Object

This study aimed to determine the risk factors of ischemic/hemorrhagic stroke in patients suffering moyamoya disease (MMD), as well as to compare the effects of six analysis methods.

Methods

In the present retrospective study, the data originated from the database of Jiang Xi Province Medical Big Data Engineering & Technology Research Center. In addition, the information of patients with MMD that were admitted to the second affiliated hospital of Nanchang university from January 1st, 2012 to December 31st, 2019 was acquired. Six different machine learning methods were adopted to build the models, and XGboost, Logistic regression (LR) and Support vector machine (SVM) models were adopted to determine the risk factors of ischemic/hemorrhagic stroke in patients with MMD because of their excellent performance. Next, the effects of the built models were compared and validated in internal and independent external validation sets. The external validation set involving 204 cases from January 1st, 2018 to December 31st, 2019.

Result

On the whole, 790 patients with MMD were screened, i.e., 397 patients with cerebral infarction and 393 patients with cerebral hemorrhage. In the internal validation set, XGboost model exhibited significant discrimination (AUC>0.75), with its area under the curve (AUC) reaching 0.874 (95% CI: 0.859, 0.889). Compared with the LR and SVM models, the XGboost model in the internal validation set achieved the improved accuracy by 3.2% and 3.1%, respectively, whereas no significant difference was identified.

Conclusion

XGboost model could be more efficient in analyzing the risk factors of ischemic/hemorrhagic stroke in patients with MMD; the risk factors of hemorrhagic stroke in MMD might be closely related to Suzuki stages, presence of an aneurysm, rural residence, hospitalization times and age of onset.

中文翻译：

---

烟雾病缺血/出血的机器学习模型及其危险因素分析

目的

本研究旨在确定烟雾病（MMD）患者缺血性/出血性卒中的危险因素，并比较六种分析方法的效果。

方法

本回顾性研究数据来源于江西省医学大数据工程技术研究中心数据库。此外，获取2012年1月1日至2019年12月31日南昌大学第二附属医院收治的MMD患者信息。采用六种不同的机器学习方法建立模型，并采用XGboost、Logistic回归（LR）和支持向量机（SVM）模型确定MMD患者缺血性/出血性脑卒中的危险因素，因为它们表现优异。接下来，在内部和独立的外部验证集中比较和验证所构建模型的效果。外部验证集涉及 2018 年 1 月 1 日至 2019 年 12 月 31 日的 204 个案例。

结果

总体筛查MMD患者790例，即脑梗死397例，脑出血393例。在内部验证集中，XGboost 模型表现出显着的区分度（AUC>0.75），其曲线下面积（AUC）达到 0.874（95% CI：0.859，0.889）。与 LR 和 SVM 模型相比，内部验证集中的 XGboost 模型的准确率分别提高了 3.2% 和 3.1%，但没有发现显着差异。

结论

XGboost模型可以更有效地分析MMD患者缺血性/出血性卒中的危险因素；MMD出血性卒中的危险因素可能与铃木分期、动脉瘤的存在、农村居住地、住院时间和发病年龄密切相关。