Natural Language Processing and ICD-10 Coding for Detecting Bleeding Events in Discharge Summaries: Comparative Cross-Sectional Study
This study highlights the considerable advantage of NLP over traditional ICD-10-based methods for detecting bleeding ADEs within electronic medical records. The NLP model effectively captured nuanced clinical narratives, including severity, negations, and historical bleeding events, demonstrating substantial promise for improving patient safety surveillance and clinical decision-making. Future research should extend validation across multiple institutions, diversify annotated datasets, and further refine temporal reasoning capabilities within NLP algorithms.
Authors
- E Bertrand
- Marie‐Annick Le Pogam (ORCID: https://orcid.org/0000-0003-1672-3644)
- Chantal Csajka (ORCID: https://orcid.org/0000-0002-0660-082X)
- Frédéric Gaspar (ORCID: https://orcid.org/0000-0002-0225-7294)
- Claire Coumau (ORCID: https://orcid.org/0000-0002-2303-7848)
- Marie Bettex
- Mehdi Zayene
Institutions
- University of Geneva (CH)
- HES-SO University of Applied Sciences and Arts Western Switzerland (CH)
- Center for Innovation (US)
- Centre universitaire de médecine générale et santé publique, Lausanne (CH)
- University of Lausanne (CH)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-05-07
- DOI
- https://doi.org/10.2196/67837
- Citations
- 1
- Primary Topic
- Text Readability and Simplification
- Type
- article
- Field-Weighted Citation Impact
- 2.48