Construction and validation of short-term and long-term prognosis prediction models for in-hospital cardiac arrest patients
10.3969/j.issn.1673-9701.2025.31.009
- VernacularTitle:院内心脏骤停患者短期及远期预后预测模型的构建与验证
- Author:
Gaosheng ZHOU
1
;
Yayuan TAN
;
Yulan ZHANG
;
Wen WU
;
Rong ZHANG
Author Information
1. 三峡大学第一临床医学院/宜昌市中心人民医院重症医学科,湖北宜昌 443003;宜昌市脓毒症临床研究中心,湖北宜昌 443003;三峡大学第一临床医学院/宜昌市中心人民医院医务部,湖北宜昌 443003
- Publication Type:Journal Article
- Keywords:
In-hospital cardiac arrest;
Prognostic model;
Nomogram
- From:
China Modern Doctor
2025;63(31):43-49
- CountryChina
- Language:Chinese
-
Abstract:
Objective To construct a prognostic model for patients with in-hospital cardiac arrest(CA)to evaluate their short-term and long-term prognosis and provide a reference for clinical decision-making.Methods Data of in-hospital CA patients were extracted from the Medical Information Mart for Intensive Care Ⅳ 2.2 database,and randomly divided into training set and validation set at a 7∶3 ratio.A predictive nomogram model was constructed in the training set via multivariate COX regression analysis,and internally validated using the validation set.Results A total of 1787 patients were included(1250 in training set and 537 in validation set).Univariate regression,LASSO regression,and multivariate COX regression analyses identified age,body weight,base excess,red cell volume distribution width,model for end-stage liver disease,acute physiology and chronic health evaluation,systemic inflammatory response index,dopamine,norepinephrine,congestive heart failure,diabetes with complications,and metastatic solid tumor were all independent risk factors affecting the prognosis of patients with CA.The receiver operating characteristic curve of the constructed nomogram showed good discrimination,and the decision curve analysis indicated that it had good clinical applicability.Conclusion The constructed nomogram model has certain clinical application value in identifying populations with good and poor prognosis,providing an auxiliary reference for the termination of resuscitation and post-resuscitation treatment.
