Objective:

To develop and validate a prediction model for lower extremity deep vein thrombosis risk in elderly patients with intracerebral hemorrhage.

Approach:

• Data Collection: Demographic variables, clinical features, and laboratory parameters were retrospectively collected from elderly intracerebral hemorrhage patients.
• Model Development: Multiple imputation was used for missing values; LASSO regression was employed for feature selection followed by multivariable logistic regression to construct the prediction model and a nomogram.
• Model Assessment: Model performance was evaluated using ROC curve, calibration curve, decision curve analysis, and clinical impact curve.

Key Findings:

• Five potential predictors identified: logDFR, D-dimer, eGFR, GCS, and infection.
• Final model included four independent predictors: logDFR (OR 1.84, 95% CI 1.28–2.63), eGFR (OR 1.01, 95% CI 1.00–1.02), GCS (OR 0.87, 95% CI 0.79–0.96), and infection (OR 2.20, 95% CI 1.05–4.63).
• Model had an AUC of 0.819, indicating good discrimination.
• Moderate overestimation of risk was noted in calibration assessment.

Interpretation:

Limitations:

• Study conducted at a single center, which may limit generalizability.
• Retrospective design may introduce bias.

Conclusion:

An effective prediction model was developed for estimating the risk of lower extremity deep vein thrombosis in elderly patients with intracerebral hemorrhage.