Ishida Shunsuke, Furutani Motoki, Nakashima Mika, Ishibashi Naoki, Maeda Junji, Sakai Takumi, Oguri Naoto, Miyamoto Shogo, Miyauchi Shunsuke, Okamura Sho, Okubo Yousaku, Tokuyama Takehito, Oda Noboru, Nakano Yukiko
Department of Cardiovascular Medicine, Hiroshima University Graduate School of Biomedical and Health Sciences, Hiroshima, Japan.
Heart Rhythm O2. 2025 Apr 24;6(7):987-994. doi: 10.1016/j.hroo.2025.04.009. eCollection 2025 Jul.
Brugada syndrome (BrS) has been known to cause fatal arrhythmias, and an effective risk stratification method should be developed.
This study aimed to construct a risk prediction model for BrS using machine learning models.
We enrolled 234 Japanese patients with BrS and analyzed the clinical information including the age, gender, history of syncope, family history of BrS or sudden cardiac death, PR interval in lead Ⅱ, QRS duration in V6, RR interval in V1, r-J interval in V1, T-peak-to-T-end interval, max QTc, fragmented QRS, Type-1 in peripheral leads, spontaneous type 1 pattern, aVR sign, presence of early repolarization (ER), and presence of ER in the peripheral leads. We validated the previous stratification method (BRUGADA-RISK and Predicting Arrhythmic evenT [PAT] scores). Next, we constructed 3 machine learning models (logistic regression, support vector machine [SVM], and random forest). To detect the important clinical features, we used SHapely additive exPlanations and constructed a low-dimensional model.
The area under the curve (AUC) was 0.57 for the BRUGADA-RISK score and 0.59 for the PAT score. The SVM revealed the highest AUCs. Moreover, the low-dimension model with the SVM (r-J interval in V1, history of syncope, fragmented QRS, presence of ER, T-peak-to-T-end interval, QRS duration in V6, and age) exhibited a higher AUC than the SVM model using all clinical features (mean AUC, 0.77; 95% confidence interval [0.64-0.89], Welch's T-test < .001).
The machine learning model could be useful for stratifying major arrhythmic events in BrS.
已知 Brugada 综合征（BrS）可导致致命性心律失常，因此应开发一种有效的风险分层方法。
本研究旨在使用机器学习模型构建 BrS 的风险预测模型。
我们纳入了 234 例日本 BrS 患者，并分析了其临床信息，包括年龄、性别、晕厥史、BrS 或心源性猝死家族史、Ⅱ导联 PR 间期、V6 导联 QRS 时限、V1 导联 RR 间期、V1 导联 r-J 间期、T 峰至 T 末间期、最大 QTc、碎裂 QRS、外周导联 1 型、自发 1 型心电图形态、aVR 征、早期复极（ER）的存在情况以及外周导联 ER 的存在情况。我们验证了先前的分层方法（BRUGADA-RISK 和心律失常事件预测 [PAT] 评分）。接下来，我们构建了 3 种机器学习模型（逻辑回归、支持向量机 [SVM] 和随机森林）。为了检测重要的临床特征，我们使用了 SHapely 加性解释并构建了一个低维模型。
BRUGADA-RISK 评分的曲线下面积（AUC）为 0.57，PAT 评分为 0.59。支持向量机显示出最高的 AUC。此外，包含支持向量机的低维模型（V1 导联 r-J 间期、晕厥史、碎裂 QRS、ER 的存在情况、T 峰至 T 末间期、V6 导联 QRS 时限和年龄）的 AUC 高于使用所有临床特征的支持向量机模型（平均 AUC，0.77；95% 置信区间 [0.64 - 0.89]，Welch's T 检验 <.001）。
机器学习模型可能有助于对 BrS 中的主要心律失常事件进行分层。
