A retrospective cohort study using machine learning to predict coronary artery lesions in children with Kawasaki disease

Abstract Background Kawasaki disease (KD) mainly occurs in children under 5 years old, and the most common complication of KD is coronary artery lesion (CAL). In recent years, the incidence rate of KD has increased year by year worldwide, so it is particularly important to strengthen the diagnosis o...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanan Duan, Aiping Chen, Xuedi Cheng
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BMC Pediatrics
Subjects:
Online Access:https://doi.org/10.1186/s12887-025-05917-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849332212018708480
author Yanan Duan
Aiping Chen
Xuedi Cheng
author_facet Yanan Duan
Aiping Chen
Xuedi Cheng
author_sort Yanan Duan
collection DOAJ
description Abstract Background Kawasaki disease (KD) mainly occurs in children under 5 years old, and the most common complication of KD is coronary artery lesion (CAL). In recent years, the incidence rate of KD has increased year by year worldwide, so it is particularly important to strengthen the diagnosis of KD and identify CAL early. Method This retrospective cohort study included a total of 436 children diagnosed with Kawasaki disease and aimed to develop a predictive model for CAL using early clinical symptoms and laboratory features. To reduce potential confounding, propensity score matching (PSM) was applied, and both univariate and multivariate analyses were conducted to identify significant predictors of CAL. Subsequently, through machine learning, a predictive column chart model was constructed using clinical features and routine laboratory blood indicators, and the model was evaluated using ROC curves, calibration curves, and DCA curves. Result This study found that gender, medical history, cough, diarrhea symptoms, and high CRP levels were independent risk factors for concurrent CAL. To further predict CAL risk, a column chart model was constructed based on LASSO regression and ten fold cross validation. The ROC curve in the training queue showed good discriminative ability (AUC: 0.879), while the ROC curve in the validation queue showed good discriminative ability (AUC: 0.859). This model exhibits good discriminative ability, high accuracy, and potential clinical benefits in both training and validation sets. Conclusion Through this study, we provide clinicians with a new tool to more accurately predict and manage CAL risk in children with KD, which can help optimize treatment strategies and improve efficacy.
format Article
id doaj-art-54eeb9c804fb4245b60926e981db1b7c
institution Kabale University
issn 1471-2431
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BMC Pediatrics
spelling doaj-art-54eeb9c804fb4245b60926e981db1b7c2025-08-20T03:46:16ZengBMCBMC Pediatrics1471-24312025-07-0125111110.1186/s12887-025-05917-wA retrospective cohort study using machine learning to predict coronary artery lesions in children with Kawasaki diseaseYanan Duan0Aiping Chen1Xuedi Cheng2Department of Obstetrics and Gynecology, The Affiliated Hospital of Qingdao UniversityDepartment of Obstetrics and Gynecology, The Affiliated Hospital of Qingdao UniversityDepartment of Clinical Laboratory, The Affiliated Hospital of Qingdao UniversityAbstract Background Kawasaki disease (KD) mainly occurs in children under 5 years old, and the most common complication of KD is coronary artery lesion (CAL). In recent years, the incidence rate of KD has increased year by year worldwide, so it is particularly important to strengthen the diagnosis of KD and identify CAL early. Method This retrospective cohort study included a total of 436 children diagnosed with Kawasaki disease and aimed to develop a predictive model for CAL using early clinical symptoms and laboratory features. To reduce potential confounding, propensity score matching (PSM) was applied, and both univariate and multivariate analyses were conducted to identify significant predictors of CAL. Subsequently, through machine learning, a predictive column chart model was constructed using clinical features and routine laboratory blood indicators, and the model was evaluated using ROC curves, calibration curves, and DCA curves. Result This study found that gender, medical history, cough, diarrhea symptoms, and high CRP levels were independent risk factors for concurrent CAL. To further predict CAL risk, a column chart model was constructed based on LASSO regression and ten fold cross validation. The ROC curve in the training queue showed good discriminative ability (AUC: 0.879), while the ROC curve in the validation queue showed good discriminative ability (AUC: 0.859). This model exhibits good discriminative ability, high accuracy, and potential clinical benefits in both training and validation sets. Conclusion Through this study, we provide clinicians with a new tool to more accurately predict and manage CAL risk in children with KD, which can help optimize treatment strategies and improve efficacy.https://doi.org/10.1186/s12887-025-05917-wKawasaki diseaseCoronary artery lesionPropensity score matchingMachine learningCRP
spellingShingle Yanan Duan
Aiping Chen
Xuedi Cheng
A retrospective cohort study using machine learning to predict coronary artery lesions in children with Kawasaki disease
BMC Pediatrics
Kawasaki disease
Coronary artery lesion
Propensity score matching
Machine learning
CRP
title A retrospective cohort study using machine learning to predict coronary artery lesions in children with Kawasaki disease
title_full A retrospective cohort study using machine learning to predict coronary artery lesions in children with Kawasaki disease
title_fullStr A retrospective cohort study using machine learning to predict coronary artery lesions in children with Kawasaki disease
title_full_unstemmed A retrospective cohort study using machine learning to predict coronary artery lesions in children with Kawasaki disease
title_short A retrospective cohort study using machine learning to predict coronary artery lesions in children with Kawasaki disease
title_sort retrospective cohort study using machine learning to predict coronary artery lesions in children with kawasaki disease
topic Kawasaki disease
Coronary artery lesion
Propensity score matching
Machine learning
CRP
url https://doi.org/10.1186/s12887-025-05917-w
work_keys_str_mv AT yananduan aretrospectivecohortstudyusingmachinelearningtopredictcoronaryarterylesionsinchildrenwithkawasakidisease
AT aipingchen aretrospectivecohortstudyusingmachinelearningtopredictcoronaryarterylesionsinchildrenwithkawasakidisease
AT xuedicheng aretrospectivecohortstudyusingmachinelearningtopredictcoronaryarterylesionsinchildrenwithkawasakidisease
AT yananduan retrospectivecohortstudyusingmachinelearningtopredictcoronaryarterylesionsinchildrenwithkawasakidisease
AT aipingchen retrospectivecohortstudyusingmachinelearningtopredictcoronaryarterylesionsinchildrenwithkawasakidisease
AT xuedicheng retrospectivecohortstudyusingmachinelearningtopredictcoronaryarterylesionsinchildrenwithkawasakidisease