EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A parallel dual-stream state-space module for reliable and efficient biomedical relation extraction

Yaxun Jia, Zhu Yuan, Lian Zhu, Bing Han, Li Ren, Zuo-Lin Xiang iD

PLOS Computational Biology · 30.07.2026 · 22 (7) · e1014480

DOI: 10.1371/journal.pcbi.1014480 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 30.07.2026. Verfasst von Yaxun Jia und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Shanghai East Hospital, Tongji University School of Medicine, Shanghai, China. Hauptthemen laut MEDLINE: Computational Biology, Data Mining. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Specialty Construction Project of Shanghai Pudong New Area Health Commission, Outstanding Leaders Training Program of Pudong Health Bureau of Shanghai, Shanghai Science and Technology Innovation Action Plan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated drug-drug interaction (DDI) extraction is a cornerstone of global pharmacovigilance, yet its progress is stymied by a fundamental linguistic paradox: relations are signaled by localized morphological cues while being governed by long-range semantic logic. Current monolithic architectures, including Transformer-based models, often face challenges in resolving this feature entanglement, where local clinical descriptors often distort the distal logical chain, leading to noise propagation and reasoning failures. To address this, we present DuSSM, a parallel state-space framework that structurally disentangles surface patterns from semantic evolution. DuSSM implements a bifurcated pipeline: an explicit convolutional stream acting as a local pattern recognizer to isolate syntactic triggers, and an implicit stream leveraging selective state-space modeling (Mamba) to maintain stable semantic states. Although the initial contextual encoding retains a quadratic complexity ( 𝒪 ( N 2 ) ), this decoupled downstream reasoning module operates with a strictly linear 𝒪 ( N ) complexity. Our extensive experiments across four diverse biomedical benchmarks (DDI-2013, ChemProt, GAD, EU-ADR) demonstrate that this dual-stream feature separation generalizes exceptionally well, achieving a robust Fl-score of 82.27% on the DDI benchmark. Notably, DuSSM yields 94.32% precision on non-interaction cases, effectively mitigating the alert fatigue that can arise from the probabilistic nature of generative large language models (LLMs) in zero-shot settings. By reconciling computational efficiency with mechanistic interpretability, DuSSM provides a scalable and trustworthy paradigm for deciphering complex biological interactions within massive electronic health records. All code and data have been publicly released at: https://github.com/Hero-Legend/DuSSM .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computational BiologyData MiningHumansDrug InteractionsSemanticsNatural Language ProcessingAlgorithmsPattern Recognition, Automated

Autor:innen und Institutionen

  • Department of Radiation Oncology, Shanghai East Hospital, Tongji University School of Medicine, Shanghai, China.
  • Department of Information Management, The National Police University for Criminal Justice, Baoding, China.

ORCID-Profile: Zuo-Lin Xiang

Förderung

  • Key Specialty Construction Project of Shanghai Pudong New Area Health Commission
  • Outstanding Leaders Training Program of Pudong Health Bureau of Shanghai
  • Shanghai Science and Technology Innovation Action Plan
  • Science Research Project of Hebei Education Department
  • Doctoral Research Start-up Fund Program of The National Police University for Criminal Justice
  • University-level Research Project of The National Police University for Criminal Justice

Zitieren

APA

Jia, Y., Yuan, Z., Zhu, L., Han, B., Ren, L., & Xiang, Z. L. (2026). A parallel dual-stream state-space module for reliable and efficient biomedical relation extraction. PLOS Computational Biology, 22(7), e1014480. https://doi.org/10.1371/journal.pcbi.1014480

Vancouver

Jia Y, Yuan Z, Zhu L, Han B, Ren L, Xiang ZL. A parallel dual-stream state-space module for reliable and efficient biomedical relation extraction. PLOS Computational Biology. 2026;22(7):e1014480. doi:10.1371/journal.pcbi.1014480

BibTeX
@article{Jia2026,
  author = {Jia, Yaxun and Yuan, Zhu and Zhu, Lian and Han, Bing and Ren, Li and Xiang, Zuo-Lin},
  title = {A parallel dual-stream state-space module for reliable and efficient biomedical relation extraction},
  journal = {PLOS Computational Biology},
  year = {2026},
  volume = {22},
  number = {7},
  pages = {e1014480},
  doi = {10.1371/journal.pcbi.1014480}
}
Kostenlos starten →