Dataset Information

Predictive model based on gene and laboratory data for intravenous immunoglobulin resistance in Kawasaki disease in a Chinese population.

ABSTRACT:

Background

Here, we investigated the predictive efficiency of a newly developed model based on single nucleotide polymorphisms (SNPs) and laboratory data for intravenous immunoglobulin (IVIG) resistance in Kawasaki disease (KD) in a Chinese population.

Methods

Data relating to children with KD were acquired from a single center between December 2015 and August 2019 and used to screen target SNPs. We then developed a predictive model of IVIG resistance using previous laboratory parameters. We then validated our model using data acquired from children with KD attending a second center between January and December 2019.

Results

Analysis showed that rs10056474 GG, rs746994GG, rs76863441GT, rs16944 (CT/TT), and rs1143627 (CT/CC), increased the risk of IVIG-resistance in KD patients (odds ratio, OR > 1). The new predictive model, which combined SNP data with a previous model derived from laboratory data, significantly increased the area under the receiver-operator-characteristic curves (AUC) (0.832, 95% CI: 0.776-0.878 vs 0.793, 95%CI:0.734-0.844, P < 0.05) in the development dataset, and (0.820, 95% CI: 0.730-0.889 vs 0.749, 95% CI: 0.652-0.830, P < 0.05) in the validation dataset. The sensitivity and specificity of the new assay were 65.33% (95% CI: 53.5-76.0%) and 86.67% (95% CI: 80.2-91.7%) in the development dataset and 77.14% (95% CI: 59.9-89.6%) and 86.15% (95% CI: 75.3-93.5%) in the validation dataset.

Conclusion

Analysis showed that rs10056474 and rs746994 in the SMAD5 gene, rs76863441 in the PLA2G7 gene, and rs16944 or rs1143627 in the interleukin (IL)-1B gene, were associated with IVIG resistant KD in a Chinese population. The new model combined SNPs with laboratory data and improved the predictve efficiency of IVIG-resistant KD.

SUBMITTER: Meng L

PROVIDER: S-EPMC8236184 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundAbout 10-20% of Kawasaki disease (KD) patients are resistant to the initial infusion of intravenous immunoglobin (IVIG). The aim of this study was to assess whether IVIG resistance in KD patients could be predicted using standard clinical and laboratory features.MethodsData were from two cohorts: a Korean cohort of 7101 KD patients from 2015 to 2017 and a cohort of 649 KD patients from San Diego enrolled from 1998 to 2021. Features included laboratory values, the worst Z-score from the initial echocardiogram or during hospitalization, and the five clinical KD signs at presentation.ResultsFive machine learning models achieved a maximum median AUC of 0.711 [IQR: 0.706-0.72] in the Korean cohort and 0.696 [IQR: 0.609-0.722] in the San Diego cohort during stratified 10-fold cross-validation using significant laboratory features identified from univariate analysis. Adding the Z-score, KD clinical signs, or both did not considerably improve the median AUC in either cohort.ConclusionsUsing commonly measured clinical laboratory data alone or in conjunction with echocardiographic findings and clinical features is not sufficient to predict IVIG resistance. Further attempts to predict IVIG resistance will need to incorporate additional data such as transcriptomics, proteomics, and genetics to achieve meaningful predictive utility.ImpactWe demonstrated that laboratory, echocardiographic, and clinical findings cannot predict intravenous immunoglobin (IVIG) resistance to a clinically meaningful extent using machine learning in a homogenous Asian or ethnically diverse population of patients with Kawasaki disease (KD). Visualizing these features using uniform manifold approximation and projection (UMAP) is an important step to evaluate predictive utility in a qualitative manner. Further attempts to predict IVIG resistance in KD patients will need to incorporate novel biomarkers or other specialized features such as genetic differences or transcriptomics to be clinically useful.

Project description:BackgroundIntravenous immunoglobulin (IVIG) has been the mainstay of treatment for Kawasaki disease (KD) over the past decades. However, 10-20% of KD patients are resistant to IVIG treatment which puts those patients at high risk of coronary artery lesions (CALs). Therefore, it is important to predict whether patients will be resistant to IVIG before the treatment. This study aimed to investigate the risk factors for IVIG non-responsive patients with KD.MethodsThis study enrolled patients diagnosed with KD and divided them into two groups, IVIG responders and IVIG non-responders. We compared the differences in demographics and clinical data between the two groups. Differences among the groups were analyzed by ANOVA and Chi-square analysis. Predictors of IVIG resistance were determined by multiple logistic regression analysis and receiver operating characteristic (ROC) curve analysis.ResultsIn total, 907 KD patients were reviewed, with 841 IVIG responders and 66 IVIG non-responders. Patients in IVIG responders were younger than IVIG non-responders. The length of hospitalization of the IVIG non-responders was significantly longer than IVIG responders. The neutrophils%, C-reaction protein (CRP), and CRP/albumin ratio in IVIG responders were significantly lower than in IVIG non-responders (P < 0.05). The lymphocyte% and Albumin in IVIG responders were significantly higher than in IVIG non-responders. Multivariable logistic regression analysis demonstrated that albumin (OR = 0.881, 95% CI, 0.781 to 0.994, p-value = 0.039) was an independent risk factor for predicting IVIG resistance. The area under the ROC curve was 0.644, with a cut-off of ≤ 33.4 g/L determined by Youden's index. The sensitivity and specificity in predicting IVIG resistance were 40.91% and 83.47%, respectively.ConclusionAlbumin can serve as a potential predicting marker for IVIG resistance in KD. A lower albumin level may be useful for identifying KD patients with a high risk of IVIG resistance to guide further therapy strategies.

