Establishment and verification of a Nomogram model for individualized prediction of the risk of acute exacerbation COPD combined with pulmonary embolism
10.3760/cma.j.cn115682-20200720-04497
- VernacularTitle:个体化预测COPD急性加重期合并肺动脉栓塞风险Nomogram模型的建立与验证
- Author:
Zhenjuan XU
1
;
Min ZHOU
;
Lijuan ZHOU
Author Information
1. 江苏省泰州市人民医院呼吸与危重症医学科 225300
- Keywords:
Pulmonary disease, chronic obstructive;
Pulmonary embolism;
Risk factors;
Nomogram model
- From:
Chinese Journal of Modern Nursing
2021;27(10):1276-1282
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To construct a Nomogram model for individualized prediction of the risk of acute exacerbation chronic obstructive pulmonary disease (AECOPD) combined with pulmonary embolism (PE) , and verify the predictive ability of the model.Methods:This study is a cross-sectional study. We retrospectively analyzed the clinical data of 292 patients admitted to the hospital for AECOPD from January 2018 to January 2020.The data was divided into training set ( n=203) and validation set ( n=89) according to the order of admission. Single factor and Logistic regression were used to analyze independent risk factors of PE. The Nomogram prediction model was established, and the Bootstrap method was used to internal verification, and the external verification was verified by the validation set. Results:Age ≥70 years, bed time ≥7 days, history of deep vein thrombosis, circumference difference of both lower limbs ≥1 cm, partial pressure of carbon dioxide in artery decreased≥5 mmHg, and D-dimer ≥500 μg/L were independent risk factors for AECOPD combined with PE ( P<0.05) . Based on the above 6 risk factors, a Nomogram model for predicting AECOPD combined with PE was established. Calibration curve verification showed that the predicted values of the training set and the validation set were basically the same as the measured values. The receiver operating characteristic (ROC) curve verification showed that the C-index of the training set and the validation set were 0.879 and 0.774 respectively. Conclusions:The Nomogram model based on the independent risk factors of AECOPD combined with PE has high prediction accuracy.
