AUTHOR=Jianling Qiang , Lulu Jin , Liuyi Qiu , Lanfang Feng , Xu Ma , Wenchen Li , Maofeng Wang 

TITLE=A nomogram for predicting the risk of pulmonary embolism in neurology department suspected PE patients: A 10-year retrospective analysis

JOURNAL=Frontiers in Neurology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2023.1139598

DOI=10.3389/fneur.2023.1139598

ISSN=1664-2295

ABSTRACT=Objective: The aim of this retrospective study was to establish a  nomogram for predicting the risk of pulmonary embolism (PE)  in neurology department patients. 
Methods: Totally 1578 subjects suspected PE at Neurology Department during January 2012 to December 2021 were considered in our study, and randomly divided into training cohort and validation cohort at a ratio of 7:3. The LASSO regression technique was used to select the optimal predictive features, and multivariate logistic regression to construct the predictive model, which was visualized by nomograms. The predictive performance of the model was evaluated based on discrimination, calibration, and clinical utility. 
Results: Our predictive model indicated that age, pulse, systolic pressure, hemoglobin (HGB), neutrophil count (N), low density lipoprotein (LDL), D-Dimer(DD), PO2, those eight variables that were associated with PE. The area under receiver operating characteristic curve (AUC) of the model was 0.750(95% CI 0.721-0.783), indicating that the model had a good differential diagnostic performance. Good consistency between predicted risk and observed actual risk was presented as the calibration curve. The decision curve analysis (DCA) curve showed that the model obtained a better net clinical benefit.
Conclusions: We developed a novel numerical model for selecting risk factors for PE in neurology department patients. Our findings may help decision-makers weigh the risk of PE and appropriately select PE prevention strategies.