Topic

Venous Thromboembolism

Fillmore and his collaborators focus on improving the identification and risk stratification of venous thromboembolism using computational tools. His work includes the development of VTE-BERT, a natural language processing model designed to automate the detection of thrombotic events and their anatomical locations within clinical notes. Additionally, he has validated the EHR-CAT model as a reliable instrument for predicting thromboembolism risk in cancer patients, facilitating the identification of individuals who may benefit from prophylactic anticoagulation.

External Validation 2 Model Validation 2 U.S. Veterans and VA Data 2 Cancer-Associated Thrombosis 1 Electronic Health Records 1 Observational Study 1 Predictive Modeling 1 Retrospective Cohort Study 1 Systemic Cancer Therapy 1 Natural Language Processing 1 Clinical Notes 1 Radiology and Pathology Reports 1

Publications (2)

2026

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

Jennifer La, Omid Jafari, Kaelyn Nannini, Nhan V. Do, Mary T. Brophy, Nathanael R. Fillmore^‡, Ang Li^‡^‡ Equal senior authorship

Research and Practice in Thrombosis and Haemostasis10(5), 106830

Cancer-Associated Thrombosis Electronic Health Records External Validation Model Validation Observational Study

2026

Development and validation of venous thromboembolism-bidirectional encoder representations from transformers (VTE-BERT) natural language processing model.

Omid Jafari, Shengling Ma, Barbara D. Lam, Jun Y. Jiang, Emily Zhou, Mrinal Ranjan, Justine Ryu, Raka Bandyo, Arash Maghsoudi, Bo Peng, Christopher I. Amos, Abiodun Oluyomi, Nathanael R. Fillmore, Jennifer La^‡, Ang Li^‡^‡ Equal senior authorship

Journal of Thrombosis and Haemostasis24(7), 2522-2531

Natural Language Processing External Validation Clinical Notes Radiology and Pathology Reports Cancer Patients