Hu Linwang, Yu Jie, Deng Jian, Zhou Hong, Yang Feng, Lu Xiaohang
Department of Neurosurgery, Hunan Provincial People's Hospital, The First Affiliated Hospital of Hunan Normal University, Changsha, China.
Department of Pharmacy, Hunan Provincial People's Hospital, The First Affiliated Hospital of Hunan Normal University, Changsha, China.
Front Neurol. 2022 Nov 24;13:968623. doi: 10.3389/fneur.2022.968623. eCollection 2022.
This study aimed to investigate the association between systemic immune-inflammation (SII) and the risk of in-hospital death for patients with intracerebral hemorrhage (ICH) in the intensive care units (ICU) and to further develop a prediction model related to SII in predicting the risk of in-hospital death for patients with ICH.
In this retrospective cohort study, we included 1,176 patients with ICH from the Medical Information Mart for Intensive Care III (MIMIC-III) database. All patients were randomly assigned to the training group for the construction of the nomogram and the testing group for the validation of the nomogram based on a ratio of 8:2. Predictors were screened by the least absolute shrinkage and selection operator (LASSO) regression analysis. A multivariate Cox regression analysis was used to investigate the association between SII and in-hospital death for patients with ICH in the ICU and develop a model for predicting the in-hospital death risk for ICU patients with ICH. The receiver operator characteristic curve was used to assess the predicting performance of the constructed nomogram.
In the training group, 232 patients with ICH died while 708 survived. LASSO regression showed some predictors, including white blood cell count, glucose, blood urea nitrogen, SII, the Glasgow Coma Scale, age, heart rate, mean artery pressure, red blood cell, bicarbonate, red blood cell distribution width, liver cirrhosis, respiratory failure, renal failure, malignant cancer, vasopressor, and mechanical ventilation. A prediction model integrating these predictors was established. The area under the curve (AUC) of the nomogram was 0.810 in the training group and 0.822 in the testing group, indicating that this nomogram might have a good performance.
Systemic immune-inflammation was associated with an increased in-hospital death risk for patients with ICH in the ICU. A nomogram for in-hospital death risk for patients with ICH in the ICU was developed and validated.
本研究旨在探讨全身免疫炎症（SII）与重症监护病房（ICU）脑出血（ICH）患者院内死亡风险之间的关联，并进一步构建与SII相关的预测模型，以预测ICH患者的院内死亡风险。
在这项回顾性队列研究中，我们纳入了医学重症监护三期信息数据库（MIMIC-III）中的1176例ICH患者。所有患者按照8:2的比例随机分为用于构建列线图的训练组和用于验证列线图的测试组。通过最小绝对收缩和选择算子（LASSO）回归分析筛选预测因素。采用多因素Cox回归分析来研究ICU中ICH患者的SII与院内死亡之间的关联，并建立预测ICU中ICH患者院内死亡风险的模型。采用受试者工作特征曲线评估所构建列线图的预测性能。
在训练组中，232例ICH患者死亡，708例存活。LASSO回归显示了一些预测因素，包括白细胞计数、血糖、血尿素氮、SII、格拉斯哥昏迷量表、年龄、心率、平均动脉压、红细胞、碳酸氢盐、红细胞分布宽度、肝硬化、呼吸衰竭、肾衰竭、恶性肿瘤、血管升压药和机械通气。建立了整合这些预测因素的预测模型。列线图在训练组中的曲线下面积（AUC）为0.810，在测试组中为0.822，表明该列线图可能具有良好的性能。
全身免疫炎症与ICU中ICH患者院内死亡风险增加相关。构建并验证了ICU中ICH患者院内死亡风险的列线图。
