Related Experiment Videos
Explainable machine learning for predicting venous thromboembolism in septic shock patients
Yuanyuan Li1, Qi Xin1, Yizhao Lu1
1Department of Emergency Surgery, Shaanxi Provincial People's Hospital, Xi'an, China.
Frontiers in Immunology
|August 4, 2026
Summary
This study developed an explainable machine learning model to predict venous thromboembolism (VTE) in septic shock patients. The Random Forest model accurately identifies high-risk individuals using routine clinical biomarkers, aiding thromboprophylaxis decisions.
Area of Science:
- Critical Care Medicine
- Data Science in Healthcare
- Thrombosis Research
Background:
- Venous thromboembolism (VTE) is a common complication in septic shock patients.
- Current risk stratification tools for VTE in this population are limited.
- Developing precise, individualized prediction models is crucial for effective management.
Purpose of the Study:
- To develop and externally validate an explainable machine learning (ML) framework for predicting VTE in adult patients with septic shock.
- To identify key clinical predictors of VTE in this high-risk group.
- To enhance transparency in ML-based risk prediction for clinical decision support.
Main Methods:
- A retrospective cohort study included 733 patients for development and 257 for external validation.
- Boruta algorithm and recursive feature elimination identified six key predictors: FDP, PT, WBC, APTT, D-dimer, and CRP.
- Six ML algorithms were trained, with Random Forest (RF) selected for its performance, and SHAP values used for interpretability.
Main Results:
- VTE incidence was 17.74% in the development cohort.
- The RF model achieved high accuracy in external validation (AUC 0.9718, F1 score 0.7917).
- SHAP analysis highlighted the role of thrombo-inflammatory markers and coagulation times in VTE risk.
Conclusions:
- A highly accurate and interpretable RF-based model for VTE prediction in septic shock was successfully developed.
- This tool utilizes routine biomarkers and provides transparent risk assessment, potentially aiding thromboprophylaxis decisions.
- Further prospective studies are needed to confirm clinical utility and impact on patient outcomes.
Related Concept Videos
01:29Venous Thrombosis III: Interprofessional Care
Venous thrombosis requires effective prevention and treatment strategies to improve patient outcomes and reduce potential complications.Prevention StrategiesHealthcare providers must prioritize preventing venous thromboembolism (VTE) for all adult patients upon admission. Interventions depend on bleeding and thrombosis risk, medical history, current medications, diagnoses, planned procedures, and patient preferences. Patients on bed rest should change positions every two hours and, if not...
01:20Venous Thrombosis II: Clinical Manifestations and Diagnostic Studies
The key difference between Superficial Vein Thrombosis (SVT) and Deep Vein Thrombosis (DVT) lies in their location and severity.Clinical ManifestationsSVT typically presents with localized pain, tenderness, and redness along the course of a superficial vein, often accompanied by a palpable, cord-like structure under the skin. This condition is usually less dangerous than DVT but can be uncomfortable and may lead to complications such as cellulitis or, rarely, a clot extension into the deep...
01:30Venous Thrombosis I: Introduction
Venous thrombosis, the most common disorder of the veins, involves the formation of a thrombus or blood clot associated with vein inflammation. It can be classified as either superficial vein thrombosis or deep vein thrombosis.Superficial Vein Thrombosis: This involves the formation of a thrombus in a superficial vein, usually the greater or lesser saphenous vein. Though less severe than deep vein thrombosis (DVT), SVT can lead to complications if untreated.Deep Vein Thrombosis (DVT): This...