An interpretable machine learning-assisted diagnostic model for Kawasaki disease in children

Abstract Kawasaki disease (KD) is a syndrome of acute systemic vasculitis commonly observed in children. Due to its unclear pathogenesis and the lack of specific diagnostic markers, it is prone to being confused with other diseases that exhibit similar symptoms, making early and accurate diagnosis c...

Full description

Saved in:
Bibliographic Details
Main Authors: Mengyu Duan, Zhimin Geng, Lichao Gao, Yonggen Zhao, Zheming Li, Lindong Chen, Pekka Kuosmanen, Guoqiang Qi, Fangqi Gong, Gang Yu
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-92277-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850253247116214272
author Mengyu Duan
Zhimin Geng
Lichao Gao
Yonggen Zhao
Zheming Li
Lindong Chen
Pekka Kuosmanen
Guoqiang Qi
Fangqi Gong
Gang Yu
author_facet Mengyu Duan
Zhimin Geng
Lichao Gao
Yonggen Zhao
Zheming Li
Lindong Chen
Pekka Kuosmanen
Guoqiang Qi
Fangqi Gong
Gang Yu
author_sort Mengyu Duan
collection DOAJ
description Abstract Kawasaki disease (KD) is a syndrome of acute systemic vasculitis commonly observed in children. Due to its unclear pathogenesis and the lack of specific diagnostic markers, it is prone to being confused with other diseases that exhibit similar symptoms, making early and accurate diagnosis challenging. This study aimed to develop an interpretable machine learning (ML) diagnostic model for KD. We collected demographic and laboratory data from 3650 patients (2299 with KD, 1351 with similar symptoms but different diseases) and employed 10 ML algorithms to construct the diagnostic model. Diagnostic performance was evaluated using several metrics, including area under the receiver-operating characteristic curve (AUC). Additionally, the shapley additive explanations (SHAP) method was employed to select important features and explain the final model. Using the Streamlit framework, we converted the model into a user-friendly web application to enhance its practicality in clinical settings. Among the 10 ML algorithms, XGBoost demonstrates the best diagnostic performance, achieving an AUC of 0.9833. SHAP analysis revealed that features, including age in months, fibrinogen, and human interferon gamma, are important for diagnosis. When relying on the top 10 most important features, the model’s AUC remains at 0.9757. The proposed model can assist clinicians in making early and accurate diagnoses of KD. Furthermore, its interpretability enhances model transparency, facilitating clinicians’ understanding of prediction reliability.
format Article
id doaj-art-ec53be8dfa144ed5bbd8c52f0052a556
institution OA Journals
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ec53be8dfa144ed5bbd8c52f0052a5562025-08-20T01:57:25ZengNature PortfolioScientific Reports2045-23222025-03-0115111210.1038/s41598-025-92277-1An interpretable machine learning-assisted diagnostic model for Kawasaki disease in childrenMengyu Duan0Zhimin Geng1Lichao Gao2Yonggen Zhao3Zheming Li4Lindong Chen5Pekka Kuosmanen6Guoqiang Qi7Fangqi Gong8Gang Yu9National Clinical Research Center for Child Health, National Children’s Regional Medical Center, Children’s Hospital, Zhejiang University School of MedicineNational Clinical Research Center for Child Health, National Children’s Regional Medical Center, Children’s Hospital, Zhejiang University School of MedicineNational Clinical Research Center for Child Health, National Children’s Regional Medical Center, Children’s Hospital, Zhejiang University School of MedicineNational Clinical Research Center for Child Health, National Children’s Regional Medical Center, Children’s Hospital, Zhejiang University School of MedicineNational Clinical Research Center for Child Health, National Children’s Regional Medical Center, Children’s Hospital, Zhejiang University School of MedicineNational Clinical Research Center for Child Health, National Children’s Regional Medical Center, Children’s Hospital, Zhejiang University School of MedicineSino-Finland Joint AI Laboratory for Child Health of Zhejiang ProvinceNational Clinical Research Center for Child Health, National Children’s Regional Medical Center, Children’s Hospital, Zhejiang University School of MedicineNational Clinical Research Center for Child Health, National Children’s Regional Medical Center, Children’s Hospital, Zhejiang University School of MedicineNational Clinical Research Center for Child Health, National Children’s Regional Medical Center, Children’s Hospital, Zhejiang University School of MedicineAbstract Kawasaki disease (KD) is a syndrome of acute systemic vasculitis commonly observed in children. Due to its unclear pathogenesis and the lack of specific diagnostic markers, it is prone to being confused with other diseases that exhibit similar symptoms, making early and accurate diagnosis challenging. This study aimed to develop an interpretable machine learning (ML) diagnostic model for KD. We collected demographic and laboratory data from 3650 patients (2299 with KD, 1351 with similar symptoms but different diseases) and employed 10 ML algorithms to construct the diagnostic model. Diagnostic performance was evaluated using several metrics, including area under the receiver-operating characteristic curve (AUC). Additionally, the shapley additive explanations (SHAP) method was employed to select important features and explain the final model. Using the Streamlit framework, we converted the model into a user-friendly web application to enhance its practicality in clinical settings. Among the 10 ML algorithms, XGBoost demonstrates the best diagnostic performance, achieving an AUC of 0.9833. SHAP analysis revealed that features, including age in months, fibrinogen, and human interferon gamma, are important for diagnosis. When relying on the top 10 most important features, the model’s AUC remains at 0.9757. The proposed model can assist clinicians in making early and accurate diagnoses of KD. Furthermore, its interpretability enhances model transparency, facilitating clinicians’ understanding of prediction reliability.https://doi.org/10.1038/s41598-025-92277-1Machine learningInterpretabilityKawasaki diseaseSHAPXGBoostStreamlit.
spellingShingle Mengyu Duan
Zhimin Geng
Lichao Gao
Yonggen Zhao
Zheming Li
Lindong Chen
Pekka Kuosmanen
Guoqiang Qi
Fangqi Gong
Gang Yu
An interpretable machine learning-assisted diagnostic model for Kawasaki disease in children
Scientific Reports
Machine learning
Interpretability
Kawasaki disease
SHAP
XGBoost
Streamlit.
title An interpretable machine learning-assisted diagnostic model for Kawasaki disease in children
title_full An interpretable machine learning-assisted diagnostic model for Kawasaki disease in children
title_fullStr An interpretable machine learning-assisted diagnostic model for Kawasaki disease in children
title_full_unstemmed An interpretable machine learning-assisted diagnostic model for Kawasaki disease in children
title_short An interpretable machine learning-assisted diagnostic model for Kawasaki disease in children
title_sort interpretable machine learning assisted diagnostic model for kawasaki disease in children
topic Machine learning
Interpretability
Kawasaki disease
SHAP
XGBoost
Streamlit.
url https://doi.org/10.1038/s41598-025-92277-1
work_keys_str_mv AT mengyuduan aninterpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT zhimingeng aninterpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT lichaogao aninterpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT yonggenzhao aninterpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT zhemingli aninterpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT lindongchen aninterpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT pekkakuosmanen aninterpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT guoqiangqi aninterpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT fangqigong aninterpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT gangyu aninterpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT mengyuduan interpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT zhimingeng interpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT lichaogao interpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT yonggenzhao interpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT zhemingli interpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT lindongchen interpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT pekkakuosmanen interpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT guoqiangqi interpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT fangqigong interpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren
AT gangyu interpretablemachinelearningassisteddiagnosticmodelforkawasakidiseaseinchildren