EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Biomedical concept recognition with error-aware negative-enhanced ranking framework

Shanshan Liu iD, Noriki Nishida iD, Fei Cheng iD, Takehito Utsuro, Yuji Matsumoto iD

Bioinformatics · 02.07.2026 · 42 (7)

DOI: 10.1093/bioinformatics/btag495 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 03.07.2026. Verfasst von Shanshan Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: RIKEN Center for Advanced Intelligence Project, Nihonbashi 1-chome Mitsui Building, 15th floor, 1-4-1 Nihonbashi, Chuo-ku, Tokyo, 103-0027, Japan. Hauptthemen laut MEDLINE: Biological Ontologies, Computational Biology. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Mention-agnostic biomedical concept recognition (MA-BCR) requires inferring ontology concepts directly from passages, without relying on explicit mention spans. Prior work has mainly focused on generative and classification-based approaches. Ranking-based methods typically use a retrieve-rerank pipeline, and this paradigm has not been systematically studied for MA-BCR. Consequently, it remains unclear how ranking-based approaches compare with existing paradigms and what types of supervision are most beneficial for ranker training under limited annotation settings. Results Through a systematic comparison of ranking-, generative-, and classification-based paradigms, we show that a two-stage retrieve-rerank architecture is the most robust and scalable backbone for MA-BCR. Building on this finding, we propose ENR, an error-aware negative-enhanced ranking framework that augments training with false positives collected from heterogeneous recognizers, improving reranking performance without increasing inference-time cost. Experiments on MM-HPO and MM-GO (two datasets derived from MedMentions-ST21pv) demonstrate that ENR substantially outperforms prior approaches. Availability and implementation The code and data underlying this article are available in Github at https://github.com/sl-633/enr-recognizer or in Zenodo at https://doi.org/10.5281/zenodo.20730803.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Biological OntologiesComputational BiologyAlgorithms

Autor:innen und Institutionen

  • RIKEN Center for Advanced Intelligence Project, Nihonbashi 1-chome Mitsui Building, 15th floor, 1-4-1 Nihonbashi, Chuo-ku, Tokyo, 103-0027, Japan.
  • Graduate School of Science and Technology, University of Tsukuba, 1-1-1 Tennodai, Tsukuba, Ibaraki, 305-8577, Japan.
  • Graduate School of Informatics, Kyoto University, S212, Research Bldg. No.9, Yoshida Main Campus, Yoshida-honmachi, Sakyo-ku, Kyoto, 606-8501, Japan.
  • Faculty of Engineering, Information and Systems, University of Tsukuba, 1-1-1 Tennodai, Tsukuba, 305-8573, Japan.

ORCID-Profile: Shanshan Liu, Noriki Nishida, Fei Cheng, Yuji Matsumoto

Zitieren

APA

Liu, S., Nishida, N., Cheng, F., Utsuro, T., & Matsumoto, Y. (2026). Biomedical concept recognition with error-aware negative-enhanced ranking framework. Bioinformatics, 42(7). https://doi.org/10.1093/bioinformatics/btag495

Vancouver

Liu S, Nishida N, Cheng F, Utsuro T, Matsumoto Y. Biomedical concept recognition with error-aware negative-enhanced ranking framework. Bioinformatics. 2026;42(7). doi:10.1093/bioinformatics/btag495

BibTeX
@article{Liu2026,
  author = {Liu, Shanshan and Nishida, Noriki and Cheng, Fei and Utsuro, Takehito and Matsumoto, Yuji},
  title = {Biomedical concept recognition with error-aware negative-enhanced ranking framework},
  journal = {Bioinformatics},
  year = {2026},
  volume = {42},
  number = {7},
  doi = {10.1093/bioinformatics/btag495}
}
Kostenlos starten →