A simple scoring model based on machine learning predicts intravenous immunoglobulin resistance in Kawasaki disease.

INTRODUCTION: In Kawasaki disease (KD), accurate prediction of intravenous immunoglobulin (IVIG) resistance is crucial to reduce a risk for developing coronary artery lesions. OBJECTIVE: To establish a simple scoring model predicting IVIG resistance in KD patients based on the machine learning model. METHODS: A retrospective cohort study of 1002 KD patients diagnosed at 12 facilities for 10 years, in which 22.7% were resistant to initial IVIG treatment. We performed machine learning with diverse models using 30 clinical variables at diagnosis in 801 and 201 cases for training and test datasets, respectively. SHAP was applied to identify the variables that influenced the prediction model. A scoring model was designed using the influential clinical variables based on the Shapley additive explanation results. RESULTS: Light gradient boosting machine model accurately predicted IVIG resistance (area under the receiver operating characteristic curve (AUC), 0.78; sensitivity, 0.50; specificity, 0.88). Next, using top three influential features (days of illness at initial therapy, serum levels of C-reactive protein, and total cholesterol), we designed a simple scoring system. In spite of its simplicity, it predicted IVIG resistance (AUC, 0.72; sensitivity, 0.49; specificity, 0.82) as accurately as machine learning models. Moreover, accuracy of our scoring system with three clinical features was almost identical to that of Gunma score with seven clinical features (AUC, 0.73; sensitivity, 0.53; specificity, 0.83), a well-known logistic regression scoring model. CONCLUSION: A simple scoring system based on the findings in machine learning seems to be a useful tool to accurately predict IVIG resistance in KD patients.

Prevention Measures for COVID-19 and Changes in Kawasaki Disease Incidence.

BACKGROUND: Kawasaki disease is suspected to be triggered by previous infection. The prevention measures for coronavirus disease 2019 (COVID-19) have reportedly reduced transmission of certain infectious diseases. Under these circumstances, the prevention measures for COVID-19 may reduce the incidence of Kawasaki disease. METHODS: We conducted a retrospective study using registration datasets of patients with Kawasaki disease who were diagnosed in all 11 inpatient pediatric facilities in Yamanashi Prefecture. The eligible cases were 595 cases that were diagnosed before the COVID-19 pandemic (from January 2015 through February 2020) and 38 cases that were diagnosed during the COVID-19 pandemic (from March through November 2020). Incidence of several infectious disease were evaluated using data from the Infectious Disease Weekly Report conducted by the National Institute of Infectious Diseases. RESULTS: Epidemics of various infectious diseases generally remained at low levels during the first 9 months (March through November 2020) of the COVID-19 pandemic. Moreover, the incidence of COVID-19 was 50-80 times lower than the incidence in European countries and the United States. The total number of 38 cases with Kawasaki disease for the 9 months during the COVID-19 pandemic was 46.3% (-3.5 standard deviations [SDs] of the average [82.0; SD, 12.7 cases] for the corresponding 9 months of the previous 5 years. None of the 38 cases was determined to be triggered by COVID-19 based on their medical histories and negative results of severe acute respiratory syndrome coronavirus 2 testing at admission. CONCLUSION: These observations provide a new epidemiological evidence for the notion that Kawasaki disease is triggered by major infectious diseases in children.

Right Pulmonary Vein Atresia in a Mildly Symptomatic Boy: Comprehensive Analysis of Flow Dynamics Using Non-contrast-enhanced 4D Flow MR Imaging.

We present multimodal imaging in the rare case of isolated unilateral pulmonary vein atresia in a 6 year-old boy, including analysis of hemodynamics by magnetic resonance acquisition technique of time-resolved three-dimensional phase contrast imaging (4D flow magnetic resonance imaging). This novel imaging method enables the quantification and especially comprehensive visualization of blood flow patterns, even in complex congenital anomalies which abducted detailed assessment so far, and therefore constitutes a promising alternative to conventional vascular imaging techniques.

Characterization of biklf/klf17-deficient zebrafish in posterior lateral line neuromast and hatching gland development.

