A universal model for predicting coronary artery lesions in subgroups of kawasaki disease in China: based on cluster analysis

Bibliographic Details
Title: A universal model for predicting coronary artery lesions in subgroups of kawasaki disease in China: based on cluster analysis
Authors: Chuxiong Gong, Feng Li, Zhongjian Su, Yanan Fu, Xing Zhang, Qinhong Li, Xiaomei Liu, Lili Deng
Source: Frontiers in Cardiovascular Medicine, Vol 12 (2025)
Publisher Information: Frontiers Media S.A., 2025.
Publication Year: 2025
Collection: LCC:Diseases of the circulatory (Cardiovascular) system
Subject Terms: kawasaki disease, cluster analysis, coronary artery lesions, cardiovascular diseases, children's diseases, Diseases of the circulatory (Cardiovascular) system, RC666-701
More Details: ObjectiveCoronary artery lesions (CAL) represent the most severe complication of Kawasaki disease (KD). Currently, there is no standardized method for predicting CAL in KD, and the predictive effectiveness varies among different KD patients. Therefore, our study aims to establish distinct predictive models for CAL complications based on the characteristics of different clusters.MethodsWe employed principal component clustering analysis to categorize 1,795 KD patients into different clustered subgroups. We summarized the characteristics of each cluster and compared the occurrence of CAL components within each cluster. Additionally, we utilized LASSO analysis to further screen for factors associated with CAL. We then constructed CAL predictive models for each subgroup using the selected factors and conducted preliminary validation and assessment.ResultsThrough PCA analysis, we identified three clusters in KD. We developed predictive models for each of the three clusters. The AUCs of the three predictive models were 0.789 (95% CI: 0.732–0.845), 0.894 (95% CI: 0.856–0.932), and 0.773 (95% CI: 0.727–0.819), respectively, all demonstrating good predictive performance.ConclusionOur study identified the existence of three clusters among KD patients. We developed KD-related CAL predictive models with good predictive performance for each cluster with distinct characteristics. This provides reference for individualized precision treatment of KD patients and aids in the health management of coronary arteries in KD.
Document Type: article
File Description: electronic resource
Language: English
ISSN: 2297-055X
Relation: https://www.frontiersin.org/articles/10.3389/fcvm.2025.1532768/full; https://doaj.org/toc/2297-055X
DOI: 10.3389/fcvm.2025.1532768
Access URL: https://doaj.org/article/77cd22e2dd234fcea5ffbe7085697378
Accession Number: edsdoj.77cd22e2dd234fcea5ffbe7085697378
Database: Directory of Open Access Journals
More Details
ISSN:2297055X
DOI:10.3389/fcvm.2025.1532768
Published in:Frontiers in Cardiovascular Medicine
Language:English