Integration of natural and deep artificial cognitive models in medical images: BERT-based NER and relation extraction for electronic medical records
IntroductionMedical images and signals are important data sources in the medical field, and they contain key information such as patients' physiology, pathology, and genetics. However, due to the complexity and diversity of medical images and signals, resulting in difficulties in medical knowle...
| 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.2023.1266771/full |
| _version_ | 1797693920749027328 |
|---|---|
| author | Bo Guo Bo Guo Huaming Liu Lei Niu |
| author_facet | Bo Guo Bo Guo Huaming Liu Lei Niu |
| author_sort | Bo Guo |
| collection | DOAJ |
| description | IntroductionMedical images and signals are important data sources in the medical field, and they contain key information such as patients' physiology, pathology, and genetics. However, due to the complexity and diversity of medical images and signals, resulting in difficulties in medical knowledge acquisition and decision support.MethodsIn order to solve this problem, this paper proposes an end-to-end framework based on BERT for NER and RE tasks in electronic medical records. Our framework first integrates NER and RE tasks into a unified model, adopting an end-to-end processing manner, which removes the limitation and error propagation of multiple independent steps in traditional methods. Second, by pre-training and fine-tuning the BERT model on large-scale electronic medical record data, we enable the model to obtain rich semantic representation capabilities that adapt to the needs of medical fields and tasks. Finally, through multi-task learning, we enable the model to make full use of the correlation and complementarity between NER and RE tasks, and improve the generalization ability and effect of the model on different data sets.Results and discussionWe conduct experimental evaluation on four electronic medical record datasets, and the model significantly out performs other methods on different datasets in the NER task. In the RE task, the EMLB model also achieved advantages on different data sets, especially in the multi-task learning mode, its performance has been significantly improved, and the ETE and MTL modules performed well in terms of comprehensive precision and recall. Our research provides an innovative solution for medical image and signal data. |
| first_indexed | 2024-03-12T02:50:38Z |
| format | Article |
| id | doaj.art-c0856c5f598449a696c76f22c9ba97cf |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-03-12T02:50:38Z |
| publishDate | 2023-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-c0856c5f598449a696c76f22c9ba97cf2023-09-04T05:02:57ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2023-09-011710.3389/fnins.2023.12667711266771Integration of natural and deep artificial cognitive models in medical images: BERT-based NER and relation extraction for electronic medical recordsBo Guo0Bo Guo1Huaming Liu2Lei Niu3School of Computer and Information Engineering, Fuyang Normal University, Fuyang, ChinaDepartment of Computing, Faculty of Communication, Visual Art and Computing, Universiti Selangor, Bestari Jaya, Selangor, MalaysiaSchool of Computer and Information Engineering, Fuyang Normal University, Fuyang, ChinaSchool of Computer and Information Engineering, Fuyang Normal University, Fuyang, ChinaIntroductionMedical images and signals are important data sources in the medical field, and they contain key information such as patients' physiology, pathology, and genetics. However, due to the complexity and diversity of medical images and signals, resulting in difficulties in medical knowledge acquisition and decision support.MethodsIn order to solve this problem, this paper proposes an end-to-end framework based on BERT for NER and RE tasks in electronic medical records. Our framework first integrates NER and RE tasks into a unified model, adopting an end-to-end processing manner, which removes the limitation and error propagation of multiple independent steps in traditional methods. Second, by pre-training and fine-tuning the BERT model on large-scale electronic medical record data, we enable the model to obtain rich semantic representation capabilities that adapt to the needs of medical fields and tasks. Finally, through multi-task learning, we enable the model to make full use of the correlation and complementarity between NER and RE tasks, and improve the generalization ability and effect of the model on different data sets.Results and discussionWe conduct experimental evaluation on four electronic medical record datasets, and the model significantly out performs other methods on different datasets in the NER task. In the RE task, the EMLB model also achieved advantages on different data sets, especially in the multi-task learning mode, its performance has been significantly improved, and the ETE and MTL modules performed well in terms of comprehensive precision and recall. Our research provides an innovative solution for medical image and signal data.https://www.frontiersin.org/articles/10.3389/fnins.2023.1266771/fullmedical informaticsdecision support systemdeep artificial cognitive modelnatural language processingelectronic medical recordnamed entity recognition (NER) |
| spellingShingle | Bo Guo Bo Guo Huaming Liu Lei Niu Integration of natural and deep artificial cognitive models in medical images: BERT-based NER and relation extraction for electronic medical records Frontiers in Neuroscience medical informatics decision support system deep artificial cognitive model natural language processing electronic medical record named entity recognition (NER) |
| title | Integration of natural and deep artificial cognitive models in medical images: BERT-based NER and relation extraction for electronic medical records |
| title_full | Integration of natural and deep artificial cognitive models in medical images: BERT-based NER and relation extraction for electronic medical records |
| title_fullStr | Integration of natural and deep artificial cognitive models in medical images: BERT-based NER and relation extraction for electronic medical records |
| title_full_unstemmed | Integration of natural and deep artificial cognitive models in medical images: BERT-based NER and relation extraction for electronic medical records |
| title_short | Integration of natural and deep artificial cognitive models in medical images: BERT-based NER and relation extraction for electronic medical records |
| title_sort | integration of natural and deep artificial cognitive models in medical images bert based ner and relation extraction for electronic medical records |
| topic | medical informatics decision support system deep artificial cognitive model natural language processing electronic medical record named entity recognition (NER) |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2023.1266771/full |
| work_keys_str_mv | AT boguo integrationofnaturalanddeepartificialcognitivemodelsinmedicalimagesbertbasednerandrelationextractionforelectronicmedicalrecords AT boguo integrationofnaturalanddeepartificialcognitivemodelsinmedicalimagesbertbasednerandrelationextractionforelectronicmedicalrecords AT huamingliu integrationofnaturalanddeepartificialcognitivemodelsinmedicalimagesbertbasednerandrelationextractionforelectronicmedicalrecords AT leiniu integrationofnaturalanddeepartificialcognitivemodelsinmedicalimagesbertbasednerandrelationextractionforelectronicmedicalrecords |