{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T04:52:35Z","timestamp":1783572755283,"version":"3.55.0"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"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>Liver cancer is a leading cause of cancer-related mortality worldwide, necessitating advanced tools for diagnosis and management. Knowledge graphs (KGs) are crucial for advancing smart healthcare, but existing liver cancer-specific KGs are mostly derived from literature or public databases, lacking integration with real-world clinical data [e.g., Electronic Medical Records (EMRs)], creating a critical gap. Furthermore, there is currently no publicly available KGs specifically for liver cancer, creating a significant gap in structured clinical knowledge resources.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This study proposes a novel framework to construct the first Chinese liver cancer KG from Real-World Liver Cancer Electronic Medical Records (RLC-EMRs). A new named entity recognition (NER) model, DERM-RoBERTa-wwm-large-BiLSTM-CRF was developed that uses a Dynamic Entity Replacement and Masking (DERM) strategy to address data scarcity. Knowledge fusion was performed using the TF-IDF algorithm to standardize and integrate entities from clinical records, the professional medical website <jats:uri>www.XYWY.com<\/jats:uri>, and the CCMT-2019 terminology standard.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The final constructed liver cancer KG contained 46,364 entities and 296,655 semantic relationships. The proposed NER model achieved a state-of-the-art F1 score of 68.84% on the public CMeEE-v2 dataset. On the proprietary RLC-EMRs dataset, the model demonstrated high effectiveness with a precision of 93.23%, recall of 94.69%, and an F1 score of 93.96%. In addition, a KG-based retrieval system was successfully developed to query for complications, medications, and other related information.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>The findings demonstrated the effectiveness of the proposed framework in constructing a comprehensive and clinically relevant liver cancer KG. The novel DERM-based NER model significantly improved entity extraction from complex medical texts. By successfully integrating real-world clinical data, this study addresses a critical gap in existing liver cancer-specific KGs, which are mostly derived from literature or public databases and lack integration with real-world clinical information.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2025.1663877","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T05:29:58Z","timestamp":1760678998000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Liver cancer knowledge graph construction based on dynamic entity replacement and masking strategies RoBERTa-wwm-large-BiLSTM-CRF model with clinical Chinese EMRs"],"prefix":"10.3389","volume":"8","author":[{"given":"Yichi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hailing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongbin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingfang","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhijun","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1186\/s40537-023-00774-9","article-title":"Healthcare knowledge graph construction: a systematic review of the state-of-the-art, open issues, and opportunities","volume":"10","author":"Abu-Salih","year":"2023","journal-title":"J. Big Data"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1388479","DOI":"10.3389\/frai.2024.1388479","article-title":"Patient-centric knowledge graphs: a survey of current methods, challenges, and applications","volume":"7","author":"Al Khatib","year":"2024","journal-title":"Front. Artif. Intelligence"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"D267","DOI":"10.1093\/nar\/gkh061","article-title":"The unified medical language system (UMLS): integrating biomedical terminology","volume":"32","author":"Bodenreider","year":"2004","journal-title":"Nucleic Acids Res."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"229","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J. Clin."},{"key":"ref5","author":"Brown","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"300","DOI":"10.3390\/jpm11040300","article-title":"Knowledge graphs for COVID-19: an exploratory review of the current landscape","volume":"11","author":"Chatterjee","year":"2021","journal-title":"J. Pers. Med."},{"key":"ref7","first-page":"19","article-title":"Robustly extracting medical knowledge from EHRs: a case study of learning a health knowledge graph","volume-title":"Biocomputing 2020. Presented at the Pacific symposium on Biocomputing 2020","author":"Chen","year":"2019"},{"key":"ref1001","first-page":"19","article-title":"Chinese expert consensus on multidisciplinary treatment of liver cancer.","volume-title":"J. Clin. Hepatol","year":"2025"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"104861","DOI":"10.1016\/j.jbi.2025.104861","article-title":"A review on knowledge graphs for healthcare: resources, applications, and promises","volume":"169","author":"Cui","year":"2025","journal-title":"J. Biomed. Inform."