Data_Sheet_1_Novel machine learning models to predict pneumonia events in supratentorial intracerebral hemorrhage populations: An analysis of the Risa-MIS-ICH study.docx

BackgroundStroke-associated pneumonia (SAP) contributes to high mortality rates in spontaneous intracerebral hemorrhage (sICH) populations. Accurate prediction and early intervention of SAP are associated with prognosis. None of the previously developed predictive scoring systems are widely accepted. We aimed to derive and validate novel supervised machine learning (ML) models to predict SAP events in supratentorial sICH populations.MethodsThe data of eligible supratentorial sICH individuals were extracted from the Risa-MIS-ICH database and split into training, internal validation, and external validation datasets. The primary outcome was SAP during hospitalization. Univariate and multivariate analyses were used for variable filtering, and logistic regression (LR), Gaussian naïve Bayes (GNB), random forest (RF), K-nearest neighbor (KNN), support vector machine (SVM), extreme gradient boosting (XGB), and ensemble soft voting model (ESVM) were adopted for ML model derivations. The accuracy, sensitivity, specificity, and area under the curve (AUC) were adopted to evaluate the predictive value of each model with internal/cross-/external validations.ResultsA total of 468 individuals with sICH were included in this work. Six independent variables [nasogastric feeding, airway support, unconscious onset, surgery for external ventricular drainage (EVD), larger sICH volume, and intensive care unit (ICU) stay] for SAP were identified and selected for ML prediction model derivations and validations. The internal and cross-validations revealed the superior and robust performance of the GNB model with the highest AUC value (0.861, 95% CI: 0.793–0.930), while the LR model had the highest AUC value (0.867, 95% CI: 0.812–0.923) in external validation. The ESVM method combining the other six methods had moderate but robust abilities in both cross-validation and external validation and achieved an AUC of 0.843 (95% CI: 0.784–0.902) in external validation.ConclusionThe ML models could effectively predict SAP in sICH populations, and our novel ensemble model demonstrated reliable robust performance outcomes despite the populational and algorithmic differences. This attempt indicated that ML application may benefit in the early identification of SAP.

背景脑室出血相关肺炎（SAP）在自发性脑室内出血（sICH）患者群体中导致高死亡率。精确预测及早期干预SAP与预后密切相关。此前开发的预测评分系统均未得到广泛认可。本研究旨在推导并验证新型监督机器学习（ML）模型，以预测sICH患者群体中的SAP事件。方法：从Risa-MIS-ICH数据库中提取符合条件的高位sICH个体的数据，并将其分为训练集、内部验证集和外部验证集。主要结局指标为住院期间的SAP。采用单因素和多因素分析进行变量筛选，并采用逻辑回归（LR）、高斯朴素贝叶斯（GNB）、随机森林（RF）、K最近邻（KNN）、支持向量机（SVM）、极端梯度提升（XGB）和集成软投票模型（ESVM）进行ML模型的推导。通过内部/交叉/外部验证评估每个模型的预测价值，采用准确率、敏感性、特异性和曲线下面积（AUC）作为评估指标。结果：本研究共纳入sICH患者468例。确定了六项独立变量[鼻胃管喂养、气道支持、昏迷发作、外引流术（EVD）手术、较大sICH体积和重症监护室（ICU）住院时间]与SAP相关，并选入ML预测模型推导和验证。内部和交叉验证显示，GNB模型在内部验证和交叉验证中表现出优异且稳健的性能，其AUC值最高（0.861，95% CI：0.793–0.930），而在外部验证中，LR模型具有最高的AUC值（0.867，95% CI：0.812–0.923）。结合其他六种方法的ESVM方法在交叉验证和外部验证中均表现出中等但稳健的能力，在外部验证中实现了AUC值为0.843（95% CI：0.784–0.902）。结论：ML模型能有效预测sICH患者中的SAP，我们提出的集成模型尽管在人群和算法上存在差异，但展现了可靠的稳健性能。这一尝试表明，ML应用可能有助于SAP的早期识别。