory parameters and RAT in diagnosing COVID-19 patients
Considering the intermediate diagnostic power (AUC = 0.7)(Figure 2 A) and low diagnostic performance of the RAT(Tables 2 and 3) , we investigated whether combining laboratory indices measured in blood and RAT would enhance the true identification of COVID-19 patients by the RAT. First, the SVM model revealed that HB, urea, RAT and S. ferritin were the top-4 parameters most frequently selected during the model building and cross validation followed by the other features (Figure 2 B). Various combination between these parameters (i.e. those listed in ascending order in Figure 2 B ) yielded various accuracies in predicting true COVID-19 cases. The highest prediction accuracy (59.3%) was obtained when combining RAT with both HB and urea (top 2- features inFigure 2 B). Coupling RAT with HB, urea, S. ferritin and CRP (top 5- ranked features) yielded slightly lower prediction accuracy (58%) than the one produced by the 3-feature model. Combining all features together revealed low prediction accuracy of 48%. Subsequent evaluation of the “top 3-feature” model by predictive class probability analyses (Figure 2 D) revealed a sensitivity of 75.4%, where this model correctly identified 43 as positive subjects out of the 57 true positive ones (as determined by RT-qPCR). The model specificity was 81.8%, where the model correctly identified nine negative subjects out of the 11 true negative ones. The misclassified subjects are labelled in figure 2 D .