Application of Entity-BERT model based on neuroscience and brain-like cognition in electronic medical record entity recognition
IntroductionIn the medical field, electronic medical records contain a large amount of textual information, and the unstructured nature of this information makes data extraction and analysis challenging. Therefore, automatic extraction of entity information from electronic medical records has become...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-09-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2023.1259652/full |
| _version_ | 1827811944184152064 |
|---|---|
| author | Weijia Lu Weijia Lu Jiehui Jiang Yaxiang Shi Xiaowei Zhong Jun Gu Lixia Huangfu Ming Gong |
| author_facet | Weijia Lu Weijia Lu Jiehui Jiang Yaxiang Shi Xiaowei Zhong Jun Gu Lixia Huangfu Ming Gong |
| author_sort | Weijia Lu |
| collection | DOAJ |
| description | IntroductionIn the medical field, electronic medical records contain a large amount of textual information, and the unstructured nature of this information makes data extraction and analysis challenging. Therefore, automatic extraction of entity information from electronic medical records has become a significant issue in the healthcare domain.MethodsTo address this problem, this paper proposes a deep learning-based entity information extraction model called Entity-BERT. The model aims to leverage the powerful feature extraction capabilities of deep learning and the pre-training language representation learning of BERT(Bidirectional Encoder Representations from Transformers), enabling it to automatically learn and recognize various entity types in medical electronic records, including medical terminologies, disease names, drug information, and more, providing more effective support for medical research and clinical practices. The Entity-BERT model utilizes a multi-layer neural network and cross-attention mechanism to process and fuse information at different levels and types, resembling the hierarchical and distributed processing of the human brain. Additionally, the model employs pre-trained language and sequence models to process and learn textual data, sharing similarities with the language processing and semantic understanding of the human brain. Furthermore, the Entity-BERT model can capture contextual information and long-term dependencies, combining the cross-attention mechanism to handle the complex and diverse language expressions in electronic medical records, resembling the information processing method of the human brain in many aspects. Additionally, exploring how to utilize competitive learning, adaptive regulation, and synaptic plasticity to optimize the model's prediction results, automatically adjust its parameters, and achieve adaptive learning and dynamic adjustments from the perspective of neuroscience and brain-like cognition is of interest.Results and discussionExperimental results demonstrate that the Entity-BERT model achieves outstanding performance in entity recognition tasks within electronic medical records, surpassing other existing entity recognition models. This research not only provides more efficient and accurate natural language processing technology for the medical and health field but also introduces new ideas and directions for the design and optimization of deep learning models. |
| first_indexed | 2024-03-11T23:12:23Z |
| format | Article |
| id | doaj.art-52ce4f0a570442169e1d6cecc4859d47 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-03-11T23:12:23Z |
| publishDate | 2023-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-52ce4f0a570442169e1d6cecc4859d472023-09-21T07:20:46ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2023-09-011710.3389/fnins.2023.12596521259652Application of Entity-BERT model based on neuroscience and brain-like cognition in electronic medical record entity recognitionWeijia Lu0Weijia Lu1Jiehui Jiang2Yaxiang Shi3Xiaowei Zhong4Jun Gu5Lixia Huangfu6Ming Gong7Science and Technology Department, Affiliated Hospital of Nantong University, Nantong, ChinaJianghai Hospital of Nantong Sutong Science and Technology Park, Nantong, ChinaDepartment of Biomedical Engineering, Shanghai University, Shanghai, ChinaNetwork Information Center, Zhongda Hospital Southeast University, Nanjing, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaDepartment of Respiratory, Affiliated Hospital Nantong University, Nantong, ChinaInformation Center Department, Affiliated Hospital of Nantong University, Nantong, ChinaInformation Center Department, Affiliated Hospital of Nantong University, Nantong, ChinaIntroductionIn the medical field, electronic medical records contain a large amount of textual information, and the unstructured nature of this information makes data extraction and analysis challenging. Therefore, automatic extraction of entity information from electronic medical records has become a significant issue in the healthcare domain.MethodsTo address this problem, this paper proposes a deep learning-based entity information extraction model called Entity-BERT. The model aims to leverage the powerful feature extraction capabilities of deep learning and the pre-training language representation learning of BERT(Bidirectional Encoder Representations from Transformers), enabling it to automatically learn and recognize various entity types in medical electronic records, including medical terminologies, disease names, drug information, and more, providing more effective support for medical research and clinical practices. The Entity-BERT model utilizes a multi-layer neural network and cross-attention mechanism to process and fuse information at different levels and types, resembling the hierarchical and distributed processing of the human brain. Additionally, the model employs pre-trained language and sequence models to process and learn textual data, sharing similarities with the language processing and semantic understanding of the human brain. Furthermore, the Entity-BERT model can capture contextual information and long-term dependencies, combining the cross-attention mechanism to handle the complex and diverse language expressions in electronic medical records, resembling the information processing method of the human brain in many aspects. Additionally, exploring how to utilize competitive learning, adaptive regulation, and synaptic plasticity to optimize the model's prediction results, automatically adjust its parameters, and achieve adaptive learning and dynamic adjustments from the perspective of neuroscience and brain-like cognition is of interest.Results and discussionExperimental results demonstrate that the Entity-BERT model achieves outstanding performance in entity recognition tasks within electronic medical records, surpassing other existing entity recognition models. This research not only provides more efficient and accurate natural language processing technology for the medical and health field but also introduces new ideas and directions for the design and optimization of deep learning models.https://www.frontiersin.org/articles/10.3389/fnins.2023.1259652/fullBERTLSTMcross attentionentity recognitionelectronic medical records |
| spellingShingle | Weijia Lu Weijia Lu Jiehui Jiang Yaxiang Shi Xiaowei Zhong Jun Gu Lixia Huangfu Ming Gong Application of Entity-BERT model based on neuroscience and brain-like cognition in electronic medical record entity recognition Frontiers in Neuroscience BERT LSTM cross attention entity recognition electronic medical records |
| title | Application of Entity-BERT model based on neuroscience and brain-like cognition in electronic medical record entity recognition |
| title_full | Application of Entity-BERT model based on neuroscience and brain-like cognition in electronic medical record entity recognition |
| title_fullStr | Application of Entity-BERT model based on neuroscience and brain-like cognition in electronic medical record entity recognition |
| title_full_unstemmed | Application of Entity-BERT model based on neuroscience and brain-like cognition in electronic medical record entity recognition |
| title_short | Application of Entity-BERT model based on neuroscience and brain-like cognition in electronic medical record entity recognition |
| title_sort | application of entity bert model based on neuroscience and brain like cognition in electronic medical record entity recognition |
| topic | BERT LSTM cross attention entity recognition electronic medical records |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2023.1259652/full |
| work_keys_str_mv | AT weijialu applicationofentitybertmodelbasedonneuroscienceandbrainlikecognitioninelectronicmedicalrecordentityrecognition AT weijialu applicationofentitybertmodelbasedonneuroscienceandbrainlikecognitioninelectronicmedicalrecordentityrecognition AT jiehuijiang applicationofentitybertmodelbasedonneuroscienceandbrainlikecognitioninelectronicmedicalrecordentityrecognition AT yaxiangshi applicationofentitybertmodelbasedonneuroscienceandbrainlikecognitioninelectronicmedicalrecordentityrecognition AT xiaoweizhong applicationofentitybertmodelbasedonneuroscienceandbrainlikecognitioninelectronicmedicalrecordentityrecognition AT jungu applicationofentitybertmodelbasedonneuroscienceandbrainlikecognitioninelectronicmedicalrecordentityrecognition AT lixiahuangfu applicationofentitybertmodelbasedonneuroscienceandbrainlikecognitioninelectronicmedicalrecordentityrecognition AT minggong applicationofentitybertmodelbasedonneuroscienceandbrainlikecognitioninelectronicmedicalrecordentityrecognition |