Department of Pediatrics, Haibara Hospital, Makinohara City, Shizuoka, Japan.
The Shizuoka Kawasaki Disease Study Group, Shizuoka, Japan.
Clin Drug Investig. 2024 Jun;44(6):425-437. doi: 10.1007/s40261-024-01373-z. Epub 2024 Jun 13.
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.
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。各种方法，包括机器学习，已被用于开发 IVIG 无反应预测模型；然而，其验证和可重复性仍未得到验证。本研究旨在开发一种预测评分系统，以识别 IVIG 无反应者，并严格测试该系统的准确性和可靠性。
本研究纳入 228 例 IVIG 无反应者和 997 例 IVIG 反应者作为暴露组。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）、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值（临界值：≥2.6）等变量。符合两个或更多这些标准的患者被归类为高风险 IVIG 无反应者。使用静冈评分对 IVIG 反应者进行分层，通过倾向评分匹配分析高风险组中 85 例接受 IVIG 和 IVIG 加泼尼松龙治疗的患者。在 IVIG 加泼尼松龙组中，IVIG 无反应者数量显著减少（p<0.001），优势比为 0.192（95%置信区间 0.078-0.441）。
使用机器学习模型预测 IVIG 无反应者，并使用倾向评分匹配进行验证。使用机器学习模型制定的静冈评分，对高危组患者初始 IVIG 加泼尼松龙治疗的启动，似乎有助于预测 IVIG 无反应者。
