Academic Journal
Persona-Driven Data Augmentation for Disease Name Recognition Across Rare and General Disease Corpora: Comparative Evaluation Study.
| Τίτλος: | Persona-Driven Data Augmentation for Disease Name Recognition Across Rare and General Disease Corpora: Comparative Evaluation Study. |
|---|---|
| Συγγραφείς: | Pierre JCJ; Nara Institute of Science and Technology, Ikoma, Nara, Japan., Nishiyama T; Nara Institute of Science and Technology, Ikoma, Nara, Japan., Peng S; Nara Institute of Science and Technology, Ikoma, Nara, Japan., Wakamiya S; Nara Institute of Science and Technology, Ikoma, Nara, Japan., Aramaki E; Nara Institute of Science and Technology, Ikoma, Nara, Japan. |
| Πηγή: | JMIR medical informatics [JMIR Med Inform] 2026 Jul 24; Vol. 14, pp. e87831. Date of Electronic Publication: 2026 Jul 24. |
| Τύπος έκδοσης: | Journal Article; Comparative Study |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: JMIR Publications Country of Publication: Canada NLM ID: 101645109 Publication Model: Electronic Cited Medium: Internet ISSN: 2291-9694 (Electronic) Linking ISSN: 22919694 NLM ISO Abbreviation: JMIR Med Inform Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Toronto : JMIR Publications, [2013]- |
| Ιατρικοί όροι (MeSH): | Rare Diseases*/classification , Disease*/classification , Data Mining*/methods , Natural Language Processing*, Humans ; Large Language Models |
| Περίληψη: | Background: Medical information extraction requires automatically identifying disease names and related terms in text. This task, known as named entity recognition (NER), relies on expert-annotated data that are costly to produce and often available only in limited quantities. Data augmentation (DA) aims to expand available training data; however, standard techniques such as synonym replacement and back-translation may introduce inappropriate substitutions or fail to preserve entity-label alignment, which is critical for sequence-labeling tasks. Although large language models can generate fluent text, their outputs may also contain factual inconsistencies or unintended changes if not carefully controlled. Objective: This study investigated whether persona-driven, document-level DA using a large language model could improve biomedical disease NER performance by generating diverse rephrasings of medical documents while preserving annotated entities. Methods: We designed a DA framework using multiple personas that varied in medical expertise, personality, tone, and narrative style. Using prompting constrained by XML tags, each persona rephrased training documents while aiming to preserve annotated entity spans. We evaluated the framework on 2 biomedical disease NER datasets with complementary roles: RareDis, a low-resource rare disease corpus, and National Center for Biotechnology Information (NCBI) disease, a more general disease benchmark. Semantic fidelity and lexical diversity were measured using BERTScore and Bilingual Evaluation Understudy (BLEU-4), respectively, and personas were grouped into high-, balanced-, and low-fidelity subsets. Biomedical pretrained BioBERT models were fine-tuned and evaluated under multiple settings, including gold-standard (GS) data only, synonym replacement, single-persona augmentation, curated persona subsets, and all-persona augmentation. Performance was assessed using microaveraged entity-level precision, recall, and F Results: Persona-driven DA improved NER performance over GS-only training in both datasets, with the strongest gains obtained by combining multiple persona-generated variants with GS data. In RareDis, the best result was achieved by the low-fidelity subset (mean F Conclusions: Persona-driven DA improved biomedical disease NER by introducing controlled linguistic variation while largely preserving annotated entities. The strongest gains were obtained when multiple persona-generated variants were combined with GS data, although the benefit varied across datasets. These findings suggest that this approach is a promising strategy for low-resource biomedical NER. (©Jude Crener Junior Pierre, Tomohiro Nishiyama, Shaowen Peng, Shoko Wakamiya, Eiji Aramaki. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 24.07.2026.) |
| Contributed Indexing: | Keywords: LLM; NER; NLP; data augmentation; disease; large language model; low-resource; named entity recognition; natural language processing; persona; rare disease |
| Entry Date(s): | Date Created: 20260724 Date Completed: 20260724 Latest Revision: 20260724 |
| Update Code: | 20260725 |
| DOI: | 10.2196/87831 |
| PMID: | 42497410 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 2291-9694 |
|---|---|
| DOI: | 10.2196/87831 |