Automated health information question-answering reimagined: Medical Relation-Aware Encoding Network
Journal of Information Science · 2026-08 · 52 (4) · 1130-1148
DOI: 10.1177/01655515261433926 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Information Science, online erschienen am 06.04.2026. Verfasst von Ting Pan und 3 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
This article introduces the Medical Relation-Aware Encoding Network (MeRAEN) to improve medical answer generation (MAG) in automated health information question-answering systems. MeRAEN enhances pre-trained large language models (LLMs) by jointly encoding dialog history and medical knowledge graph. To effectively capture semantic and medical relational information, MeRAEN introduces three innovations: (1) a knowledge association matrix that models word-level medical relations, (2) a medical relation-aware dialog graph that models utterance-level medical relations and (3) a Relational Graph Attention Network with Knowledge (KRGAT). Experiments on real-world medical dialog datasets demonstrate that MeRAEN significantly outperforms state-of-the-art baselines in terms of accuracy, diversity, knowledge utilisation, fluency, patient safety and health outcomes. Ablation studies further verify the effectiveness of each component in MeRAEN. These results underscore MeRAEN’s potential to improve MAG systems and inform the design of domain-adaptive Q&A systems for broader applications beyond healthcare.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Pan, T., Chua, A. Y., Shen, J., & Xu, M. (2026). Automated health information question-answering reimagined: Medical Relation-Aware Encoding Network. Journal of Information Science, 52(4), 1130-1148. https://doi.org/10.1177/01655515261433926
Vancouver
Pan T, Chua AY, Shen J, Xu M. Automated health information question-answering reimagined: Medical Relation-Aware Encoding Network. Journal of Information Science. 2026;52(4):1130-1148. doi:10.1177/01655515261433926
BibTeX
@article{Pan2026,
author = {Pan, Ting and Chua, Alton YK and Shen, Jiang and Xu, Man},
title = {Automated health information question-answering reimagined: Medical Relation-Aware Encoding Network},
journal = {Journal of Information Science},
year = {2026},
volume = {52},
number = {4},
pages = {1130--1148},
doi = {10.1177/01655515261433926}
}
EUVIMED