Journal article
ICU Admission Prediction for Patients With Kawasaki Disease or MIS-C Using Machine Learning
JACC. Advances (Online), Vol.4(3), 101621
03/01/2025
DOI: 10.1016/j.jacadv.2025.101621
PMCID: PMC11994043
PMID: 40147056
Abstract
BACKGROUND Multisystem inflammatory syndrome in children (MIS-C) and Kawasaki disease (KD) show a broad spectrum of clinical severity, from a relatively benign clinical course to requiring admission to the intensive care unit (ICU). With either, clinical deterioration may be rapid and unexpected. OBJECTIVES The aim of the study was to develop a machine learning (ML) model to predict future ICU admission for patients with KD or MIS-C to augment clinical decision-making. METHODS We developed a prediction model for ICU admission using 2,539 patients <18 years of age with MIS-C or KD enrolled in the International Kawasaki Disease Registry. Using discrete time-point clinical features and engineered time-series clinical features, we developed predictive snapshot and window ML models with logistic regression, XGBoost, and random forest. Performance was compared between the various iterations of the models. RESULTS ML models effectively predicted admission to the ICU within the next 48 hours of the time of prediction. The time-series window-XGBoost model outperformed other models with an AUROC of 0.92 and an area under the precision-recall curve of 0.86. The incorporation of engineered time-series features improved the precision and recall independent of the length of the sampling time window. Higher ferritin level, treatment with anticoagulant or unfractionated heparin, higher C-reactive protein level, and lower platelet count were identified as the most predictive features for positive ICU prediction. CONCLUSIONS ML algorithms can effectively predict ICU admission for pediatric patients with MIS-C or KD. These models may prompt physicians to pre-emptively implement supportive measures, possibly mitigating the risk of clinical deterioration.
Details
- Title: Subtitle
- ICU Admission Prediction for Patients With Kawasaki Disease or MIS-C Using Machine Learning
- Creators
- Jiwon Woo - Johns Hopkins UniversityRebecca Mosier - Johns Hopkins UniversityRishima Mukherjee - Johns Hopkins UniversityAshraf S. Harahsheh - George Washington UniversitySupriya S. Jain - Maria Fareri Children's HospitalGeetha Raghuveer - Children's Mercy HospitalBalasubramanian Sundaram - Kanchi Kamakoti CHILDS Trust HospitalSimon Lee - Nationwide Children's HospitalMichael A. Portman - Seattle Children's HospitalNagib Dahdah - Université de MontréalMarianna Fabi - Azienda USL di BolognaTodd T. Nowlen - Phoenix Children's HospitalAudrey Dionne - Boston Children's HospitalMona El Ganzoury - Ain Shams UniversityTyler H. Harris - Children's Hospital of PittsburghBenjamin T. Barnes - Johns Hopkins MedicineFrederic Dallaire - Université de SherbrookePaul Dancey - Janeway Children's Health and Rehabilitation CentreKambiz Norozi - Children’s Health Research InstituteMahmoud Alsalehi - Kingston Health Sciences CentreElif Seda Selamet Tierney - Lucile Packard Children's HospitalJacqueline R. Szmuszkovicz - Children's Hospital of Los AngelesPei-Ni Jone - Lurie Children's HospitalDeepa Prasad - Banner Desert Medical CenterAnji T. Yetman - Children's Hospital & Medical CenterNilanjana Misra - Cohen Children's Medical CenterMark D. Hicar - University at Buffalo, State University of New YorkDeepika Thacker - Community Health Systems - Dupont HospitalNadine F. Choueiter - Children's Hospital at MontefioreElisa Fernandez Cooke - Hospital Universitario 12 De OctubreDaniel Mauriello - Johns Hopkins All Children's HospitalTapas Mondal - Nationwide Children's HospitalMatthew D. Elias - Children's Hospital of PhiladelphiaKimberly E. Mchugh - Medical University of South CarolinaShae A. Merves - Arkansas Children's HospitalLuis Martin Garrido-Garcia - Hosp Angeles Lomas, Huixquilucan, MexicoMichael Khoury - University of AlbertaGuillermo Larios - Pontificia Universidad Católica de ChileBhargava Chinni - Johns Hopkins UniversityKaashvi Pruthi - Johns Hopkins UniversityWenyu Yang - Johns Hopkins UniversityJoseph Greenstein - Johns Hopkins UniversityCasey Taylor - Johns Hopkins UniversityPedrom Farid - Hospital for Sick ChildrenBrian W. McCrindle - Hospital for Sick ChildrenCedric Manlhiot - Johns Hopkins UniversityInternational Kawasaki Disease RegistryHidemi Kajimoto (Contributor) - Stead Family Department of Pediatrics
- Resource Type
- Journal article
- Publication Details
- JACC. Advances (Online), Vol.4(3), 101621
- DOI
- 10.1016/j.jacadv.2025.101621
- PMID
- 40147056
- PMCID
- PMC11994043
- NLM abbreviation
- JACC Adv
- ISSN
- 2772-963X
- eISSN
- 2772-963X
- Publisher
- Elsevier
- Number of pages
- 12
- Grant note
- Office of the Director, National Institute of Health (OD) R61HD105591/R33HD105591 / Eunice Kennedy Shriver National Institute of Child Health & Human Development; United States Department of Health & Human Services; National Institutes of Health (NIH) - USA; NIH Eunice Kennedy Shriver National Institute of Child Health & Human Development (NICHD)
- Language
- English
- Date published
- 03/01/2025
- Academic Unit
- Cardiology; Stead Family Department of Pediatrics
- Record Identifier
- 9984961114202771
Metrics
23 Record Views