Using natural language processing to identify symptoms in systemic mastocytosis
This study demonstrates the feasibility of using rule-based NLP to identify SM-related symptoms from unstructured EHR narratives. The approach achieved strong performance and revealed meaningful patterns in symptom documentation. These findings support the broader utility of NLP for characterizing rare disease symptoms, informing early recognition, and enhancing data-driven care strategies.
Authors
- Wansu Chen (ORCID: https://orcid.org/0000-0002-3486-7468)
- Ben Lampson
- Kerri Miller (ORCID: https://orcid.org/0000-0001-8502-5693)
- Fagen Xie (ORCID: https://orcid.org/0000-0002-1565-0490)
- Robert S. Zeiger (ORCID: https://orcid.org/0000-0001-5788-5063)
- Eric J. Puttock (ORCID: https://orcid.org/0000-0003-3963-314X)
- Matt Zhou
- Kevin Tse (ORCID: https://orcid.org/0009-0004-3633-5037)
- Chantal Avila (ORCID: https://orcid.org/0000-0003-1753-5549)
- Erin Sullivan (ORCID: https://orcid.org/0000-0003-3801-4064)
- Chris Yuen
- Dakota Powell
- Mary Saparudin
- Hiba Atif
Institutions
- Kaiser Permanente (US)
- Kaiser Permanente San Diego Medical Center (US)
- Blueprint Medicines (United States) (US)
Publication Details
- Journal
- JAMIA Open
- Published
- 2025-11-03
- DOI
- https://doi.org/10.1093/jamiaopen/ooaf154
- Primary Topic
- Mast cells and histamine
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Kaiser Permanente