深静脉血栓患者入院时合并肺栓塞的早期预测模型
本研究回顾性收集深静脉血栓(DVT)患者数据,利用LASSO回归筛选变量并构建多因素logistic回归模型,用于入院时早期识别合并肺栓塞(PE)。模型纳入女性、高血压、心血管疾病、骨折、年龄、D-二聚体和髂静脉压迫百分比七个预测因子,训练集AUC为0.727(95%CI 0.667-0.787),验证集AUC为0.707(95%CI 0.611-0.803),校准良好,决策曲线分析显示在18%至80%阈值概率范围内有净获益。
要点
- 模型含女性、高血压、心血管病、骨折、年龄、D-二聚体、髂静脉压迫百分比七个预测因子。
- 训练集AUC 0.727,验证集AUC 0.707,校准良好。
- 决策曲线分析显示阈值概率18%至80%范围内有净获益。
核心结论
- 构建的预测模型校准良好且具有 discriminative power,可用于评估DVT患者合并PE的风险。
- 该模型有助于在获得确定性CT血管造影结果前早期估计PE概率,支持及时管理流程。
研究设计与样本
- 回顾性收集确诊DVT患者队列数据,包括基线人口学、临床特征、实验室参数和基于影像的髂静脉压迫测量。
- 采用LASSO回归筛选变量,多因素logistic回归构建预测模型,并绘制列线图。
- 患者随机分为开发数据集(69.8%,143例有PE和130例无PE)和验证数据集(30.2%,63例有PE和55例无PE)用于模型构建和内部验证。
主要发现
- LASSO回归识别出七个预测因子:女性、高血压、心血管疾病、骨折、年龄、D-二聚体和髂静脉压迫百分比,均纳入列线图。
- 模型在训练集的AUC为0.727(95%CI 0.667-0.787),在验证集的AUC为0.707(95%CI 0.611-0.803)。
- 模型校准良好,决策曲线分析显示在阈值概率18%至80%范围内预测PE有净获益。
关键数值与推荐
- 预测因子包括女性、高血压、心血管疾病、骨折、年龄、D-二聚体和髂静脉压迫百分比。
- 训练集AUC 0.727(95%CI 0.667-0.787),验证集AUC 0.707(95%CI 0.611-0.803)。
- 决策曲线分析净获益的阈值概率范围为18%至80%。
临床怎么用
- 对于入院的DVT患者,可使用该模型基于常规临床和实验室指标早期估计合并PE的概率。
- 在等待CT血管造影确诊前,模型结果可辅助临床决策和及时管理。
局限性
- 本研究为回顾性队列研究,仅进行内部验证,未进行外部验证。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVE: To develop and validate a predictive model for the early identification of concomitant pulmonary embolism (PE) in patients with deep vein thrombosis (DVT) upon hospital admission. METHODS: We retrospectively collected data from a cohort of patients diagnosed with DVT, including baseline demographics, clinical characteristics, laboratory parameters, and imaging-based measurements of compression of the iliac vein to develop a predictive model. The least absolute shrinkage and selection operator regression, widely used in clinical decision-making algorithms for its ability to perform variable selection and regularization simultaneously, was used for variables selection. A multivariate logistic regression was then conducted to construct a predictive model. The model's discriminatory ability was assessed using the area under the curve. Calibration analysis and decision curve analysis were performed. RESULTS: Patients were randomly divided into a development dataset (69.8% [143 with PE and 130 without PE]) and a validation dataset (30.2% [63 with PE and 55 without PE]) for model construction and internal validation. Seven predictors, including female gender, hypertension, cardiovascular disease, fracture, age, D-dimer, and compression of the iliac vein percentage were identified by least absolute shrinkage and selection operator regression and finally incorporated into the nomogram. The model achieved an area under the curve of 0.727 (95% confidence interval, 0.667-0.787) in the training set, and 0.707 (95% confidence interval, 0.611-0.803) in the validation set. The model was well-calibrated, and decision curve analysis demonstrated a net benefit for predicting PE at threshold probabilities ranged between 18% and 80%. CONCLUSIONS: A novel predictive model with strong calibration and discriminative power was developed for assessing concomitant PE risk in patients with DVT. This model may facilitate early estimating of PE probability before obtaining definitive CT angiography results and support timely management processes.
引用
- Gong M, Jiang R, Guo K, et al. A predictive model for early detection of concomitant pulmonary embolism in patients with deep vein thrombosis immediately upon hospital admission. J Vasc Surg Venous Lymphat Disord. 2025. PMID: 40752891. doi:10.1016/j.jvsv.2025.102299
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。