Distinguishing Kawasaki Disease from Febrile Infectious Disease Using Gene Pair Signatures

Abstract

Kawasaki disease (KD) is an acute systemic vasculitis of childhood with prolonged fever, and the diagnosis of KD is mainly based on clinical criteria, which is prone to misdiagnosis with other febrile infectious (FI) diseases. Currently, there remain no effective molecular markers for KD diagnosis. In this study, we aimed to use a relative-expression-based method k-TSP and resampling framework to identify robust gene pair signatures to distinguish KD from bacterial and virus febrile infectious diseases. Our study pool consisted of 808 childhood patients from several studies and assigned to three groups, namely, the discovery set (n = 224), validation set-1 (n = 197), and validation set-2 (n = 387). We had identified 60 biologically relevant gene pairs and developed a top-ranked gene pair classifier (TRGP) using the first seven signatures, with the area under the receiver-operating characteristic curves (AUROC) of 0.947 (95% CI, 0.918-0.976), a sensitivity of 0.936 (95% CI, 0.872-0.987), and a specificity of 0.774 (95% CI, 0.705-0.836) in the discovery set. In the validation set-1, the TRGP classifier distinguished KD from FI with AUROC of 0.955 (95% CI, 0.919-0.991), a sensitivity of 0.959 (95% CI, 0.925-0.986), and a specificity of 0.863 (95% CI, 0.764-0.961). In the validation set-2, the predictive performance of classification was with an AUROC of 0.796 (95% CI, 0.747-0.845), a sensitivity of 0.797 (95% CI, 0.720-0.864), and a specificity of 0.661 (95% CI, 0.606-0.717). Our study reveals that gene pair signatures are robust across diverse studies and can be utilized as objective biomarkers to distinguish KD from FI, helping to develop a fast, simple, and effective molecular approach to improve the diagnosis of KD.

Figure 1

The workflow of the gene pair identification and evaluation for the KD and FI prediction. The workflow has four major analysis steps. (a) Resampling sample space of the discovery set by 10,000 times. Each resampled discovery set is divided into the train data and the test data in a ratio of 8 : 2. (b) Identification of top score gene pairs. (c) Ranking the repeats of the gene pairs form 10,000 k-TSP classifiers. (d) The prediction classifier of KD and FI by the top-ranked gene pairs and validation.

Figure 2

The 60 top-ranked gene pairs. (a) The repetition rate and mean scores of gene pairs in 10,000 resampled train data. Each point represents a gene pair, the red line is the threshold line with a repetition rate of 0.1, and we take a repetition rate greater than 0.1 as the top-ranked gene pairs. (b) Unsupervised t-SNE classification of the discovery set was performed using 60 top-ranked gene pairs. (c) The overlap of differentially expressed genes (KD vs. FI in the discovery set) with 60 top-ranked gene pairs, and Gene i (red triangle) and Gene j (green square) represent the genes to the left and the right of gene pairs, respectively.

Figure 3

The AUROC and balanced accuracy of number features in a k-TSP classifier selected from the 60 top-ranked gene pairs in the discovery set. We selected gene pairs from 1 to 60 to develop the TRGP classifier and found that the TRGP classifier with seven of the top gene pairs (dotted line) optimally achieved the best AUROC and balanced accuracy performance.

Figure 4

Prediction performance of the TRGP classifier using the seven top-ranked gene pairs. (a) The ROC curve, (b) the prediction confusion matrix, and (c) the classification scores of FI and KD patients in the discovery set (black), validation set-1 (red), and external validation set-2 (blue). In box plots (c), the horizontal lines, box edges, and whiskers represent the median, interquartile ranges, and 95% percentile range, respectively. The dotted line represents the threshold of classification, and the classification scores > 0 are predicted to be KD, otherwise FI. AUROC: area under the receiver-operating characteristic curve. A two-tailed unpaired Student's t-test was used for statistical comparison of classification scores between FI and KD patients. ^∗P < 0.05,^∗∗P < 0.01,^∗∗∗P < 0.001, and^∗∗∗∗P < 0.0001.