AUTHOR=Guo Bo , Liu Huaming , Niu Lei TITLE=Integration of natural and deep artificial cognitive models in medical images: BERT-based NER and relation extraction for electronic medical records JOURNAL=Frontiers in Neuroscience VOLUME=Volume 17 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2023.1266771 DOI=10.3389/fnins.2023.1266771 ISSN=1662-453X ABSTRACT=Medical 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. In order to solve this problem, this paper proposes an end-to-end framework based on BERT (Bidirectional Encoder Representation from Transformer) for NER and RE tasks in electronic medical records. Our framework employs the integration of natural and artificial cognitive systems to efficiently and accurately recognize named entities and relations in electronic medical records, thereby providing powerful support for medical image and signal processing. 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. We conduct experimental evaluation on four electronic medical record datasets, and the model significantly outperforms 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 and efficient solution for automated processing and knowledge mining of medical image and signal data.