Augmenting Electronic Health Records for Adverse Event Detection
These results demonstrate the potential of structured, NLP-inspired augmentation methods to overcome data limitations in clinical predictive modeling, ultimately contributing to improved patient safety outcomes. TASER-AE is available at https://github.com/Kingsford-Group/taserae.
Authors
- Gün Kaynar (ORCID: https://orcid.org/0009-0006-6764-7716)
- Richard D. Boyce (ORCID: https://orcid.org/0000-0002-2993-2085)
- Zhaoyi You
- Takahiro Yakoh
Institutions
- University of Pittsburgh (US)
- Keio University (JP)
- Carnegie Mellon University (US)
Publication Details
- Journal
- medRxiv
- Published
- 2026-02-11
- DOI
- https://doi.org/10.64898/2026.02.10.26345962
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Science Foundation
- University of Pittsburgh
- Jewish Healthcare Foundation
- National Institutes of Health
- Medical Center, University of Pittsburgh
- National Center for Advancing Translational Sciences