Related Experiment Video
Updated: Jul 13, 2026
A Multicenter MRI Protocol for the Evaluation and Quantification of Deep Vein Thrombosis
Published on: June 2, 2015
Efficacy of three predictive models for deep vein thrombosis in patients with lumbar disc herniation
Shuai Yang1, Qingfeng Guo1, Yaqing Xing1
1Department of Traditional Chinese Medicine, The First Hospital of Hebei Medical University Shijiazhuang 050091, Hebei, China.
Insights
This study developed predictive models for deep vein thrombosis (DVT) risk in lumbar disc herniation (LDH) patients. The Random Forest model demonstrated the best performance in predicting DVT occurrence.
Area of Science:
- Medical Informatics
- Clinical Medicine
- Biostatistics
Background:
- Lumbar disc herniation (LDH) patients face an increased risk of deep vein thrombosis (DVT).
- Accurate risk assessment is crucial for timely intervention and improved patient outcomes in LDH populations.
- Existing predictive tools may not fully capture the complexity of DVT risk in this specific patient group.
Purpose of the Study:
- To develop and evaluate machine learning-based predictive models for DVT risk in patients with LDH.
- To compare the performance of Logistic Regression, Gradient Boosting, and Random Forest models in predicting DVT.
- To identify key clinical indicators associated with DVT development in LDH patients.
Main Methods:
- A retrospective analysis of 798 LDH patients was conducted, with data split into training (n=558) and testing (n=240) sets.
- Univariate analysis identified significant clinical variables (age, platelets, cholesterol, triglycerides, HbA1c, D-dimer, fibrinogen, APTT, PT, TT) for model development.
- Three predictive models (Logistic Regression, Gradient Boosting, Random Forest) were built and assessed using ROC curves and calibration plots.
Main Results:
- Significant differences in age and various hematological parameters (PLT, TC, TG, HbA1c, D-D, FIB, APTT, PT, TT) were observed between DVT and non-DVT groups.
- In the training set, the Random Forest model achieved the highest Area Under the Curve (AUC) at 0.978, followed by Gradient Boosting (0.943) and Logistic Regression (0.919).
- The Random Forest model also showed superior performance in the test set (AUC=0.952), outperforming Gradient Boosting (0.941) and Logistic Regression (0.908).
Conclusions:
- The developed Logistic Regression, Gradient Boosting, and Random Forest models demonstrate significant predictive value for DVT in LDH patients.
- These models can aid in optimizing clinical management strategies for DVT prevention in this cohort.
- The Random Forest model exhibited the strongest predictive capability among the evaluated models.
Objective:
To develop predictive models for assessing deep vein thrombosis (DVT) risk among lumbar disc herniation (LDH) patients and evaluate their performances.
Methods:
A retrospective study was conducted on 798 LDH patients treated at the First Hospital of Hebei Medical University from January 2017 to December 2023. The patients were divided into a training set (n = 558) and a test set (n = 240) using computer-generated random numbers in a ratio of 7:3. Patients without DVT in the training set were categorized as the non-DVT group (n = 463), while those diagnosed with DVT were the DVT group (n = 95). Univariate analysis was performed to compare clinical data between the two groups. Data with statistical significance were used for the development of a Logistic regression model, Gradient boosting model, and Random Forest model. Model performance was evaluated through receiver operating characteristic (ROC) curve analysis and calibration curve assessment.
Results:
In the training set, univariate analysis revealed significant differences in age, platelets (PLT), cholesterol (TC), triglycerides (TG), glycated hemoglobin (HbAlc), D-dimer (D-D), fibrinogen (FIB), activated partial thromboplastin time (APTT), prothrombin time (PT), and thrombin time (TT) between the non-DVT group and the DVT group (all P<0.05). Predictive models were constructed based on these indicators. The areas under the ROC curves (AUCs) in the training set were as follows (in descending order): Random Forest model (0.978) > Gradient boosting model (0.943) > Logistic regression model (0.919). In the test set, the AUCs were: Random Forest model (0.952) > Gradient boosting model (0.941) > Logistic regression model (0.908). The DeLong test indicated that the AUC of the Random Forest model in the training set was significantly higher than that of the Logistic regression model (P<0.05); however, no significant difference was observed between the other two models. Calibration curves demonstrated that the predictive probabilities from all three models closely aligned with actual DVT incidence in both sets.
Conclusion:
The Logistic regression model, Gradient boosting model, and Random Forest model constructed in this study exhibit good predictive value for the occurrence of DVT in LDH patients, aiding in the optimization of clinical management of clinical management. Among them, the Random Forest model performed the best of the three.
Related Concept Videos
01:20Venous Thrombosis II: Clinical Manifestations and Diagnostic Studies
01:29Venous Thrombosis III: Interprofessional Care
01:29Herniated Intervertebral Disc l: Introduction