Construction of a Risk Prediction Model for Hospital-Acquired Pulmonary Embolism in Hospitalized Patients.
Construction of a Risk Prediction Model for Hospital-Acquired Pulmonary Embolism in Hospitalized Patients.
复制标题
在住院的患者中为医院获得的肺栓塞建造风险预测模型。
DOI：
10.1177/10760296211040868
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Li J
中科院分区：
文献类型：
--
作者：
Hou L;Hu L;Gao W;Sheng W;Hao Z;Chen Y;Li J
本研究的目的是建立一种基于机器学习（ML）方法的新型肺栓塞（PE）风险预测模型，并评估模型的预测性能以及各变量对预测性能的贡献。我们在上海市第十人民医院进行了一项回顾性研究，收集了2014年1月1日至2018年12月31日期间接受肺部计算机断层成像的住院患者的临床数据。我们训练了几个机器学习模型，包括逻辑回归（LR）、支持向量机（SVM）、随机森林（RF）和梯度增强决策树（GBDT），并将这些模型与代表性的基线算法进行了比较，并研究了它们的可预测性和特征解释。共纳入3619例患者。我们发现GBDT模型的预测效果最好，曲线下面积为0.799，而RF、LR和SVM模型的预测面积分别为0.791、0.716和0.743。GBDT、LR、RF和SVM模型的敏感性分别为63.9%、68.1%、71.5%和75%；特异性分别为81.1%、66.1%、72.7%、65.1%；准确率分别为77.8%、66.5%、72.5%、67%。我们发现，最大d -二聚体水平对预后预测贡献最大，其次是血浆纤维蛋白原水平的极端增长率、住院时间和d -二聚体水平的极端增长率。本研究证明了GBDT模型在预测住院患者PE发生风险方面的优越性。然而，为了应用于临床实践，为临床决策提供支持，还需要对模型的预测性能进行前瞻性验证。
The purpose of this study is to establish a novel pulmonary embolism (PE) risk prediction model based on machine learning (ML) methods and to evaluate the predictive performance of the model and the contribution of variables to the predictive performance. We conducted a retrospective study at the Shanghai Tenth People's Hospital and collected the clinical data of in-patients that received pulmonary computed tomography imaging between January 1, 2014 and December 31, 2018. We trained several ML models, including logistic regression (LR), support vector machine (SVM), random forest (RF), and gradient boosting decision tree (GBDT), compared the models with representative baseline algorithms, and investigated their predictability and feature interpretation. A total of 3619 patients were included in the study. We discovered that the GBDT model demonstrated the best prediction with an area under the curve value of 0.799, whereas those of the RF, LR, and SVM models were 0.791, 0.716, and 0.743, respectively. The sensibilities of the GBDT, LR, RF, and SVM models were 63.9%, 68.1%, 71.5%, and 75%, respectively; the specificities were 81.1%, 66.1, 72.7%, and 65.1%, respectively; and the accuracies were 77.8%, 66.5%, 72.5%, and 67%, respectively. We discovered that the maximum D-dimer level contributed the most to the outcome prediction, followed by the extreme growth rate of the plasma fibrinogen level, in-hospital duration, and extreme growth rate of the D-dimer level. The study demonstrates the superiority of the GBDT model in predicting the risk of PE in hospitalized patients. However, in order to be applied in clinical practice and provide support for clinical decision-making, the predictive performance of the model needs to be prospectively verified.
登录
查看更多内容
DOI：
10.1016/j.jvsv.2017.08.015
发表时间：
2018-01-01
影响因子：
3.2
作者：
Huynh, Nancy;Fares, Wassim H.;Chaar, Cassius Lyad Ochoa
通讯作者：
Chaar, Cassius Lyad Ochoa
影响因子：
--
作者：
Ferroni P;Zanzotto FM;Scarpato N;Riondino S;Guadagni F;Roselli M
通讯作者：
Roselli M
影响因子：
81.5
作者：
Huisman, Menno V.;Barco, Stefano;Klok, Frederikus A.
通讯作者：
Klok, Frederikus A.
影响因子：
9.6
作者：
CVITANIC, O;MARINO, PL
通讯作者：
MARINO, PL
影响因子：
5.9
作者：
Miniati, M;Monti, S;Bottai, M
通讯作者：
Bottai, M