OEMA: ontology-enhanced multi-agent collaboration framework for zero-shot clinical named entity recognition
JAMIA Open · 05.05.2026 · 9 (3)
DOI: 10.1093/jamiaopen/ooag049 ↗Kurz gefasst
Fachartikel in der Zeitschrift JAMIA Open, online erschienen am 14.05.2026. Verfasst von Xinli Tao und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Artificial Intelligence, School of Computer Science & Technology, Beijing Jiaotong University, Beijing, 100044, China. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China, Prevention and Control of Emerging and Major Infectious Diseases-National Science and Technology Major Project.
Abstract (Originalsprache)
Objective
With the rapid growth of unstructured clinical narratives in electronic health records (EHRs), clinical named entity recognition (NER) has become a crucial technique for extracting structured medical information. However, traditional supervised models such as CRF and BioClinicalBERT rely on costly manual annotations. Although large language model (LLM)-based zero-shot NER reduces the dependency on labeled data, challenges remain in aligning example selection with task granularity and in effectively integrating prompt design with self-improvement frameworks. Materials and Methods To address these limitations, we propose OEMA, a novel zero-shot clinical NER framework based on ontology-enhanced multi-agent collaboration. OEMA consists of three core components: (1) a self-annotator that autonomously generates candidate examples; (2) a discriminator that leverages SNOMED CT to filter token-level examples based on clinical relevance; and (3) a predictor that incorporates entity-type descriptions to enhance inference consistency and accuracy.
Results
Experimental results on three benchmark datasets, including the real-world I2B2 2010 dataset alongside MTSamples and VAERS, demonstrate that OEMA consistently outperforms existing zero-shot baselines under exact-match evaluation across multiple backbone LLMs (including gpt-3.5, gpt-4.1, and gemini-2.5-flash). Moreover, under relaxed-match criteria, OEMA performs comparably to the supervised BioClinicalBERT model while significantly outperforming the traditional CRF method.
Discussion
OEMA integrates ontology-guided reasoning with multi-agent collaboration to address two key challenges in zero-shot clinical NER: granularity mismatch and prompt-self-improvement integration. Ablation studies indicate that ontology-based filtering reduces noise and improves semantic alignment, helping to bridge the style gap between synthetic data and real-world clinical narratives.
Conclusion
OEMA advances zero-shot clinical NER and achieves performance approaching supervised models under relaxed-match criteria. Future work will focus on continual learning, open-domain adaptation, negation and assertion status detection, and multilingual generalization to further expand its applicability in clinical NLP.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Artificial Intelligence, School of Computer Science & Technology, Beijing Jiaotong University, Beijing, 100044, China.
ORCID-Profile: Xin Dong, Xuezhong Zhou
Förderung
- National Natural Science Foundation of China
- Prevention and Control of Emerging and Major Infectious Diseases-National Science and Technology Major Project
Zitieren
APA
Tao, X., Dong, X., Zhu, Q., & Zhou, X. (2026). OEMA: ontology-enhanced multi-agent collaboration framework for zero-shot clinical named entity recognition. JAMIA Open, 9(3). https://doi.org/10.1093/jamiaopen/ooag049
Vancouver
Tao X, Dong X, Zhu Q, Zhou X. OEMA: ontology-enhanced multi-agent collaboration framework for zero-shot clinical named entity recognition. JAMIA Open. 2026;9(3). doi:10.1093/jamiaopen/ooag049
BibTeX
@article{Tao2026,
author = {Tao, Xinli and Dong, Xin and Zhu, Qiang and Zhou, Xuezhong},
title = {OEMA: ontology-enhanced multi-agent collaboration framework for zero-shot clinical named entity recognition},
journal = {JAMIA Open},
year = {2026},
volume = {9},
number = {3},
doi = {10.1093/jamiaopen/ooag049}
}
EUVIMED