Identifying the risk of Kawasaki disease based solely on routine blood test features through novel construction of machine learning models
Open Access
- 1 January 2025
- journal article
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 27, 2832-2842
Abstract
Kawasaki disease (KD) is a leading cause of acquired coronary vasculitis in children and remains a critical diagnostic challenge among febrile pediatric patients. To support frontline pediatricians with a more objective diagnostic tool, we developed and implemented KDpredictor, a machine learning-based model for KD risk identification. KDpredictor leverages only the routine blood test features, including complete blood count with differential count, C-reactive protein, and alanine aminotransferase. It also takes the lead in using age-calibrated eosinophil, platelet, and hemoglobin results. Trained using the light gradient boosting machine algorithm on clinical data from 1,927 KD cases and 45,274 febrile controls, KDpredictor achieved strong performance metrics (auROC: 95.7%, auPRC: 72.4%, recall: 0.89) on a reserved test set, outperforming previous models by at least 3% in auROC and 39.3% in auPRC. Additional explainable AI analyses revealed that several top predictive features in KDpredictor are consistent with prior clinical findings. We also evaluated KDpredictor on three independent cohorts collected in East Asia (Taiwan and China) during the COVID-19 period. KDpredictor achieves recall values of 90.9%, 83.7%, and 91.7% on KD samples identified in three independent medical centers, respectively, indicating its applicability across independent clinical settings. In summary, KDpredictor demonstrates robust generalizability in KD risk identification across populations by using only standard blood samples independent of clinical symptoms. KDpredictor is freely available at https://cosbi.ee.ncku.edu.tw/KD_under7/.Keywords
Funding Information
- Ministry of Science and Technology, Taiwan (NSTC 112-2221-E-006-129-MY2)
- Ministry of Science and Technology, Taiwan (111-2221-E-006-231)
- Chang Gung Memorial Hospital (CMRPG8N0821)
- Chang Gung Memorial Hospital (CMRPG8M1421-2)
- Chang Gung Memorial Hospital (CMRPG8M1441)
- Chang Gung Memorial Hospital (CMRPG8M1431-2)
- Chang Gung Memorial Hospital (CMRPG8M1321)
- National Cheng Kung University
- Ministry of Education
- National Science and Technology Council (MOST 111-2221-E-006-151-MY3)
- National Science and Technology Council (NSTC 112-2314-B-182-032-MY3)
- National Science and Technology Council (113-2221-E-006-135-MY3)
- National Science and Technology Council (110-2221-E-006-198-MY3)
This publication has 45 references indexed in Scilit:
- RDDL: A systematic ensemble pipeline tool that streamlines balancing training schemes to reduce the effects of data imbalance in rare-disease-related deep-learning applicationsComputational Biology and Chemistry, 2023
- CFA: An explainable deep learning model for annotating the transcriptional roles of cis-regulatory modules based on epigenetic codesComputers in Biology and Medicine, 2022
- Explainable deep learning algorithm for distinguishing incomplete Kawasaki disease by coronary artery lesions on echocardiographic imagingComputer Methods and Programs in Biomedicine, 2022
- The emerging roles of eosinophils: Implications for the targeted treatment of eosinophilic-associated inflammatory conditionsCurrent Research in Immunology, 2022
- regCNN: identifying Drosophila genome-wide cis -regulatory modules via integrating the local patterns in epigenetic marks and transcription factor binding motifsComputational and Structural Biotechnology Journal, 2021
- Evaluation of Hemoglobin Cutoff Levels to Define Anemia Among Healthy IndividualsJAMA Network Open, 2021
- Hepcidin in Kawasaki disease: upregulation by acute inflammation in patients having resistance to intravenous immunoglobulin therapyClinical Rheumatology, 2021
- Prevalence of Bacterial Meningitis Among Febrile Infants Aged 29-60 Days With Positive Urinalysis ResultsJAMA Network Open, 2021
- Macrophage activation syndrome in children with Kawasaki disease: diagnostic and therapeutic approachesWorld Journal of Pediatrics, 2020
- Dissecting Kawasaki disease: a state-of-the-art reviewEuropean Journal of Pediatrics, 2017