•  
  •  
 

Journal of Scientific Information Research

Keywords

knowledge enhancement; question answering systems; large language models; medical knowledge bases; healthcare

Abstract

[Purpose/significance] This paper aims to review the research progress and applications of knowledge enhancement techniques in healthcare question answering systems, in response to the limitations of traditional systems in knowledge representation and reasoning, as well as challenges faced by current large language model-based systems, such as insufficient domain knowledge, privacy concerns, and hallucination. The review provides a systematic reference for improving the precision and knowledge reliability of such systems. [Process/method] Focusing on knowledge enhancement strategies, this paper firstly outlines their fundamental concepts and overall framework. The strategies are then categorized into explicit and implicit types, with an analysis of their characteristics, implementation methods, and applications in typical healthcare scenarios. Finally, future research directions are discussed. [Result/conclusion] The study indicates that knowledge enhancement techniques, which integrate external medical knowledge during the pre-training or inference stages of large language models, can effectively improve the accuracy, interpretability, and trustworthiness of the models. Explicit enhancement strategies emphasize the traceability and structured integration of knowledge, while implicit strategies focus on the semantic internalization and generative flexibility of knowledge. Their synergistic application provides crucial support for building more intelligent and reliable healthcare question answering systems.

First Page

130

Last Page

140

Submission Date

24-Jul-2025

Revision Date

15-Jan-2026

Acceptance Date

27-Jan-2026

Published Date

01-Apr-2026

Reference

[1] 新华社.中共中央 国务院印发《 “健康中国2030" 规划纲要》[EB/OL].(2016-10-25)[2025-05-13].https://www.gov.cn/zhengce/2016-10/25/content_5124174.htm.
[2] 班晓娟. “健康中国" 行动下的智慧医疗[J].工程科学学报, 2021, 43(9): 1137-1139.
[3] 王志伟, 陆振宇.基于细粒度特征增强的多模态视觉问答研究[J/OL].南京信息工程大学学报, 1-17(2025-01-07)[2025-05-13].https://doi.org/10.13878/j.cnki.jnuist.20250107001.
[4] HE Y, ZHU Z W, ZHANG Y, et al.Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.2020: 4604-4614.
[5] LEE J, YOON W, KIM S, et al.BioBERT: a pre-trained biomedical language representation model for biomedical text mining[J].Bioinformatics, 2020, 36(4): 1234-1240.
[6] 刘雪颖, 云静, 李博, 等.基于大型语言模型的检索增强生成综述[J].计算机工程与应用, 2025, 61(13): 1-25.
[7] 袁成哲, 陈国华, 李丁丁, 等.ScholatGPT: 面向学术社交网络的大语言模型及智能应用[J].计算机应用, 2025, 45(3): 755-764.
[8] 孙毅, 裘杭萍, 郑雨, 等.自然语言预训练模型知识增强方法综述[J].中文信息学报, 2021, 35(7): 10-29.
[9] 吴信东, 黄满宗, 卜晨阳.BEKO: 大语言模型与知识图谱的双向增强[J].计算机学报, 2025, 48(7): 1572-1588.
[10] 侯梦薇, 卫荣, 陆亮, 等.知识图谱研究综述及其在医疗领域的应用[J].计算机研究与发展, 2018, 55(12): 2587-2599.
[11] HU L M, LIU Z Y, ZHAO Z W, et al.A survey of knowledge enhanced pre-trained language models[J].IEEE Transactions on Knowledge and Data Engineering, 2024, 36(4): 1413-1430.
[12] 杨善林, 丁帅, 顾东晓, 等.医疗健康大数据驱动的知识发现与知识服务方法[J].管理世界, 2022, 38(1): 219-229.
[13] BUDLER L C, GOSAK L, STIGLIC G.Review of artificial intelligence-based question-answering systems in healthcare[J].WIREs Data Mining and Knowledge Discovery, 2023, 13(2): e1487.
[14] YANG S, KIM C Y, HWANG S, et al.COEXPEDIA: exploring biomedical hypotheses via co-expressions associated with medical subject headings(MeSH)[J].Nucleic Acids Research, 2017, 45(D1): D389-D396.
[15] 奥德玛, 杨云飞, 穗志方, 等.中文医学知识图谱CMeKG构建初探[J].中文信息学报, 2019, 33(10): 1-9.
[16] JIN Q, DHINGRA B, LIU Z, et al.PubMedQA: A Dataset for Biomedical Research Question Answering[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP), Hong Kong.2019: 2567-2577.
[17] 郭亚军, 李天祥, 王会森, 等.从结绳记事到认知引擎: 人类知识增强的历史演进与DeepSeek的创新启示[J].图书馆论坛, 2025, 45(9): 102-113.
[18] SPASIC I, NENADIC G.Clinical text data in machine learning: systematic review[J].JMIR Medical Informatics, 2020, 8(3): e17984.
[19] HAO T Y, LI X X, HE Y L, et al.Recent progress in leveraging deep learning methods for question answering[J].Neural Computing and Applications, 2022, 34(4): 2765-2783.
[20] 韩普, 李雄, 刘森嶺, 等.基于大语言模型的医疗健康领域知识服务模式研究[J].西华大学学报(哲学社会科学版), 2025, 44(1): 24-35.
[21] LU Y X, LIU X H, DU Z X, et al.Medkpl: A heterogeneous knowledge enhanced prompt learning framework for transferable diagnosis[J].Journal of Biomedical Informatics, 2023, 143: 104417.
[22] CHEN J, HU B T, PENG W H, et al.Biomedical relation extraction via knowledge-enhanced reading comprehension[J].BMC Bioinformatics, 2022, 23(1): 1-19.
[23] AZAD B, MAHDIYAR A A A, JAFARZADEH P, et al.Unlocking wisdom: enhancing biomedical question answering with domain knowledge[J].Knowledge and Information Systems, 2025, 67: 4087-4112.
[24] PARK H, SON J, MIN J, et al.Selective UMLS knowledge infusion for biomedical question answering[J].Scientific Reports, 2023, 13(1): 14214.
[25] WANG X, LUO F, WU Q, et al.How context or knowledge can benefit healthcare question answering?[J].IEEE Transactions on Knowledge and Data Engineering, 2021, 35(1): 575-588.
[26] HUANG J, CHEN Y H, LI Y, et al.Medical knowledge-based network for patient-oriented visual question answering[J].Information Processing & Management, 2023, 60(2): 103241.
[27] 张殿元, 余传明.基于知识增强与多模态融合的医疗视觉问答模型[J].数据分析与知识发现, 2024, 8(Z1): 226-239.
[28] ZAFAR A, VARSHNEY D, SAHOO S K, et al.Are my answers medically accurate?Exploiting medical knowledge graphs for medical question answering[J].Applied Intelligence, 2024, 54(2): 2172-2187.
[29] ZAFAR A, SAHOO S K, VARSHNEY D, et al.KIMedQA: towards building knowledge-enhanced medical QA models[J].Journal of Intelligent Information Systems, 2024, 62(3): 833-858.
[30] ABDUL A, CHEN B, PHANI S, et al.Improving preliminary clinical diagnosis accuracy through knowledge filtering techniques in consultation dialogues[J].Computer Methods and Programs in Biomedicine, 2024, 246: 108051.
[31] BORA A, CUAYÁHUITL H.Systematic Analysis of Retrieval-Augmented Generation-Based LLMs for Medical Chatbot Applications[J].Machine Learning and Knowledge Extraction, 2024, 6(4): 2355-2374.
[32] 王文湖, 韦昌法.基于大语言模型和知识库的阿尔茨海默病智能问答系统构建研究[J].世界科学技术-中医药现代化, 2025, 27(3): 856-866.
[33] VU M H, LÖFSTEDT T, NYHOLM T, et al.A question-centric model for visual question answering in medical imaging[J].IEEE Transactions on Medical Imaging, 2020, 39(9): 2856-2868.
[34] SINGHAL K, AZIZI S, TU T, et al.Large language models encode clinical knowledge[J].Nature, 2023, 620(7972): 172-180.
[35] LIU Y Y, LI X Y, LUO Y, et al.Toward a Large Language Model-Driven Medical Knowledge Retrieval and QA System: Framework Design and Evaluation[J].Engineering, 2025, 50: 270-282.
[36] KOMOROWSKI M, CELI L, BADAWI O, et al.The artificial intelligence clinician learns optimal treatment strategies for sepsis in intensive care[J].Nature Medicine, 2018, 24(11): 1716-1720.
[37] JING F, REN H, CHENG W, et al.Knowledge-enhanced attentive learning for answer selection in community question answering systems[J].Knowledge-Based Systems, 2022, 250: 109117.
[38] LIEVIN V, HOTHER C E, MOTZFELDT A G, et al.Can large language models reason about medical questions?[J].Patterns, 2024, 5(3): 100943.
[39] 苑中旭, 李理, 何凡, 等.融合思维链与知识图谱的中医问答模型[J].计算机工程与应用, 2025, 61(4): 158-166.
[40] SONG M, ZHENG M.A Survey of Query Optimization in Large Language Models[J].arXiv e-prints arXiv: 2412.17558[cs.CL].
[41] 徐博, 林鸿飞, 林原, 等.一种融合语义资源的生物医学查询理解方法[J].计算机学报, 2019, 42(10): 2160-2174.
[42] 丁浩, 胡广伟, 齐江蕾, 等.基于随机森林和关键词查询扩展的医学文献推荐方法[J].数据分析与知识发现, 2022, 6(7): 32-43.
[43] LIU B, ZHAN L M, XU L, et al.SLAKE: A semantically-labeled knowledge-enhanced dataset for medical visual question answering[C]//2021 IEEE 18th international symposium on biomedical imaging(ISBI), Nice.2021: 1650-1654.
[44] BAE S, KYUNG D, RYU J, et al.EHRXQA: A multi-modal question answering dataset for electronic health records with chest x-ray images[J].Advances in Neural Information Processing Systems, 2023, 36: 3867-3880.
[45] LEWIS P, PEREZ E, PIKTUS A, et al.Retrieval-augmented generation for knowledge-intensive nlp tasks[J].arXiv e-prints arXiv: 2005.11401v4 [cs.CL].
[46] PENG B C, ZHU Y, LIU Y C, et al.Graph retrieval-augmented generation: A survey[J].arXiv e-prints arXiv: 2408.08921[cs.CL].
[47] YANG L Y, CHEN H Y, LI Z, et al.Give us the facts: Enhancing large language models with knowledge graphs for fact-aware language modeling[J].IEEE Transactions on Knowledge and Data Engineering, 2024, 36(7): 3091-3110.
[48] LAI T M, ZHAI C X, JI H.KEBLM: Knowledge-Enhanced Biomedical Language Models[J].Journal of Biomedical Informatics, 2023, 143: 104392.
[49] 刘军, 冷芳玲, 吴旺旺, 等.基于多模态和知识蒸馏的教材知识图谱构建方法[J].计算机科学与探索, 2024, 18(11): 2901-2911.
[50] ZHANG Z S, YAO Y, ZHANG A, et al.Igniting Language Intelligence: The Hitchhiker's Guide from Chain-of-Thought Reasoning to Language Agents[J].ACM Computing Surveys, 2025, 57(8): 1-39.
[51] 冯涛, 刘晨.自动化偏好对齐的双阶段提示调优方法[J].计算机应用, 2025, 45(8): 2442-2447.
[52] ZENG Z F, CHENG Q, HU X C, et al.KoSEL: Knowledge subgraph enhanced large language model for medical question answering[J].Knowledge-Based Systems, 2025, 309: 112837.
[53] RISLING T, MARTINEZ J, YOUNG J, et al.Evaluating patient empowerment in association with eHealth technology: scoping review[J].Journal of Medical Internet Research, 2017, 19(9): e329.
[54] ARIF T B, MUNAF U, UL-HAQUE I.The future of medical education and research: Is ChatGPT a blessing or blight in disguise?[J].Medical education online, 2023, 28(1): 2181052.
[55] SUN Y L, LIU F.Real-world implementation of an AI learning tool-MetaGP-Edu in medical education: A multi-center cohort study[J].Computers & Education, 2025, 237: 105388.

Digital Object Identifier (DOI)

10.19809/j.cnki.kjqbyj.2026.02.013

Download

Share

COinS