Krüpple-like factors (Klfs) are highly conserved zinc-finger transcription factors that regulate various developmental processes, such as haematopoiesis and cardiovascular development. In zebrafish, transient knockdown analysis of biklf/klf17 using antisense morpholino suggests the involvement of biklf/klf17 in primitive erythropoiesis and hatching gland development; however, the continuous physiological importance of klf17 remains uncharacterized under the genetic ablation of the klf17 gene among vertebrates. We established the klf17-disrupted zebrafish lines using the CRISPR/Cas9 technology and performed phenotypic analysis throughout early embryogenesis. We found that the klf17-deficient embryos exhibited abnormal lateral line neuromast deposition, whereas the production of primitive erythrocytes and haemoglobin production were observed in the klf17-deficient embryos. The expression of lateral line neuromast genes, klf17 and s100t, in the klf17-deficient embryos was detected in posterior lateral line neuromasts abnormally positioned at short intervals. Furthermore, the klf17-deficient embryos failed to hatch and died without hatching around 15 days post-fertilization (dpf), whereas the dechorionated klf17-deficient embryos and wild-type embryos were alive at 15 dpf. The klf17-deficient embryos abolished hatching gland cells and Ctsl1b protein expression, and eliminated the expression of polster and hatching gland marker genes, he1.1, ctsl1b and cd63. Thus, the klf17 gene plays important roles in posterior lateral line neuromast and hatching gland development.

Plasma Exchange Downregulates Activated Monocytes and Restores Regulatory T Cells in Kawasaki Disease.

In Kawasaki disease (KD), the effect of plasma exchange (PE) on immune cells has not been fully elucidated. Therefore, we examined the changes in the number of CD14+ CD16+ activated monocytes, regulatory T (Treg ), and T-helper type 17 (Th17) cells in KD patients treated with PE. The percentage of total monocytes and subclasses of lymphocytes, including CD4+ and CD8+ T cells, and CD19+ B cells, showed no significant difference before and after PE. However, the percentage of CD14+ CD16+ monocytes in total leukocytes decreased significantly after PE (1.1% ± 1.5% vs. 2.1% ± 2.3%, P < 0.05). Furthermore, while the percentage of Th17 cells in CD4+ T cells did not change, the percentage of Treg cells in CD4+ T cells increased significantly after PE (11.1% ± 5.1% vs. 8.0% ± 4.4%, P < 0.05). Therefore, PE downregulates activated monocytes and upregulates Treg cells toward normal levels and thus attenuates inflammation in KD.

Infliximab regulates monocytes and regulatory T cells in Kawasaki disease.

BACKGROUND: The effect of infliximab (IFX) on immune cells has not been fully reported in Kawasaki disease (KD). To investigate the mechanism of IFX in KD, we examined changes in the abundance of CD14+ CD16+ activated monocytes, regulatory T cells (Treg ) cells, and T-helper type 17 (Th17) cells following treatment with IFX. METHODS: We collected peripheral blood from patients with i.v. immunoglobulin (IVIG)-resistant KD and analyzed absolute CD14+ CD16+ monocyte, Treg (CD4+ CD25+ FOXP3+ ) and Th17 cell (CD4+ IL-17A+ ) counts on flow cytometry. We also measured changes in serum soluble interleukin (IL)-2 receptor (IL-2R), IL-6, and tumor necrosis factor (TNF)-α on enzyme-linked immunosorbent assay. RESULTS: Treg cells and Th17 cells significantly increased after IFX treatment compared with baseline (126 ± 85 cells/µL vs 62 ± 53 cells/µL, P < 0.01; 100 ± 111 cells/µL vs 28 ± 27 cells/µL, P < 0.05, respectively). In contrast, in a subgroup of patients with CD14+ CD16+ monocytes above the normal range before IFX, the CD14+ CD16+ monocytes significantly decreased following IFX treatment (72 ± 51 cells/µL vs 242 ± 156 cells/µL, P < 0.05).. Serum TNF-α did not change, but soluble IL-2R and IL-6 decreased after IFX treatment. CONCLUSION: IFX could downregulate activated monocytes and upregulate Treg cells towards the normal range. IFX treatment thus contributes to the process of attenuating inflammation in KD.