A machine learning-based model to predict intravenous immunoglobulin resistance in Kawasaki disease

Summary: Accurate prediction of intravenous immunoglobulin (IVIG) resistance is crucial for the effective treatment of Kawasaki disease(KD). This study aimed to develop a predictive model for IVIG resistance in patients with Kawasaki disease and to identify the key predictors. The training set under...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuhan Xia, Yuezhong Huang, Min Gong, Weirong Liu, Yuanhui Meng, Huiyang Wu, Hui Zhang, Hao Zhang, Luyi Weng, Xiao-Li Chen, Huixian Qiu, Xing Rong, Rongzhou Wu, Maoping Chu, Xiu-Feng Huang
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:iScience
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2589004225002640
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204983934320640
author Yuhan Xia
Yuezhong Huang
Min Gong
Weirong Liu
Yuanhui Meng
Huiyang Wu
Hui Zhang
Hao Zhang
Luyi Weng
Xiao-Li Chen
Huixian Qiu
Xing Rong
Rongzhou Wu
Maoping Chu
Xiu-Feng Huang
author_facet Yuhan Xia
Yuezhong Huang
Min Gong
Weirong Liu
Yuanhui Meng
Huiyang Wu
Hui Zhang
Hao Zhang
Luyi Weng
Xiao-Li Chen
Huixian Qiu
Xing Rong
Rongzhou Wu
Maoping Chu
Xiu-Feng Huang
author_sort Yuhan Xia
collection DOAJ
description Summary: Accurate prediction of intravenous immunoglobulin (IVIG) resistance is crucial for the effective treatment of Kawasaki disease(KD). This study aimed to develop a predictive model for IVIG resistance in patients with Kawasaki disease and to identify the key predictors. The training set underwent cross-validation, and models were constructed using six machine learning algorithms. Model performance was validated through cross-validation, test set evaluation, and two external validation sets evaluation. The model constructed using the random forest algorithm demonstrated the best overall performance among six models. The areas under the receiver operating characteristic curve (AUCs) for 5-fold cross-validation, internal validation, and external validations from Shaoxing and Quzhou were 0.711, 0.751, 0.827, and 0.735, respectively. According to the Shapley additive explanation (SHAP) method, C-reactive protein-to-albumin ratio, prognostic nutritional index, and sex were identified as the most important predictors. Our model demonstrates strong predictive capability for assessing IVIG resistance in Kawasaki disease patients.
format Article
id doaj-art-d3563adb28bb423ca9f64865da8a4f34
institution OA Journals
issn 2589-0042
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series iScience
spelling doaj-art-d3563adb28bb423ca9f64865da8a4f342025-08-20T02:11:11ZengElsevieriScience2589-00422025-03-0128311200410.1016/j.isci.2025.112004A machine learning-based model to predict intravenous immunoglobulin resistance in Kawasaki diseaseYuhan Xia0Yuezhong Huang1Min Gong2Weirong Liu3Yuanhui Meng4Huiyang Wu5Hui Zhang6Hao Zhang7Luyi Weng8Xiao-Li Chen9Huixian Qiu10Xing Rong11Rongzhou Wu12Maoping Chu13Xiu-Feng Huang14Zhejiang Provincial Clinical Research Center for Pediatric Precision Medicine, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, China; Pediatrics Discipline Group, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, China; Children’s Heart Center, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, ChinaZhejiang Provincial Clinical Research Center for Pediatric Precision Medicine, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, China; Pediatrics Discipline Group, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, ChinaDepartment of Pediatrics, People’s Hospital of Quzhou, Quzhou, Zhejiang, ChinaDepartment of Pediatrics, People’s Hospital of Shaoxing, Shaoxing, ChinaChildren’s Heart Center, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, ChinaChildren’s Heart Center, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, ChinaChildren’s Heart Center, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, ChinaChildren’s Heart Center, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, ChinaChildren’s Heart Center, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, ChinaZhejiang Provincial Clinical Research Center for Pediatric Precision Medicine, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, China; Pediatrics Discipline Group, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, ChinaChildren’s Heart Center, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, ChinaChildren’s Heart Center, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, ChinaChildren’s Heart Center, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, ChinaZhejiang Provincial Clinical Research Center for Pediatric Precision Medicine, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, China; Pediatrics Discipline Group, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, China; Children’s Heart Center, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, China; Corresponding authorZhejiang Provincial Clinical Research Center for Pediatric Precision Medicine, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, China; Pediatrics Discipline Group, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, China; Corresponding authorSummary: Accurate prediction of intravenous immunoglobulin (IVIG) resistance is crucial for the effective treatment of Kawasaki disease(KD). This study aimed to develop a predictive model for IVIG resistance in patients with Kawasaki disease and to identify the key predictors. The training set underwent cross-validation, and models were constructed using six machine learning algorithms. Model performance was validated through cross-validation, test set evaluation, and two external validation sets evaluation. The model constructed using the random forest algorithm demonstrated the best overall performance among six models. The areas under the receiver operating characteristic curve (AUCs) for 5-fold cross-validation, internal validation, and external validations from Shaoxing and Quzhou were 0.711, 0.751, 0.827, and 0.735, respectively. According to the Shapley additive explanation (SHAP) method, C-reactive protein-to-albumin ratio, prognostic nutritional index, and sex were identified as the most important predictors. Our model demonstrates strong predictive capability for assessing IVIG resistance in Kawasaki disease patients.http://www.sciencedirect.com/science/article/pii/S2589004225002640Cardiovascular medicineMachine learning
spellingShingle Yuhan Xia
Yuezhong Huang
Min Gong
Weirong Liu
Yuanhui Meng
Huiyang Wu
Hui Zhang
Hao Zhang
Luyi Weng
Xiao-Li Chen
Huixian Qiu
Xing Rong
Rongzhou Wu
Maoping Chu
Xiu-Feng Huang
A machine learning-based model to predict intravenous immunoglobulin resistance in Kawasaki disease
iScience
Cardiovascular medicine
Machine learning
title A machine learning-based model to predict intravenous immunoglobulin resistance in Kawasaki disease
title_full A machine learning-based model to predict intravenous immunoglobulin resistance in Kawasaki disease
title_fullStr A machine learning-based model to predict intravenous immunoglobulin resistance in Kawasaki disease
title_full_unstemmed A machine learning-based model to predict intravenous immunoglobulin resistance in Kawasaki disease
title_short A machine learning-based model to predict intravenous immunoglobulin resistance in Kawasaki disease
title_sort machine learning based model to predict intravenous immunoglobulin resistance in kawasaki disease
topic Cardiovascular medicine
Machine learning
url http://www.sciencedirect.com/science/article/pii/S2589004225002640
work_keys_str_mv AT yuhanxia amachinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT yuezhonghuang amachinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT mingong amachinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT weirongliu amachinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT yuanhuimeng amachinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT huiyangwu amachinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT huizhang amachinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT haozhang amachinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT luyiweng amachinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT xiaolichen amachinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT huixianqiu amachinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT xingrong amachinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT rongzhouwu amachinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT maopingchu amachinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT xiufenghuang amachinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT yuhanxia machinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT yuezhonghuang machinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT mingong machinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT weirongliu machinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT yuanhuimeng machinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT huiyangwu machinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT huizhang machinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT haozhang machinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT luyiweng machinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT xiaolichen machinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT huixianqiu machinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT xingrong machinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT rongzhouwu machinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT maopingchu machinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease
AT xiufenghuang machinelearningbasedmodeltopredictintravenousimmunoglobulinresistanceinkawasakidisease