Predicting coronary artery lesions in patients with Kawasaki disease in China using a machine-learning algorithm: a retrospective cohort study
Open Access
- 22 April 2026
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Immunology
- Vol. 17, 1807028
Abstract
Background: This study aimed to analyze the risk factors of coronary artery lesions (CAL) in patients with Kawasaki disease (KD) and establish predictive models for CAL in patients with KD. Methods: This retrospective cohort study included KD patients admitted to Shengjing Hospital of China Medical University, collecting data on 41 demographic, clinical, and laboratory parameters. LASSO regression identified key predictive variables. The dataset was split into 70% training and 30% validation. Ten models were trained using 10-fold cross-validation, with the training set balanced through ROSE oversampling. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. Results: The CatBoost algorithm achieved the best results: AUC, 0.953; sensitivity, 0.908; specificity, 0.860; and accuracy, 0.883. Internal validation results were as follows: AUC, 0.874; sensitivity, 0.721; specificity, 0.848; accuracy, 0.837. External validation results were as follows: AUC, 0.876.sensitivity, 0.894; specificity, 0.954. Conclusions: We present a machine-learning model that predicts the risk of CAL in patients with KD in China, aiding doctors in creating personalized treatment strategies to improve outcomes.Keywords
This publication has 31 references indexed in Scilit:
- Risk factors associated with persistent coronary artery lesions in children with Kawasaki disease in an Italian cohortEuropean Journal of Pediatrics, 2025
- Nutrition‐Associated Biomarkers in Predicting Intravenous Immunoglobulin Resistance and Coronary Artery Lesions in Kawasaki Disease: A Systematic Review and Meta‐AnalysisFood Science & Nutrition, 2024
- Methylprednisolone pulse and prednisolone for intensification of primary treatment in Kawasaki disease patients at high risk of treatment resistance: a multicenter prospective cohort studyEuropean Journal of Pediatrics, 2024
- A Review of Machine Learning Algorithms for Biomedical ApplicationsAnnals of Biomedical Engineering, 2024
- Age-Dependent Variations in Kawasaki Disease Incidence in JapanJAMA Network Open, 2024
- Association between aspirin dose and outcomes in patients with acute Kawasaki disease: a nationwide retrospective cohort study in JapanEuropean Journal of Pediatrics, 2023
- Subgroups of children with Kawasaki disease: a data-driven cluster analysisThe Lancet Child & Adolescent Health, 2023
- Use of Machine Learning to Differentiate Children With Kawasaki Disease From Other Febrile Children in a Pediatric Emergency DepartmentJAMA Network Open, 2023
- Epidemiology, clinical characteristics, and immediate outcome of Kawasaki disease: a population-based study from a tropical countryEuropean Journal of Pediatrics, 2021
- Kawasaki Disease: an UpdateCurrent Rheumatology Reports, 2020