{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T14:04:11Z","timestamp":1770905051671,"version":"3.50.1"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"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>General purpose language models often struggle with accurately identifying domain specific terminology in the medical field, resulting in suboptimal performance in named entity recognition (NER) tasks. This challenge is particularly pronounced in Chinese electronic medical records (EMRs), which lack clear word boundaries and contain complex medical expressions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This study proposes a novel NER method for Chinese EMRs that integrates ClinicalBERT, a language model pre trained on clinical corpora, with structured knowledge from a medical knowledge graph. Entity representations derived via Translating Embeddings (TransE) are incorporated to inject external semantic knowledge. Furthermore, the model fuses multiple character level features, including positional labels, contextual category clues, and semantic embeddings, to enhance boundary detection. The input text is annotated using the BIOES (Begin, Inside, Outside, End, Single) tagging scheme and subsequently encoded by ClinicalBERT. The encoded features are then passed through a bidirectional long short term memory (BiLSTM) network and a conditional random field (CRF) layer for final label prediction.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Experiments conducted on publicly available datasets demonstrate that the proposed approach achieves an <jats:italic>F<\/jats:italic>1 score of 89.44 percent, surpassing multiple existing baseline models in performance.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>These findings confirm that the integration of domain specific language modeling, structured medical knowledge, and enriched character level features significantly enhances NER accuracy in Chinese EMRs. The proposed method shows strong potential for practical deployment in clinical information extraction systems.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2025.1634774","type":"journal-article","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T05:26:28Z","timestamp":1757481988000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Named entity recognition for Chinese electronic medical records by integrating knowledge graph and ClinicalBERT"],"prefix":"10.3389","volume":"8","author":[{"given":"Xiang","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengxiong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,10]]},"reference":[{"key":"ref1","article-title":"Publicly available clinical BERT embeddings","author":"Alsentzer","year":"2019"},{"key":"ref2","first-page":"26","article-title":"Translating embeddings for modeling multi-relational data","author":"Bordes","year":"2013"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.findings-emnlp.58","article-title":"Revisiting pre-trained models for Chinese natural language processing","author":"Cui","year":"2020"},{"key":"ref4","first-page":"1","article-title":"Named entity recognition using BERT BiLSTM CRF for Chinese electronic health records","author":"Dai","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.13705\/j.issn.1671-6841.2024116","article-title":"A Medical Named Entity Recognition Data Augmentation Method Based on EALMDA","author":"Dao","year":"2024","journal-title":"J. Zhengzhou Univ."},{"key":"ref6","first-page":"5530","article-title":"Reports of personal experiences and stories in argumentation: datasets and analysis","author":"Falk","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1220","DOI":"10.16208\/j.issn1000-7024.2023.04.035","article-title":"Chinese Electronic Medical Record Named Entity Recognition Based on BERT","volume":"44","author":"Feng","year":"2023","journal-title":"Comput. Eng. Des."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"100042","DOI":"10.1016\/j.cmpbup.2021.100042","article-title":"BERT based clinical knowledge extraction for biomedical knowledge graph construction and analysis","volume":"1","author":"Harnoune","year":"2021","journal-title":"Comput. Methods Programs Biomed. Update"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"7702","DOI":"10.3390\/app12157702","article-title":"KGNER: improving Chinese named entity recognition by BERT infused with the knowledge graph","volume":"12","author":"Hu","year":"2022","journal-title":"Appl. Sci."},{"key":"ref10","article-title":"ClinicalBERT: modeling clinical notes and predicting hospital readmission","author":"Huang","year":"2019"},{"key":"ref11","first-page":"537","article-title":"Named entity recognition in traditional Chinese medicine clinical cases combining BiLSTM-CRF with knowledge graph","author":"Jin","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","article-title":"A survey of convolutional neural networks: analysis, applications, and prospects","volume":"33","author":"Li","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.acl-main.611","article-title":"FLAT: Chinese NER using flat-lattice transformer","author":"Li","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.neucom.2021.10.101","article-title":"Chinese named entity recognition: the state of the art","volume":"473","author":"Liu","year":"2022","journal-title":"Neurocomputing"},{"key":"ref16","first-page":"17","article-title":"Conditional random fields for object recognition","author":"Quattoni","year":"2004"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"100","DOI":"10.13833\/j.issn.1007-7634.2024.03.012","article-title":"Multi-Graph Enabled Named Entity Recognition for Chinese Medical Records Processing","volume":"42","author":"Shan","year":"2024","journal-title":"Inf. Sci."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1186\/s12859-021-04260-y","article-title":"Deep learning with language models improves named entity recognition for PharmaCoNER","volume":"22","author":"Sun","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1162\/tacl_a_00360","article-title":"KEPLER: a unified model for knowledge embedding and pre-trained language representation","volume":"9","author":"Wang","year":"2021","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"5711","DOI":"10.3390\/app10165711","article-title":"An ERNIE-based joint model for Chinese named entity recognition","volume":"10","author":"Wang","year":"2020","journal-title":"Appl. Sci."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"2489754","DOI":"10.1155\/2021\/2489754","article-title":"Research on named entity recognition of electronic medical records based on RoBERTa and radical-level feature","volume":"2021","author":"Wu","year":"2021","journal-title":"Wirel. Commun. Mob. Comput."},{"key":"ref22","first-page":"2269","article-title":"Exploiting multiple embeddings for chinese named entity recognition","author":"Xu","year":"2019"},{"key":"ref23","first-page":"576","article-title":"A survey on knowledge graph embedding","author":"Yan","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"251","DOI":"10.11925\/infotech.2096-3467.2021.0910","article-title":"Named entity recognition for Chinese EMR with RoBERTa-WWM-BiLSTM-CRF","volume":"6","author":"Zhang","year":"2022","journal-title":"Data Anal. Knowl. Discov."},{"key":"ref25","first-page":"1554","article-title":"Chinese NER using lattice LSTM","author":"Zhang","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"454","DOI":"10.13744\/j.cnki.cn21-1431\/g4.2024.05.007","article-title":"A Path Enhanced Multi-hop Question Answering Method Based on Knowledge Graph Embedding","volume":"26","author":"Zhao","year":"2024","journal-title":"J. Dalian National. Univ."},{"key":"ref27","article-title":"MELM: data augmentation with masked entity language modeling for low-resource NER","author":"Zhou","year":"2021"},{"key":"ref28","first-page":"207","article-title":"Attention-based bidirectional long short-term memory networks for relation classification","author":"Zhou","year":"2016"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1634774\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T05:26:33Z","timestamp":1757481993000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1634774\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,10]]},"references-count":28,"alternative-id":["10.3389\/frai.2025.1634774"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1634774","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,10]]},"article-number":"1634774"}}