Temporal validation of the electronic health record cancer-associated thrombosis model in patients with low bleeding risk

Sep 22, 2026

Background: The electronic health record cancer-associated thrombosis (EHR-CAT) model predicts cancer-associated venous thromboembolism (VTE), and prior validations often depended on cancer registry data with reporting delays. Objectives: This study aimed for external temporal validation of EHR-CAT in low-bleeding-risk patients using contemporary Veterans Affairs electronic health record data. Methods: A retrospective cohort from 2017–2024 evaluated EHR-CAT without cancer registry inputs, applying exclusions to minimize bleeding risk. Results: 6-month VTE incidence was 5.4% with C-statistic 0.67 and calibration slope 0.876. Conclusion: Performance was comparable across therapy lines to earlier studies.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Abstract

Background

Objectives

Methods

Results

Conclusion

Essentials

Keywords

Introduction

VTE burden in cancer and prophylaxis tradeoffs

EHR-CAT model and prior validation gaps

[https://doi.org/10.1016/j.rpth.2026.106830](https://doi.org/10.1016/j.rpth.2026.106830) BRIEF REPORT Temporal validation of the electronic health record cancer-associated thrombosis model in patients with low bleeding risk Jennifer La 1, 2, 3 | Omid Jafari4 | Kaelyn Nannini1 | Nhan V. Do1, 5 | Mary T. Brophy1, 2 | Nathanael R. Fillmore1, 2, 3, 6 | Ang Li4 1Massachusetts Veterans Epidemiology Research and Information Center, Veterans Affairs Boston Healthcare System, Boston, Massachusetts, USA 2Section of Hematology & Medical Oncology, Department of Medicine, Boston University School of Medicine, Boston, Massachusetts, USA 3Veterans Affairs Boston Healthcare System, Department of Medicine, Harvard Medical School, Boston, Massachusetts, USA 4Section of Hematology-Oncology, Department of Medicine, Baylor College of Medicine, Houston, Texas, USA 5Section of General Internal Medicine, Department of Medicine, Boston University School of Medicine, Boston, Massachusetts, USA 6Department of Medical Oncology, DanaFarber Cancer Institute, Boston, Massachusetts, USA Correspondence Ang Li, Section of Hematology-Oncology, Department of Medicine, Baylor College of Medicine, One Baylor Plaza, 011DF, Houston, TX 77030, USA. Email: [ang.li2@bcm.edu](ang.li2@bcm.edu) Handling Editor: Professor Michael Makris Abstract Background: The electronic health record cancer-associated thrombosis (EHR-CAT) model was derived to predict cancer-associated venous thromboembolism (VTE). Prior validations often relied on cancer registry data with reporting delays. Objectives: We aimed to perform an external temporal validation of the EHR-CAT model among patients at low risk of bleeding using contemporary Veterans Affairs electronic health record data. Methods: We conducted a retrospective cohort study in patients with active cancer who received systemic therapy within the national Veterans Affairs (VA) health care system from 2017 to 2024. The key inclusion criteria included: (1) having readily extractable data for EHR-CAT calculation without cancer registry data,(2) index date at first or subsequent lines of therapy,(3) exclusion of adjuvant endocrine monotherapy with low risk for VTE, and (4) application of anticoagulant clinical trial exclusion criteria to minimize bleeding risk. Patients from previously published studies were excluded. Systemic therapies were defined using the VA Corporate Data Warehouse, and one line was randomly selected. VTE outcomes were determined using validated VTE–Bidirectional Encoder Representations from Transformers natural language processing from clinical notes. Timedependent C-statistic and calibration slope were assessed. Results: Among 65,341 patients with cancer receiving systemic therapy (42,865 firstline and 22,476 second-line or higher), median age was 71.9 years, and 95% were male. Most common cancers included prostate (16. 1%), lung (14.8%), lymphoma (11.5%), and bladder (11. 1%). The VTE incidence at 6 months was 5.4%. VTE was observed in 1. 9%, 4.0%, 4.7%, 6. 5%, 9. 6%, and 12. 3% of patients with EHR-CAT scores 0 − , 1, 2, 3, 4, and 5+, respectively (C-statistic 0. 67). Calibration slope was 0.876. Conclusion: The EHR-CAT model, when applied across different lines of therapy, demonstrated similar performance as in previous studies. Nathanael R. Fillmore and Ang Li contributed equally as co-first authors. © 2026 The Authors. Published by Elsevier Inc. on behalf of International Society on Thrombosis and Haemostasis. This is an open access article under the CC BY license ([http://creativecommons.org/licenses/by/4.0/](http://creativecommons.org/licenses/by/4.0/)). 2 of 7 ■ LA ET AL. Essentials • The VTE and bleeding are serious complications for patients with cancer. • We validated the EHR-CAT risk score in 65,341 veterans with cancer receiving systemic therapy. • The EHR-CAT risk scores stratified patients into distinct risk categories for VTE by 6 months. • Th

FAQs

What is the EHR-CAT model designed to predict?

The EHR-CAT model was derived to predict cancer-associated venous thromboembolism (VTE) in patients with cancer.

How was the study conducted for temporal validation?

A retrospective cohort study assessed patients with active cancer receiving systemic therapy in the national Veterans Affairs health care system from 2017 to 2024, using contemporaneous EHR data to calculate EHR-CAT.

What performance did the EHR-CAT model show in low bleeding risk patients?

Across different lines of therapy, the model demonstrated similar performance, with a reported C-statistic of 0.67 and calibration slope of 0.876.

Sep 22, 2026

Upload by PakDamar76