Key points are not available for this paper at this time.
The research delves into the process of extracting relationships from biomedical literature and building a knowledge graph using those relationships. Information retrieval, knowledge discovery, and data analysis are just a few of the uses for named entity extraction in biomedical research, which includes important entities such as Adverse Drug Effects (ADE), doses, drug names, and more. Using BERT's word contextual comprehension, the report investigates the use of the BioBERT model for named entity recognition and relationship extraction. When calibrated on Electronic Health Records (EHR) data, BioBERT— a biological text-specific model—helps with clinical decision-making and research by recognizing links between elements such as diseases, symptoms, and therapies. The use of Neo4j for knowledge graph generation, which permits a thorough representation of biomedical concepts and their relationships, is also highlighted in the paper. Information retrieval and analysis are made easier by this organized knowledge. This strategy has the potential to revolutionize biomedical research and healthcare by providing fresh perspectives and better results, despite ongoing challenges. More developments in this field are anticipated as a result of ongoing research and development.
Tirpude et al. (Fri,) studied this question.