What question did this study set out to answer?

The study aims to develop a machine learning model to predict post-thrombotic syndrome in unprovoked deep vein thrombosis using clinical risk factors and uric acid.

January 10, 2026European journal of medical research0 citationsOpen Access

Machine learning-based prediction of post-thrombotic syndrome in unprovoked lower extremity deep vein thrombosis: a two-center study incorporating uric acid and clinical risk factors

YLYajing LiCapital Medical University HDHongru DengCapital Medical University YGYongquan GuCapital Medical University

Key Result

The machine learning model, particularly the SVM algorithm, effectively predicts post-thrombotic syndrome using uric acid and clinical risk factors.

Key Points

The study aims to develop a machine learning model to predict post-thrombotic syndrome in unprovoked deep vein thrombosis using clinical risk factors and uric acid.
Two-center study design
Implementation of machine learning algorithms, specifically support vector machine
Assessment of clinical risk factors and uric acid levels in risk stratification
The machine learning model showed high prediction accuracy for post-thrombotic syndrome.
The support vector machine algorithm outperformed other machine learning algorithms.
Incorporating uric acid and treatment timing improved risk assessment.

Structured PICO

Can machine learning models incorporating uric acid and clinical risk factors accurately predict post-thrombotic syndrome in patients with unprovoked lower extremity deep vein thrombosis?

Population

265 patients with their first episode of unprovoked lower extremity deep vein thrombosis (LEDVT), hospitalized between January 2016 and January 2023 at two centers in China.

Intervention

Machine learning-based prediction models (10 algorithms, including SVM, XGBoost, LightGBM) incorporating uric acid and clinical risk factors

Outcome

Development of post-thrombotic syndrome (PTS)

Machine learning models, particularly SVM, incorporating uric acid and clinical risk factors can accurately predict the development of post-thrombotic syndrome in patients with unprovoked lower extremity deep vein thrombosis.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

The model of machine learning shows a great capacity in prediction of PTS, and had high prediction accuracy, the SVM algorithm predicted better than other algorithms. Addition of uric acid and timing of treatment refines risk stratification. The tool developed might assist clinicians in early identification and risk stratification of patients for individualized care.

Ask AI

Helpful

Bookmark

View Full Paper