Kawasaki disease is the leading cause of pediatric acquired heart disease. Coronary artery abnormalities are the main complication of Kawasaki disease. Kawasaki disease patients with intravenous immunoglobulin resistance are at a greater risk of developing coronary artery abnormalities. Several scoring models have been established to predict resistance to intravenous immunoglobulin, but clinicians usually do not apply those models in patients because of their poor performance. To find a better model, we retrospectively collected data including 753 observations and 82 variables. A total of 644 observations were included in the analysis, and 124 of the patients observed were intravenous immunoglobulin resistant (19.25%). We considered 7 different linear and nonlinear machine learning algorithms, including logistic regression (L1 and L1 regularized), decision tree, random forest, Ada-Boost, gradient boosting machine (GBM), and lightGBM, to predict the class of intravenous immunoglobulin resistance (binary classification). Data from patients who were discharged before Sep 2018 were included in the training set (n = 497), while all the data collected after 9/1/2018 were included in the test set (n = 147). We used the area under the ROC curve, accuracy, sensitivity, and specificity to evaluate the performances of each model. The gradient GBM had the best performance (area under the ROC curve 0.7423, accuracy 0.8844, sensitivity 0.3043, specificity 0.9919). Additionally, the feature importance was evaluated with SHapley Additive exPlanation (SHAP) values, and the clinical utility was assessed with decision curve analysis. We also compared our model with the Kobayashi score, Egami score, Formosa score and Kawamura score. Our machine learning model outperformed all of the aforementioned four scoring models. Our study demonstrates a novel and robust machine learning method to predict intravenous immunoglobulin resistance in Kawasaki disease patients. We believe this approach could be implemented in an electronic health record system as a form of clinical decision support in the near future.
Exploring the role of neuropeptides in the communication between monocyte subtypes facilitates an investigation of the pathogenesis of Kawasaki disease (KD). We investigated the patterns of interaction between neuropeptide-associated ligands and receptors in monocyte subpopulations in KD patients. Single-cell analysis was employed for the identification of cell subpopulations in KD patients, and monocytes were classified into 3 subpopulations: classical monocytes (CMs), intermediate monocytes (IMs), and nonclassical monocytes (NCMs). Cell-cell communication and differential analyses were used to identify ligand-receptor interactions in monocytes. Five neuropeptide-related genes (SORL1, TNF, SORT1, FPR2, and ANXA1) were involved in cell-cell interactions, wherein FPR2, a neuropeptide receptor, was significantly highly expressed in KD. Weighted gene coexpression network analysis revealed a significant correlation between the yellow module and FPR2 (
p
<
0.001
,
CC
=
0.43
). Using the genes in the yellow module, we constructed a PPI network to assess the possible functions of the FPR2-associated gene network. Gene set enrichment analysis showed that increased FPR2 levels may be involved in immune system regulation. FPR2 in CMs mediates the control of inflammation in KD. The findings of this study may provide a novel target for the clinical treatment of KD.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.