October, 2025
October 2025
M T W T F S S
 12345
6789101112
13141516171819
20212223242526
2728293031  
Omid Jafari and Colleagues Present the VTE-BERT Natural Language Processing Model
Oct 24, 2025, 11:37

Omid Jafari and Colleagues Present the VTE-BERT Natural Language Processing Model

Journal of Thrombosis and Haemostasis (JTH) shared on LinkedIn:

”Development and validation of venous thromboembolism–Bidirectional Encoder Representations from Transformers (VTE-BERT) natural language processing model
By Omid Jafari, Shengling M., Barbara Lam, Jun Y. Jiang, Emily Zhou, Mrinal Ranjan, Justine Ryu, Raka Bandyo, Arash Maghsoudi, Bo Peng, Christopher Amos, Abiodun Oluyomi, Nathanael (Nate) Fillmore, Jennifer La, and Ang Li

• Concept: Accurate phenotyping of venous thromboembolism (VTE) in longitudinal datasets remains labor-intensive; an NLP model could automate detection.
• Approach: Using >28 000 annotated clinical notes from two institutions, the team fine-tuned Bio_Clinical BERT to create VTE-BERT, trained to recognize acute VTE events and anatomic sites over time.
• Findings: Achieved 95% precision / 98% recall internally and 85% / 92% externally, outperforming manual chart review efficiency. This tool could markedly accelerate large-scale thrombosis research.”

Read the full article here.

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

Authors: 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

Omid Jafari and Colleagues Present the VTE-BERT Natural Language Processing Model

Stay updated on all scientific advances in the field of thrombosis with Hemostasis Today.