Dataset Information

Plasma clusterin concentrations may predict resistance to intravenous immunoglobulin in patients with Kawasaki disease.

ABSTRACT: Kawasaki disease (KD) is an acute febrile vasculitic syndrome of early childhood often complicated by coronary artery lesion that drastically reduces the quality of life. The study aimed to identify a reliable marker for predicting nonresponsiveness to the first course of intravenous immunoglobulin (IVIG) in KD patients. A total of 63 patients with KD were enrolled in the study (IVIG response, 58; IVIG resistance, 5). Plasma samples were collected before and after IVIG infusion for measurement of biomarkers. Patients' clinical characteristics and laboratory data were also analyzed. A receiver operating characteristic curve was generated to identify a cut-off value for predicting IVIG resistance. Among the biomarkers, the difference in plasma clusterin concentrations before and after IVIG infusion (CLUSTER 12) was significantly related to IVIG resistance (P = 0.040; 95% confidence interval (CI): -25.8% to -6.0%). Using a CLUSTER 12 cut-off value of <8.52 mg/L, the odds ratio for IVIG resistance was 11.467 (95% CI: 1.186 to 110.853). Patients with plasma CLUSTER 12 concentrations >8.52 mg/L had a much higher risk of IVIG resistance than those with CLUSTER 12 concentrations <8.52 mg/L. Plasma clusterin concentration shows promise as a candidate biomarker for predicting IVIG resistance in patients with KD.

SUBMITTER: Ou-Yang MC

PROVIDER: S-EPMC3727184 | biostudies-other | 2013

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Plasma clusterin concentrations may predict resistance to intravenous immunoglobulin in patients with Kawasaki disease.

Ou-Yang Mei-Chen MC Kuo Ho-Chang HC Lin I-Chun IC Sheen Jiunn-Ming JM Huang Fu-Chen FC Chen Chih-Cheng CC Huang Ying-Hsien YH Lin Ying-Jui YJ Yu Hong-Ren HR

TheScientificWorldJournal 20130715

Kawasaki disease (KD) is an acute febrile vasculitic syndrome of early childhood often complicated by coronary artery lesion that drastically reduces the quality of life. The study aimed to identify a reliable marker for predicting nonresponsiveness to the first course of intravenous immunoglobulin (IVIG) in KD patients. A total of 63 patients with KD were enrolled in the study (IVIG response, 58; IVIG resistance, 5). Plasma samples were collected before and after IVIG infusion for measurement o ...[more]

PMID: 23956692

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: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, AdaBoost, 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.

Project description:ObjectiveWe aimed to develop a nomogram to predict risk of resistance to intravenous immunoglobulin (IVIG) in children with Kawasaki disease in eastern China.MethodsWe retrospectively analysed the data of children with Kawasaki disease who received IVIG during hospitalisation at Soochow University Affiliated Children's Hospital. IVIG resistance was defined as recrudescent or persistent fever ≥36 h after the end of the IVIG infusion. Baseline variables were analysed using least absolute shrinkage and selection operator (LASSO) to identify the predictors of IVIG resistance, which were then used to construct a predictive nomogram. Calibration curve and area under the receiver operating characteristic curve (AUC) were used to evaluate the performance of the model. The predictive nomogram was validated on test sets of external data and prospective data.ResultsBetween January 2015 and December 2020, 1293 Kawasaki disease patients were hospitalized in Soochow University Affiliated Children's Hospital. Among them, 72 (5.57%) showed IVIG resistance. LASSO identified haemoglobin, percentage of neutrophils, C-reactive protein level, platelet count, serum albumin, serum sodium, serum alkaline phosphatase, coronary artery damage, and complete Kawasaki disease as risk factors for IVIG resistance. The nomogram constructed using these factors showed satisfactory discriminatory power (AUC, 0.75), and sensitivity (0.74) and specificity (0.64). In the external data and prospective data, the AUC was 0.66 and 0.83, respectively, the sensitivity was 0.86 and 1, respectively, and the specificity was 0.49 and 0.60, respectively.ConclusionsThe predictive nomogram constructed using nine factors associated with IVIG resistance in children with Kawasaki disease could be a useful tool for identifying patients likely to show IVIG resistance. This nomogram may help reduce the risk of coronary artery lesions.Key MessagesNone of the IVIG resistance scoring systems has shown consistently good performance in previous studies. Tools to predict the risk of IVIG resistance in eastern China are lacking.In our series, haemoglobin level, percentage of neutrophils, platelet count, coronary artery damage, incomplete Kawasaki disease, and CRP, serum albumin, serum sodium, and serum alkaline phosphatase levels were risk factors of IVIG resistance in hospitalized children in the eastern China cities of Suzhou and Fuzhou.We propose an easy-to-use nomogram to predict the risk factors of IVIG resistance in hospitalized children.

Dataset Information

Plasma clusterin concentrations may predict resistance to intravenous immunoglobulin in patients with Kawasaki disease.

Publications

Plasma clusterin concentrations may predict resistance to intravenous immunoglobulin in patients with Kawasaki disease.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets