{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T06:10:51Z","timestamp":1760076651501,"version":"build-2065373602"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:00:00Z","timestamp":1760054400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>The liver cancer question-and-answer (Q&amp;amp;A) system is primarily intended to help patients access disease-related information more conveniently. However, there is currently no Q&amp;amp;A system specifically developed for liver cancer. Additionally, most existing Q&amp;amp;A systems lack real clinical data and have limited capability in understanding Chinese questions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This paper proposes a Chinese liver cancer question-answering system based on knowledge graphs and Large Language Models (LLMs). To unify information from diverse sources, the system employs a knowledge graph to store entities and inter-entity relationships extracted from patients' clinical electronic medical records and the professional medical website xywy.com, which serves as the foundation for the system's responses. Specifically, ChatGLM3.5 is utilized to extract entity information from questions, while BERT is applied to understand users' intent. Subsequently, the system retrieves corresponding information from the knowledge graph. Finally, the retrieved information is integrated, and a natural language response is generated as the answer to the question.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The experimental results indicate that in terms of intent classification, our system achieves a precision of 92.34%, representing an improvement of 1.38% over the BERT model and 4.32% over the GEBERT model. In terms of response relevance, the system's outputs are more aligned with patients' daily speech patterns and exhibit higher relevance to the target questions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>In conclusion, the improved method significantly enhances the usefulness and reliability of the liver cancer Q&amp;amp;A system.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2025.1663891","type":"journal-article","created":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T05:28:21Z","timestamp":1760074101000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Chinese question and answer system for liver cancer based on knowledge graph and large language mode"],"prefix":"10.3389","volume":"8","author":[{"given":"Haoqi","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hailing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongbin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhijun","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojun","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingfang","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,10]]},"reference":[{"key":"B1","first-page":"1877","article-title":"\u201cLanguage models are few-shot learners,\u201d","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Brown","year":"2020"},{"key":"B2","doi-asserted-by":"publisher","first-page":"149787","DOI":"10.1109\/ACCESS.2020.3016676","article-title":"Diagnosis method of thyroid disease combining knowledge graph and deep learning","volume":"8","author":"Chai","year":"2020","journal-title":"IEEE Access"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.08998","article-title":"Data-pooling reinforcement learning for personalized healthcare intervention","author":"Chen","year":"2022","journal-title":"arXiv preprint arXiv:2211.08998"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.12449\/JCH250709","article-title":"Chinese expert consensus on multidisciplinary treatment of liver cancer (2025)","volume":"41","year":"2025","journal-title":"J. Clin. Hepatol"},{"key":"B5","doi-asserted-by":"publisher","first-page":"11324","DOI":"10.48550\/arXiv.2204.02311","article-title":"Palm: scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2024","journal-title":"J. Mach. Learn. Res"},{"key":"B6","doi-asserted-by":"publisher","first-page":"565","DOI":"10.14778\/3055540.3055549","article-title":"Kbqa: learning question answering over qa corpora and knowledge bases","volume":"10","author":"Cui","year":"2017","journal-title":"Proc. VLDB Endow"},{"key":"B7","first-page":"4171","article-title":"\u201cBert: pre-training of deep bidirectional transformers for language understanding,\u201d","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin","year":"2019"},{"key":"B8","doi-asserted-by":"crossref","first-page":"320","DOI":"10.18653\/v1\/2022.acl-long.26","article-title":"\u201cGLM: general language model pretraining with autoregressive blank infilling,\u201d","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Du","year":"2022"},{"key":"B9","doi-asserted-by":"crossref","first-page":"253","DOI":"10.18653\/v1\/2022.findings-naacl.19","article-title":"\u201cPerKGQA: question answering over personalized knowledge graphs,\u201d","volume-title":"Findings of the Association for Computational Linguistics: NAACL 2022","author":"Dutt","year":"2022"},{"key":"B10","first-page":"3368","article-title":"\u201cBidirectional maximal matching word segmentation algorithm with rules,\u201d","volume-title":"Progress in Applied Sciences, Engineering and Technology, volume 926 of Advanced Materials Research","author":"Gai","year":"2014"},{"key":"B11","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1007\/978-3-030-30796-7_25","article-title":"\u201cPersonalized knowledge graphs for the pharmaceutical domain,\u201d","author":"Gentile","year":"2019","journal-title":"The Semantic Web"},{"key":"B12","unstructured":"\u201cRealm: retrieval-augmented language model pre-training,\u201d\n          \n          3929\n          3938\n          \n            \n              Guu\n              K.\n            \n            \n              Lee\n              K.\n            \n            \n              Tung\n              Z.\n            \n            \n              Pasupat\n              P.\n            \n            \n              Chang\n              M.-W.\n            \n          \n          New York, NY\n          PMLR\n          Proceedings of the 37th International Conference on Machine Learning\n          \n          2020"},{"key":"B13","first-page":"5","article-title":"Personalized Health Knowledge Graph","volume":"2317","author":"Gyrard","year":"2018","journal-title":"CEUR Workshop Proc"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3778\/j.issn.1673-9418.2308070","volume":"17","author":"Heyi","year":"2023"},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2021\/611","article-title":"\u201cA survey on complex knowledge base question answering: Methods, challenges and solutions,\u201d","volume-title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence Survey Track","author":"Lan","year":"2021"},{"key":"B16","doi-asserted-by":"publisher","first-page":"112923","DOI":"10.1016\/j.eswa.2019.112923","article-title":"Knowledge map construction for question and answer archives","volume":"141","author":"Li","year":"2020","journal-title":"Expert Syst. Appl"},{"key":"B17","first-page":"6966","article-title":"\u201cFew-shot in-context learning on knowledge base question answering,\u201d","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics","author":"Li","year":"2023"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72344-5_17","article-title":"An enhanced prompt-based llm reasoning scheme via knowledge graph-integrated collaboration","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2402.04978"},{"key":"B19","doi-asserted-by":"publisher","first-page":"100943","DOI":"10.1016\/j.patter.2024.100943","article-title":"Can large language models reason about medical questions?","volume":"5","author":"Li\u00e9vin","year":"2024","journal-title":"Patterns"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3177197","article-title":"Personalized federated learning with adaptive batchnorm for healthcare","author":"Lu","year":"2022","journal-title":"IEEE Trans. Big Data"},{"key":"B21","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/ICICSE55337.2022.9828967","article-title":"\u201cA survey: complex knowledge base question answering,\u201d","volume-title":"2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE)","author":"Luo","year":"2022"},{"key":"B22","doi-asserted-by":"crossref","first-page":"1906","DOI":"10.18653\/v1\/2020.acl-main.173","article-title":"\u201cOn faithfulness and factuality in abstractive summarization,\u201d","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Maynez","year":"2020"},{"key":"B23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3584371.3613016","article-title":"\u201cEnabling the informed patient paradigm with secure and personalized medical question answering,\u201d","volume-title":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","author":"Oduro-Afriyie","year":"2023"},{"key":"B24","unstructured":"Applying personal knowledge graphs to health\n          \n          \n            \n              Shirai\n              S.\n            \n            \n              Seneviratne\n              O.\n            \n            \n              McGuinness\n              D. L.\n            \n          \n          arXiv preprint\n          \n          2021"},{"key":"B25","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1038\/s41746-022-00742-2","article-title":"A large language model for electronic health records","volume":"5","author":"Yang","year":"2022","journal-title":"NPJ Digit. Med"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neunet.2021.11.010","article-title":"Multi-layer information fusion based on graph convolutional network for knowledge-driven herb recommendation","volume":"146","author":"Yang","year":"2022","journal-title":"Neural Netw"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1663891\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T05:28:28Z","timestamp":1760074108000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1663891\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,10]]},"references-count":26,"alternative-id":["10.3389\/frai.2025.1663891"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1663891","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,10]]},"article-number":"1663891"}}