Zou Jianyu, Chen Huihuang, Liu Cuiqing, Cai Zhenbin, Yang Jie, Zhang Yunlong, Li Shaojin, Lin Hongsheng, Tan Minghui
Department of Orthopaedics, The First Affiliated Hospital of Jinan University, Guangzhou, China.
Department of Rehabilitation, The First Affiliated Hospital of Jinan University, Guangzhou, China.
Front Neurosci. 2022 Aug 10;16:942100. doi: 10.3389/fnins.2022.942100. eCollection 2022.
Intracerebral hemorrhage (ICH) is a stroke syndrome with an unfavorable prognosis. Currently, there is no comprehensive clinical indicator for mortality prediction of ICH patients. The purpose of our study was to construct and evaluate a nomogram for predicting the 30-day mortality risk of ICH patients.
ICH patients were extracted from the MIMIC-III database according to the ICD-9 code and randomly divided into training and verification cohorts. The least absolute shrinkage and selection operator (LASSO) method and multivariate logistic regression were applied to determine independent risk factors. These risk factors were used to construct a nomogram model for predicting the 30-day mortality risk of ICH patients. The nomogram was verified by the area under the receiver operating characteristic curve (AUC), integrated discrimination improvement (IDI), net reclassification improvement (NRI), and decision curve analysis (DCA).
A total of 890 ICH patients were included in the study. Logistic regression analysis revealed that age (OR = 1.05, < 0.001), Glasgow Coma Scale score (OR = 0.91, < 0.001), creatinine (OR = 1.30, < 0.001), white blood cell count (OR = 1.10, < 0.001), temperature (OR = 1.73, < 0.001), glucose (OR = 1.01, < 0.001), urine output (OR = 1.00, = 0.020), and bleeding volume (OR = 1.02, < 0.001) were independent risk factors for 30-day mortality of ICH patients. The calibration curve indicated that the nomogram was well calibrated. When predicting the 30-day mortality risk, the nomogram exhibited good discrimination in the training and validation cohorts (C-index: 0.782 and 0.778, respectively). The AUCs were 0.778, 0.733, and 0.728 for the nomogram, Simplified Acute Physiology Score II (SAPSII), and Oxford Acute Severity of Illness Score (OASIS), respectively, in the validation cohort. The IDI and NRI calculations and DCA analysis revealed that the nomogram model had a greater net benefit than the SAPSII and OASIS scoring systems.
This study identified independent risk factors for 30-day mortality of ICH patients and constructed a predictive nomogram model, which may help to improve the prognosis of ICH patients.
脑出血（ICH）是一种预后不良的中风综合征。目前，尚无用于预测ICH患者死亡率的综合临床指标。本研究的目的是构建并评估一种预测ICH患者30天死亡风险的列线图。
根据ICD-9编码从MIMIC-III数据库中提取ICH患者，并随机分为训练队列和验证队列。应用最小绝对收缩和选择算子（LASSO）方法及多因素逻辑回归来确定独立危险因素。这些危险因素用于构建预测ICH患者30天死亡风险的列线图模型。通过受试者操作特征曲线下面积（AUC）、综合判别改善（IDI）、净重新分类改善（NRI）和决策曲线分析（DCA）对列线图进行验证。
本研究共纳入890例ICH患者。逻辑回归分析显示，年龄（OR = 1.05，P < 0.001）、格拉斯哥昏迷量表评分（OR = 0.91，P < 0.001）、肌酐（OR = 1.30，P < 0.001）、白细胞计数（OR = 1.10，P < 0.001）、体温（OR = 1.73，P < 0.001）、血糖（OR = 1.01，P < 0.001）、尿量（OR = 1.00，P = 0.020）和出血量（OR = 1.02，P < 0.001）是ICH患者30天死亡的独立危险因素。校准曲线表明列线图校准良好。在预测30天死亡风险时，列线图在训练队列和验证队列中均表现出良好的区分度（C指数分别为0.782和0.778）。在验证队列中，列线图、简化急性生理学评分II（SAPSII）和牛津急性疾病严重程度评分（OASIS）的AUC分别为0.778、0.733和0.728。IDI和NRI计算以及DCA分析显示，列线图模型比SAPSII和OASIS评分系统具有更大的净效益。
本研究确定了ICH患者30天死亡的独立危险因素，并构建了预测列线图模型，这可能有助于改善ICH患者的预后。
