Development and Validation of an Interpretable Machine Learning Model for Predicting Venous Thromboembolism（VTE）in Intensive Care Unit (ICU) Patients

Venous thromboembolism remains a leading cause of preventable mortality in intensive care unit (ICU) patients. Existing risk-stratification tools were developed in general medical populations and lack ICU-specific predictors. This study was to develop and validate an interpretable machine learning (ML) model to predict VTE in ICU patients.

Study Overview

• Status: Completed
• Conditions: Venous Thromboembolism; Prediction Models
• Intervention / Treatment: Other: no intervention

• Study Type: Observational
• Enrollment (Actual): 12061

Contacts and Locations

Study Locations

• China
  • Beijing Municipality
    • Beijing, Beijing Municipality, China, 102218
      • Beijing Tsinghua Changgung Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Patients admitted to ICU were included in the study cohort from January 2022 to October 2025. Inclusion criteria were: (1) age ≥18 years; (2) ICU length of stay ≥48 hours; (3) only the first ICU admission per patient was retained. Exclusion criteria were: (1) VTE diagnosed prior to ICU admission; (2) VTE diagnosed within 24 hours of ICU admission; (3) >20% missing values in key variables. The final cohort comprised 12,061 patients, of whom 587 (4.9%) developed VTE during ICU hospitalization.

Description

Inclusion Criteria:

• age ≥18 years;
• ICU length of stay ≥48 hour
• the first ICU admission

Exclusion Criteria:

• VTE diagnosed prior to ICU admission
• VTE diagnosed within 24 hours of ICU admission
• >20% missing values in key variables

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Time Frame
validate an interpretable machine learning (ML) model to predict VTE in ICU patients	the first day after the patients leaf ICU

Collaborators and Investigators

• Sponsor: Beijing Tsinghua Chang Gung Hospital

Study record dates

Study Major Dates

• Study Start (Actual): January 1, 2022
• Primary Completion (Actual): December 31, 2025
• Study Completion (Actual): December 31, 2025

Study Registration Dates

• First Submitted: May 12, 2026
• First Submitted That Met QC Criteria: May 18, 2026
• First Posted (Actual): May 19, 2026

Study Record Updates

• Last Update Posted (Actual): May 19, 2026
• Last Update Submitted That Met QC Criteria: May 18, 2026
• Last Verified: January 1, 2022

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Vascular Diseases; Cardiovascular Diseases; Embolism and Thrombosis; Thromboembolism; Venous Thromboembolism
• Other Study ID Numbers: 19242-2-01

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No