Yang Jian-Yue, Li Li-Li, Fu Su-Zhen
Department of Critical Care Medicine, Xingtai People's Hospital, Hebei, 054001, China.
BMC Infect Dis. 2025 Apr 21;25(1):573. doi: 10.1186/s12879-025-10972-w.
Sepsis-induced coagulopathy (SIC) is a severe complication of sepsis, characterized by poor prognosis and high mortality. However, the predictive factors for the development of SIC in sepsis patients remain to be determined. The aim of this study was to develop an easy-to-use and efficient nomogram for predicting the risk of sepsis patients developing SIC in the intensive care unit (ICU), based on common indicators and complications observed at admission.
A total of 12, 455 sepsis patients from the MIMIC database were screened and randomly divided into training and validation cohorts. In the training cohort, LASSO regression was used for variable selection and regularization. The selected variables were then incorporated into a multivariable logistic regression model to construct the nomogram for predicting the risk of sepsis patients developing sepsis-induced coagulopathy (SIC). The model's predictive performance was evaluated using the area under the receiver operating characteristic curve (AUC), and its calibration was assessed through a calibration curve. Additionally, decision curve analysis (DCA) was performed to evaluate the clinical applicability of the model. External validation was conducted using data from the ICU database of Xingtai People's Hospital.
Among the 12, 455 sepsis patients, 5, 145 (41. 3%) developed SIC. The occurrence of SIC was significantly associated with the SOFA score, red blood cell count, red cell distribution width (RDW), white blood cell count, platelet count, INR, and lactate levels. Additionally, hypertension was identified as a potential protective factor. A nomogram was developed to predict the risk of SIC, which showed an AUC of 0. 81 (95% CI: 0. 79-0. 83) in the training set, 0. 83 (95% CI: 0. 82-0. 84) in the validation set, and 0. 79 (95% CI: 0. 74-0. 84) in the external validation. The calibration curve of the nomogram showed good consistency between the observed and predicted probabilities of SIC.
The novel nomogram demonstrates excellent predictive performance for the incidence of SIC in ICU patients with sepsis and holds promise for assisting clinicians in early identification and intervention of SIC.
Not applicable.
脓毒症诱导的凝血病（SIC）是脓毒症的一种严重并发症，其特征为预后不良和高死亡率。然而，脓毒症患者发生SIC的预测因素仍有待确定。本研究的目的是基于入院时观察到的常见指标和并发症，开发一种易于使用且高效的列线图，用于预测重症监护病房（ICU）中脓毒症患者发生SIC的风险。
从MIMIC数据库中筛选出12455例脓毒症患者，并随机分为训练队列和验证队列。在训练队列中，使用LASSO回归进行变量选择和正则化。然后将所选变量纳入多变量逻辑回归模型，以构建预测脓毒症患者发生脓毒症诱导凝血病（SIC）风险的列线图。使用受试者操作特征曲线下面积（AUC）评估模型的预测性能，并通过校准曲线评估其校准情况。此外，进行决策曲线分析（DCA）以评估模型的临床适用性。使用邢台市人民医院ICU数据库的数据进行外部验证。
在12455例脓毒症患者中，5145例（41.3%）发生了SIC。SIC的发生与序贯器官衰竭评估（SOFA）评分、红细胞计数、红细胞分布宽度（RDW）、白细胞计数、血小板计数、国际标准化比值（INR）和乳酸水平显著相关。此外，高血压被确定为潜在的保护因素。开发了一种预测SIC风险的列线图，其在训练集中的AUC为0.81（95%置信区间：0.79 - 0.83），在验证集中为0.83（95%置信区间：0.82 - 0.84），在外部验证中为0.79（95%置信区间：0.74 - 0.84）。列线图的校准曲线显示SIC的观察概率和预测概率之间具有良好的一致性。
新型列线图对ICU脓毒症患者SIC的发生率具有出色的预测性能，有望协助临床医生早期识别和干预SIC。
不适用。
