Machine learning-based prediction model of lower extremity deep vein thrombosis after stroke

被引:0
|
作者
Liu, Lingling [1 ]
Li, Liping [1 ]
Zhou, Juan [2 ]
Ye, Qian [1 ]
Meng, Dianhuai [1 ]
Xu, Guangxu [1 ]
机构
[1] Nanjing Med Univ, Affiliated Hosp 1, Dept Rehabil Med, 300 Guangzhou Rd, Nanjing 210029, Peoples R China
[2] Nanjing Med Univ, Affiliated Hosp 1, Dept Ultrasonog, 300 Guangzhou Rd, Nanjing 210029, Peoples R China
关键词
Machine learning; Stroke; DVT; Prediction model; VENOUS THROMBOEMBOLISM RISK; MANAGEMENT;
D O I
10.1007/s11239-024-03010-0
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
This study aimed to apply machine learning (ML) techniques to develop and validate a risk prediction model for post-stroke lower extremity deep vein thrombosis (DVT) based on patients' limb function, activities of daily living (ADL), clinical laboratory indicators, and DVT preventive measures. We retrospectively analyzed 620 stroke patients. Eight ML models-logistic regression (LR), support vector machine (SVM), random forest (RF), decision tree (DT), neural network (NN), extreme gradient boosting (XGBoost), Bayesian (NB), and K-nearest neighbor (KNN)-were used to build the model. These models were extensively evaluated using ROC curves, AUC, PR curves, PRAUC, accuracy, sensitivity, specificity, and clinical decision curves (DCA). Shapley's additive explanation (SHAP) was used to determine feature importance. Finally, based on the optimal ML algorithm, different functional feature set models were compared with the Padua scale to select the best feature set model. Our results indicated that the RF algorithm demonstrated superior performance in various evaluation metrics, including AUC (0.74/0.73), PRAUC (0.58/0.58), accuracy (0.75/0.77), and sensitivity (0.78/0.80) in both the training set and test set. DCA analysis revealed that the RF model had the highest clinical net benefit. SHAP analysis showed that D-dimer had the most significant influence on DVT, followed by age, Brunnstrom stage (lower limb), prothrombin time (PT), and mobility ability. The RF algorithm can predict post-stroke DVT to guide clinical practice. Stroke patients often have issues expressing DVT symptoms due to impaired consciousness, cognition, or sensation. The Padua scale is not well-suited for stroke patients. A DVT web calculator was created using machine learning algorithms based on limb function and daily mobility abilities. A flowchart was developed to assess the risk of lower extremity DVT after stroke, providing valuable clinical guidance.
引用
收藏
页码:1133 / 1144
页数:12
相关论文
共 50 条
  • [1] Machine learning-based model for prediction of deep vein thrombosis after gynecological laparoscopy: A retrospective cohort study
    Chen, Xiao
    Hou, Min
    Wang, Dongxue
    MEDICINE, 2024, 103 (01) : E36717
  • [2] Construction and verification of a machine learning-based prediction model of deep vein thrombosis formation after spinal surgery
    Wu, Xingyan
    Wang, Zhao
    Zheng, Leilei
    Yang, Yihui
    Shi, Wenyan
    Wang, Jing
    Liu, Dexing
    Zhang, Yi
    INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS, 2024, 192
  • [3] Prediction model of deep vein thrombosis risk after lower extremity orthopedic surgery
    Zhang, Jiannan
    Shao, Yang
    Zhou, Hongmei
    Li, Ronghua
    Xu, Jie
    Xiao, Zhongzhou
    Lu, Lu
    Cai, Liangyu
    HELIYON, 2024, 10 (09)
  • [4] Machine Learning-Based Screening of Risk Factors and Prediction of Deep Vein Thrombosis and Pulmonary Embolism After Hip Arthroplasty
    Ding, Ruifeng
    Ding, Yu
    Zheng, Dongyu
    Huang, Xingshuai
    Dai, Jingya
    Jia, Hui
    Deng, Mengqiu
    Yuan, Hongbin
    Zhang, Yijue
    Fu, Hailong
    CLINICAL AND APPLIED THROMBOSIS-HEMOSTASIS, 2023, 29
  • [5] A deep learning-based model for prediction of hemorrhagic transformation after stroke
    Jiang, Liang
    Zhou, Leilei
    Yong, Wei
    Cui, Jinluan
    Geng, Wen
    Chen, Huiyou
    Zou, Jianjun
    Chen, Yang
    Yin, Xindao
    Chen, Yu-Chen
    BRAIN PATHOLOGY, 2023, 33 (02)
  • [6] Analysis of risk factors and construction of prediction model for lower extremity deep vein thrombosis after liver transplantation
    Xiao, Yang
    Guo, Ran
    Yang, Haitao
    Geng, Xiaoyong
    EUROPEAN JOURNAL OF MEDICAL RESEARCH, 2025, 30 (01)
  • [7] Prediction and Risk Factors of Lower Extremity Deep Vein Thrombosis after Total Joint Arthroplasty
    Wang, Zhenhua
    Liu, Zhiwei
    Tian, Zhaoxing
    TOHOKU JOURNAL OF EXPERIMENTAL MEDICINE, 2025, 265 (03): : 113 - 121
  • [8] Analysis of risk factors and establishment of prediction model for lower extremity deep vein thrombosis after lumbar fusion surgery
    Zhao, Yixiang
    Kong, Xiangzhen
    Song, Kangle
    Liu, Zhenchuan
    Zhang, Yuanqiang
    Cheng, Lei
    BMC SURGERY, 2024, 24 (01)
  • [9] Risk of deep vein thrombosis and pulmonary embolism after heart transplantation: clinical outcomes comparing upper extremity deep vein thrombosis and lower extremity deep vein thrombosis
    Elboudwarej, Omeed
    Patel, Jignesh K.
    Liou, Frank
    Rafiei, Matthew
    Osborne, Ashley
    Chai, Wanxing
    Kittleson, Michelle
    Czer, Lawrence
    Stern, Lily
    Esmailian, Fardad
    Kobashigawa, Jon A.
    CLINICAL TRANSPLANTATION, 2015, 29 (07) : 629 - 635
  • [10] Comparison of different machine learning classification models for predicting deep vein thrombosis in lower extremity fractures
    Wei, Conghui
    Wang, Jialiang
    Yu, Pengfei
    Li, Ang
    Xiong, Ziying
    Yuan, Zhen
    Yu, Lingling
    Luo, Jun
    SCIENTIFIC REPORTS, 2024, 14 (01)