Cargando…
Comparison of Machine Learning Models for Prediction of Initial Intravenous Immunoglobulin Resistance in Children With Kawasaki Disease
We constructed an optimal machine learning (ML) method for predicting intravenous immunoglobulin (IVIG) resistance in children with Kawasaki disease (KD) using commonly available clinical and laboratory variables. We retrospectively collected 98 clinical records of hospitalized children with KD (2–1...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7744372/ https://www.ncbi.nlm.nih.gov/pubmed/33344380 http://dx.doi.org/10.3389/fped.2020.570834 |
_version_ | 1783624413788241920 |
---|---|
author | Kuniyoshi, Yasutaka Tokutake, Haruka Takahashi, Natsuki Kamura, Azusa Yasuda, Sumie Tashiro, Makoto |
author_facet | Kuniyoshi, Yasutaka Tokutake, Haruka Takahashi, Natsuki Kamura, Azusa Yasuda, Sumie Tashiro, Makoto |
author_sort | Kuniyoshi, Yasutaka |
collection | PubMed |
description | We constructed an optimal machine learning (ML) method for predicting intravenous immunoglobulin (IVIG) resistance in children with Kawasaki disease (KD) using commonly available clinical and laboratory variables. We retrospectively collected 98 clinical records of hospitalized children with KD (2–109 months of age). We found that 20 (20%) children were resistant to initial IVIG therapy. We trained three ML techniques, including logistic regression, linear support vector machine, and eXtreme gradient boosting with 10 variables against IVIG resistance. Moreover, we estimated the predictive performance based on nested 5-fold cross-validation (CV). We also selected variables using the recursive feature elimination method and performed the nested 5-fold CV with selected variables in a similar manner. We compared ML models with the existing system regardless of their predictive performance. Results of the area under the receiver operator characteristic curve were in the range of 0.58–0.60 in the all-variable model and 0.60–0.75 in the select model. The specificities were more than 0.90 and higher than those in existing scoring systems, but the sensitivities were lower. Three ML models based on demographics and routine laboratory variables did not provide reliable performance. This is possibly the first study that has attempted to establish a better predictive model. Additional biomarkers are probably needed to generate an effective prediction model. |
format | Online Article Text |
id | pubmed-7744372 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-77443722020-12-18 Comparison of Machine Learning Models for Prediction of Initial Intravenous Immunoglobulin Resistance in Children With Kawasaki Disease Kuniyoshi, Yasutaka Tokutake, Haruka Takahashi, Natsuki Kamura, Azusa Yasuda, Sumie Tashiro, Makoto Front Pediatr Pediatrics We constructed an optimal machine learning (ML) method for predicting intravenous immunoglobulin (IVIG) resistance in children with Kawasaki disease (KD) using commonly available clinical and laboratory variables. We retrospectively collected 98 clinical records of hospitalized children with KD (2–109 months of age). We found that 20 (20%) children were resistant to initial IVIG therapy. We trained three ML techniques, including logistic regression, linear support vector machine, and eXtreme gradient boosting with 10 variables against IVIG resistance. Moreover, we estimated the predictive performance based on nested 5-fold cross-validation (CV). We also selected variables using the recursive feature elimination method and performed the nested 5-fold CV with selected variables in a similar manner. We compared ML models with the existing system regardless of their predictive performance. Results of the area under the receiver operator characteristic curve were in the range of 0.58–0.60 in the all-variable model and 0.60–0.75 in the select model. The specificities were more than 0.90 and higher than those in existing scoring systems, but the sensitivities were lower. Three ML models based on demographics and routine laboratory variables did not provide reliable performance. This is possibly the first study that has attempted to establish a better predictive model. Additional biomarkers are probably needed to generate an effective prediction model. Frontiers Media S.A. 2020-12-03 /pmc/articles/PMC7744372/ /pubmed/33344380 http://dx.doi.org/10.3389/fped.2020.570834 Text en Copyright © 2020 Kuniyoshi, Tokutake, Takahashi, Kamura, Yasuda and Tashiro. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Pediatrics Kuniyoshi, Yasutaka Tokutake, Haruka Takahashi, Natsuki Kamura, Azusa Yasuda, Sumie Tashiro, Makoto Comparison of Machine Learning Models for Prediction of Initial Intravenous Immunoglobulin Resistance in Children With Kawasaki Disease |
title | Comparison of Machine Learning Models for Prediction of Initial Intravenous Immunoglobulin Resistance in Children With Kawasaki Disease |
title_full | Comparison of Machine Learning Models for Prediction of Initial Intravenous Immunoglobulin Resistance in Children With Kawasaki Disease |
title_fullStr | Comparison of Machine Learning Models for Prediction of Initial Intravenous Immunoglobulin Resistance in Children With Kawasaki Disease |
title_full_unstemmed | Comparison of Machine Learning Models for Prediction of Initial Intravenous Immunoglobulin Resistance in Children With Kawasaki Disease |
title_short | Comparison of Machine Learning Models for Prediction of Initial Intravenous Immunoglobulin Resistance in Children With Kawasaki Disease |
title_sort | comparison of machine learning models for prediction of initial intravenous immunoglobulin resistance in children with kawasaki disease |
topic | Pediatrics |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7744372/ https://www.ncbi.nlm.nih.gov/pubmed/33344380 http://dx.doi.org/10.3389/fped.2020.570834 |
work_keys_str_mv | AT kuniyoshiyasutaka comparisonofmachinelearningmodelsforpredictionofinitialintravenousimmunoglobulinresistanceinchildrenwithkawasakidisease AT tokutakeharuka comparisonofmachinelearningmodelsforpredictionofinitialintravenousimmunoglobulinresistanceinchildrenwithkawasakidisease AT takahashinatsuki comparisonofmachinelearningmodelsforpredictionofinitialintravenousimmunoglobulinresistanceinchildrenwithkawasakidisease AT kamuraazusa comparisonofmachinelearningmodelsforpredictionofinitialintravenousimmunoglobulinresistanceinchildrenwithkawasakidisease AT yasudasumie comparisonofmachinelearningmodelsforpredictionofinitialintravenousimmunoglobulinresistanceinchildrenwithkawasakidisease AT tashiromakoto comparisonofmachinelearningmodelsforpredictionofinitialintravenousimmunoglobulinresistanceinchildrenwithkawasakidisease |