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"13296","DOI":"10.3390\/app132413296","article-title":"Fusion of SoftLexicon and RoBERTa for purpose-driven electronic medical record named entity recognition","volume":"13","author":"Cui","year":"2023","journal-title":"Appl. Sci."},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/CISP-BMEI48845.2019.8965823","article-title":"Named entity recognition using BERT BiLSTM CRF for Chinese electronic health records","volume-title":"2019 12th international congress on image and signal processing, BioMedical engineering and informatics (CISP-BMEI)","author":"Dai","year":"2019"},{"key":"ref11","volume-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"ref12","first-page":"5855","article-title":"An analysis of dataset overlap on Winograd-style tasks","author":"Emami","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1186\/s12885-024-12331-5","article-title":"Reference-free inferring of transcriptomic events in cancer cells on single-cell data","volume":"24","author":"Eralp","year":"2024","journal-title":"BMC Cancer"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.procs.2024.09.313","article-title":"Advancing liver cancer research: a graph-based approach for ontology enrichment and link prediction","volume":"240","author":"Essalah","year":"2024","journal-title":"Procedia Comput. Sci."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.artint.2012.06.009","article-title":"Watson: beyond jeopardy!","author":"Ferrucci","year":"2013","journal-title":"Artif. Intell."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1402.3722","article-title":"word2vec explained: deriving Mikolov et al.\u2019s negative-sampling word-embedding method","author":"Goldberg","year":"2014","journal-title":"arXiv"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"100174","DOI":"10.1016\/j.bdr.2020.100174","article-title":"SMR: medical knowledge graph embedding for safe medicine recommendation","volume":"23","author":"Gong","year":"2021","journal-title":"Big Data Research"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1002\/poh2.97","article-title":"Application of graph theory in liver research: a review","volume":"3","author":"Hu","year":"2025","journal-title":"Portal Hypertens. Cirrhosis"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"3158","DOI":"10.1093\/bioinformatics\/bts591","article-title":"SemMedDB: a PubMed-scale repository of biomedical semantic predications","volume":"28","author":"Kilicoglu","year":"2012","journal-title":"Bioinformatics"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1007\/s13755-020-0102-4","article-title":"Automatic approach for constructing a knowledge graph of knee osteoarthritis in Chinese","volume":"8","author":"Li","year":"","journal-title":"Health Inform. Sci. Syst."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"101817","DOI":"10.1016\/j.artmed.2020.101817","article-title":"Real-world data medical knowledge graph: construction and applications","volume":"103","author":"Li","year":"2020","journal-title":"Artif. Intell. Med."},{"key":"ref24","first-page":"6836","article-title":"FLAT: Chinese NER using flat-lattice transformer","volume-title":"Proceedings of the 58th annual meeting of the Association for Computational Linguistics","author":"Li","year":""},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1907.11692","article-title":"RoBERTa: a robustly optimized BERT pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1093\/bioinformatics\/btx761","article-title":"An attention-based BiLSTM-CRF approach to document-level chemical named entity recognition","volume":"34","author":"Luo","year":"2018","journal-title":"Bioinformatics"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1908.05969","article-title":"Simplify the usage of lexicon in Chinese NER","author":"Ma","year":"2019","journal-title":"arXiv"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"15","DOI":"10.5121\/ijnlc.2012.1402","article-title":"Named entity recognition using hidden markov model (HMM)","volume":"1","author":"Morwal","year":"2012","journal-title":"Int. J. Nat. Lang. Comput."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1186\/s12911-023-02243-y","article-title":"Chinese medical entity recognition based on the dual-branch TENER model","volume":"23","author":"Peng","year":"2023","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref30","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.3115\/v1\/D14-1162","article-title":"GloVe: global vectors for word representation","volume-title":"Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)","author":"Pennington","year":"2014"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"905","DOI":"10.1016\/j.jbi.2008.12.012","article-title":"Feature selection techniques for maximum entropy based biomedical named entity recognition","volume":"42","author":"Saha","year":"2009","journal-title":"J. Biomed. Inform."