Prediction Models for Intravenous Immunoglobulin Non-Responders of Kawasaki Disease Using Machine Learning.

IF 2.9 3区 医学 Q2 PHARMACOLOGY & PHARMACY
Clinical Drug Investigation Pub Date : 2024-06-01 Epub Date: 2024-06-13 DOI:10.1007/s40261-024-01373-z
Yoshifumi Miyagi, Satoru Iwashima
{"title":"Prediction Models for Intravenous Immunoglobulin Non-Responders of Kawasaki Disease Using Machine Learning.","authors":"Yoshifumi Miyagi, Satoru Iwashima","doi":"10.1007/s40261-024-01373-z","DOIUrl":null,"url":null,"abstract":"<p><p>BACKGROUND AND OBJECTIVE: Intravenous immunoglobulin (IVIG) is a prominent therapeutic agent for Kawasaki disease (KD) that significantly reduces the incidence of coronary artery anomalies. Various methodologies, including machine learning, have been employed to develop IVIG non-responder prediction models; however, their validation and reproducibility remain unverified. This study aimed to develop a predictive scoring system for identifying IVIG nonresponders and rigorously test the accuracy and reliability of this system. METHODS: The study included an exposure group of 228 IVIG non-responders and a control group of 997 IVIG responders. Subsequently, a predictive machine learning model was constructed. The Shizuoka score, including variables such as the \"initial treatment date\" (cutoff: < 4 days), sodium level (cutoff: < 133 mEq/L), total bilirubin level (cutoff: ≥ 0.5 mg/dL), and neutrophil-to-lymphocyte ratio (cutoff: ≥ 2.6), was established. Patients meeting two or more of these criteria were grouped as high-risk IVIG non-responders. Using the Shizuoka score to stratify IVIG responders, propensity score matching was used to analyze 85 patients each for IVIG and IVIG-added prednisolone treatment in the high-risk group. In the IVIG plus prednisolone group, the IVIG non-responder count significantly decreased (p < 0.001), with an odds ratio of 0.192 (95% confidence interval 0.078-0.441). CONCLUSIONS: Intravenous immunoglobulin non-responders were predicted using machine learning models and validated using propensity score matching. The initiation of initial IVIG-added prednisolone treatment in the high-risk group identified by the Shizuoka score, crafted using machine learning models, appears useful for predicting IVIG non-responders.</p>","PeriodicalId":10402,"journal":{"name":"Clinical Drug Investigation","volume":" ","pages":"425-437"},"PeriodicalIF":2.9000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical Drug Investigation","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s40261-024-01373-z","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/6/13 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"PHARMACOLOGY & PHARMACY","Score":null,"Total":0}
引用次数: 0

Abstract

BACKGROUND AND OBJECTIVE: Intravenous immunoglobulin (IVIG) is a prominent therapeutic agent for Kawasaki disease (KD) that significantly reduces the incidence of coronary artery anomalies. Various methodologies, including machine learning, have been employed to develop IVIG non-responder prediction models; however, their validation and reproducibility remain unverified. This study aimed to develop a predictive scoring system for identifying IVIG nonresponders and rigorously test the accuracy and reliability of this system. METHODS: The study included an exposure group of 228 IVIG non-responders and a control group of 997 IVIG responders. Subsequently, a predictive machine learning model was constructed. The Shizuoka score, including variables such as the "initial treatment date" (cutoff: < 4 days), sodium level (cutoff: < 133 mEq/L), total bilirubin level (cutoff: ≥ 0.5 mg/dL), and neutrophil-to-lymphocyte ratio (cutoff: ≥ 2.6), was established. Patients meeting two or more of these criteria were grouped as high-risk IVIG non-responders. Using the Shizuoka score to stratify IVIG responders, propensity score matching was used to analyze 85 patients each for IVIG and IVIG-added prednisolone treatment in the high-risk group. In the IVIG plus prednisolone group, the IVIG non-responder count significantly decreased (p < 0.001), with an odds ratio of 0.192 (95% confidence interval 0.078-0.441). CONCLUSIONS: Intravenous immunoglobulin non-responders were predicted using machine learning models and validated using propensity score matching. The initiation of initial IVIG-added prednisolone treatment in the high-risk group identified by the Shizuoka score, crafted using machine learning models, appears useful for predicting IVIG non-responders.

Abstract Image

利用机器学习建立川崎病静脉注射免疫球蛋白未应答者的预测模型
背景和目的:静脉注射免疫球蛋白(IVIG)是川崎病(KD)的主要治疗药物,可显著降低冠状动脉异常的发生率。包括机器学习在内的各种方法已被用于开发 IVIG 无应答预测模型;然而,这些模型的有效性和可重复性仍未得到验证。本研究旨在开发一种用于识别 IVIG 无应答者的预测评分系统,并严格测试该系统的准确性和可靠性。方法:研究包括一个由 228 名 IVIG 无应答者组成的暴露组和一个由 997 名 IVIG 有应答者组成的对照组。随后,构建了一个预测性机器学习模型。静冈评分包括 "初始治疗日期"(临界值:< 4 天)、血钠水平(临界值:< 133 mEq/L)、总胆红素水平(临界值:≥ 0.5 mg/dL)和中性粒细胞与淋巴细胞比率(临界值:≥ 2.6)等变量。符合上述两个或两个以上标准的患者被归为高风险 IVIG 无应答者。利用静冈评分对 IVIG 反应者进行分层,并采用倾向评分匹配法对高风险组中接受 IVIG 和 IVIG 加用泼尼松龙治疗的各 85 例患者进行分析。在 IVIG 加泼尼松龙组中,IVIG 无应答者人数显著减少(p < 0.001),几率比为 0.192(95% 置信区间为 0.078-0.441)。结论使用机器学习模型预测了静脉注射免疫球蛋白无应答者,并使用倾向得分匹配进行了验证。在静冈评分确定的高危人群中启动初始静脉注射免疫球蛋白加用泼尼松龙治疗,并使用机器学习模型精心设计,似乎有助于预测静脉注射免疫球蛋白无应答者。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
5.90
自引率
3.10%
发文量
108
审稿时长
6-12 weeks
期刊介绍: Clinical Drug Investigation provides rapid publication of original research covering all phases of clinical drug development and therapeutic use of drugs. The Journal includes: -Clinical trials, outcomes research, clinical pharmacoeconomic studies and pharmacoepidemiology studies with a strong link to optimum prescribing practice for a drug or group of drugs. -Clinical pharmacodynamic and clinical pharmacokinetic studies with a strong link to clinical practice. -Pharmacodynamic and pharmacokinetic studies in healthy volunteers in which significant implications for clinical prescribing are discussed. -Studies focusing on the application of drug delivery technology in healthcare. -Short communications and case study reports that meet the above criteria will also be considered. Additional digital features (including animated abstracts, video abstracts, slide decks, audio slides, instructional videos, infographics, podcasts and animations) can be published with articles; these are designed to increase the visibility, readership and educational value of the journal’s content. In addition, articles published in Clinical Drug Investigation may be accompanied by plain language summaries to assist readers who have some knowledge, but non in-depth expertise in, the area to understand important medical advances.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信