Lin J, Zhang Y, Lin W, Meng Y. Development and Validation of a Risk Assessment Model for Venous Thromboembolism in Patients With Invasive Mechanical Ventilation.
Cureus 2022;
14:e27164. [PMID:
36017277 PMCID:
PMC9393746 DOI:
10.7759/cureus.27164]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 07/23/2022] [Indexed: 12/04/2022] Open
Abstract
Background
Patients with invasive mechanical ventilation may be at high risk of acquiring venous thromboembolism (VTE). We aim to develop risk assessment models for predicting the improvement of VTE in invasively ventilated patients.
Methodology
A total of 6,734 invasively ventilated patients enrolled from the Medical Information Mart for Intensive Care-III (MIMIC-III) database were used as input for model development and internal validation, while data from 168 patients from Nanfang Hospital were used for external validation. Logistic regression was performed based on predictive factors derived from least absolute shrinkage and selection operator (LASSO) regression analysis and logistic regression with backward selection to develop two Risk Assessment Models (RAM), namely, I and II, for the prediction of VTE, respectively. Model selection was performed by evaluation of the area under the receiver operating characteristic curve (AUC), the goodness of fit with calibration curves, and decision curve analyses (DCA).
Results
RAM-I included prior history of VTE, in-hospital immobilization, infection, glucose, the use of antiplatelet, and activated partial thromboplastin time (APTT) as variables, while RAM-II included prior history of VTE, in-hospital immobilization, infection, ischemic stroke, glucose, the use of antiplatelet and APTT as variables. Compared with RAM-I and ICU-Venous Thromboembolism Score, RAM-II exhibited better discrimination in the training dataset (AUC = 0.826), internal validation dataset (AUC = 0.771), and external validation dataset (AUC = 0.770). Additionally, DCA demonstrated that RAM-II was clinically beneficial. Inspection of the calibration curves revealed good agreement between the predictions and observations.
Conclusions
A RAM for VTE in invasively ventilated patients was developed with reasonable performance.
Collapse