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1089\/cmb.2024.0807","article-title":"Predicting drug responses via diffusion-based graph attention network","volume":"32","author":"Sefer","year":"2025","journal-title":"J. Comput. Biol."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"e54263","DOI":"10.2196\/54263","article-title":"Electronic health record\u2013oriented knowledge graph system for collaborative clinical decision support using multicenter fragmented medical data: design and application study","volume":"26","author":"Shang","year":"2024","journal-title":"J. Med. Internet Res."},{"key":"ref34","first-page":"27","article-title":"DEKGB: an extensible framework for health knowledge graph","volume-title":"Smart health, lecture notes in computer science","author":"Sheng","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"132306","DOI":"10.1016\/j.physd.2019.132306","article-title":"Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network","volume":"404","author":"Sherstinsky","year":"2020","journal-title":"Physica D Nonlinear Phenomena"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"10","DOI":"10.3322\/caac.21871","article-title":"Cancer statistics, 2025","volume":"75","author":"Siegel","year":"2025","journal-title":"CA Cancer J. Clin."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1561\/2200000013","article-title":"An introduction to conditional random fields","volume":"4","author":"Sutton","year":"2012","journal-title":"Found. Trends Mach. Learn."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.2196\/60334","article-title":"Chinese clinical named entity recognition with segmentation synonym sentence synthesis mechanism: algorithm development and validation","volume":"12","author":"Tang","year":"2024","journal-title":"JMIR Med. Inform."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1080\/24699322.2020.1850866","article-title":"Construction of a knowledge graph for diabetes complications from expert-reviewed clinical evidences","volume":"25","author":"Wang","year":"2020","journal-title":"Comput. Assist. Surg."},{"key":"ref40","first-page":"1812","article-title":"Clinical named entity recognition using deep learning models","volume":"2017","author":"Wu","year":"2017","journal-title":"AMIA Ann. Symp. Proc."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"e18287","DOI":"10.2196\/18287","article-title":"Construction of a digestive system tumor knowledge graph based on Chinese electronic medical records: development and usability study","volume":"8","author":"Xiu","year":"2020","journal-title":"JMIR Med. Inform."},{"key":"ref1002","first-page":"1389475","article-title":"Knowledge graph construction for heart failure using large language models with prompt engineering.","volume-title":"Front. Comput. Neurosci.","author":"Xu","year":"2024"},{"key":"ref1003","doi-asserted-by":"publisher","first-page":"19368","DOI":"10.1609\/aaai.v38i17.29907","article-title":"Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-World Multi-Turn Dialogue","volume":"38","author":"Yang","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence."},{"key":"ref43","first-page":"2720","article-title":"On the generative discovery of structured medical knowledge","volume-title":"Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining (KDD \u201818)","author":"Zhang","year":"2018"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"1554","DOI":"10.18653\/v1\/P18-1144","article-title":"Chinese NER using lattice LSTM","volume-title":"Proceedings of the 56th annual meeting of the Association for Computational Linguistics (volume 1: Long papers)","author":"Zhang","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"6399","DOI":"10.1007\/s11227-019-02917-3","article-title":"Exploiting the concept level feature for enhanced name entity recognition in Chinese EMRs","volume":"76","author":"Zhao","year":"2020","journal-title":"J. Supercomput."},{"key":"ref46","first-page":"144","article-title":"Research on construction and application of TCM knowledge graph based on ancient Chinese texts","volume-title":"Proceedings of the IEEE\/WIC\/ACM international conference on web intelligence \u2013 Companion volume (WI \u201819)","author":"Zhou","year":"2019"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1663877\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T05:30:01Z","timestamp":1760679001000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1663877\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":46,"alternative-id":["10.3389\/frai.2025.1663877"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1663877","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,17]]},"article-number":"1663877"}}