Project description:Background: The prediction of intravenous immunoglobulin (IVIG) resistance and cardiovascular complications are critically clinical issues in Kawasaki disease (KD). This prospective study firstly aimed to determine the predictive ability of the systemic immune inflammation index (SII) for IVIG resistance and cardiovascular complications and compare the prognostic accuracy of SII with that of neutrophil to lymphocyte ratio (NLR) and platelet to lymphocyte ratio (PLR). Methods: Patients with KD were divided into different groups according to the presence of IVIG resistance or cardiovascular complications (coronary artery lesions, valve regurgitation, myocarditis, pericardial effusion, and Kawasaki disease shock syndrome [KDSS]). The clinical and laboratory parameters were compared. Further analysis stratified by platelet level was performed. Multivariate logistic regression analysis was used to identify predictors for IVIG resistance and cardiovascular complications. The receiver operating characteristic (ROC) curve was applied to assess and compare the ability of SII, NLR, and PLR for predicting IVIG resistance and cardiovascular complications. Results: SII was significantly higher in KD patients with IVIG-resistance, myocarditis, valve regurgitation, and KDSS. It was identified as an independent risk factor for IVIG resistance, myocarditis, and valve regurgitation. For KD patients with thrombocytopenia, there were no significant differences in SII between KD patients with IVIG resistance/cardiovascular complications and those without. The best cutoff values of SII for IVIG resistance, myocarditis, valve regurgitation, and KDSS prediction in the whole cohort were 1331.4 × 109, 1368.6 × 109, 1002.4 × 109, and 1485.4 × 109, with a corresponding sensitivity of 0.525, 0.614, 0.754, and 0.670, a specificity of 0.711, 0.723, 0.584, and 0.730, respectively. The predictive value of SII for both IVIG resistance and cardiovascular complications were not superior to that of NLR. Conclusion: Although the parameter of SII may predict IVIG resistance, myocarditis, valve regurgitation, and KDSS in KD as a single parameter, its predictive ability was not good enough and not superior to NLR. SII might not be applicable in patients with KD having thrombocytopenia.

Project description:ObjectivesWe aimed to evaluate the clinical and laboratory characteristics of patients with Kawasaki disease (KD) before and after therapy.MethodsPatients with KD were divided into different groups according to their responsiveness to initial intravenous immunoglobulin (IVIG) treatment and coronary status. The clinical and laboratory parameters before and after therapy were compared. Multivariate analysis was performed to identify the independent risk factors, and the receiver operating characteristic (ROC) curve was applied to assess and compare the prediction ability of risk factors and their fluctuations.ResultsOf the 153 patients included in the study, 41 (26.8%) had IVIG resistance and 37 (24.2%) had developed CAA. After stratifying by therapy response, the two groups differed in the levels of total bilirubin (TSB), albumin, and sodium, neutrophil-to-lymphocyte count ratio (NLR), platelet-to-lymphocyte count ratio (PLR), TSB-to-albumin (B/A) ratio, and prognostic nutritional index (PNI) before IVIG, and in the white blood cell count (WBC), neutrophil count, levels of hemoglobin, C-reactive protein (CRP), alanine aminotransferase (ALT), and albumin, NLR, PNI, capillary leakage index (CLI), and systemic immune-inflammation index (SII) after IVIG. Multivariate analysis revealed that the B/A ratio before IVIG and CLI and SII after IVIG were significantly and positively associated with IVIG resistance and that there was a larger decline in the B/A ratio and smaller decline in CLI and SII pre- and post-treatment in the IVIG-resistant group than in the IVIG-responsive group. However, no statistical differences in the fluctuations of the B/A ratio, CLI, and SII as well as all parameters before and after therapy were observed in patients with and without CAA. ROC curve analyses found a greater AUC value of post-treatment parameters (0.751 and 0.706 for CLI and SII, respectively) compared with pre-treatment parameters (0.654 for B/A ratio) in predicting IVIG resistance; however, the predictive ability of the fluctuations in risk factors before and after therapy was not superior to that of baseline values.ConclusionsThe B/A ratio before IVIG and CLI and SII after IVIG were risk factors for IVIG resistance in patients with KD, independent of CAA development. Key Points • A high total bilirubin-to-albumin ratio before IVIG and high capillary leakage and systemic immune-inflammation indices after IVIG may indicate an increased risk of intravenous immunoglobulin resistance in patients with Kawasaki disease. • Post-treatment parameters were superior to pre-treatment parameters in terms of prediction; therefore, rapid and repeated assessment of risk factors before and after treatment must be considered in children in whom the vital signs and symptoms do not improve after treatment.