A Comparison between Named Entity Recognition Models in the Biomedical Domain

Abstract

The domain-specialised application of Named Entity Recognition (NER) is known as Biomedical NER (BioNER), which aims to identify and classify biomedical concepts that are of interest to researchers, such as genes, proteins, chemical compounds, drugs, mutations, diseases, and so on. The BioNER task is very similar to general NER but recognising Biomedical Named Entities (BNEs) is more challenging than recognising proper names from newspapers due to the characteristics of biomedical nomenclature. In order to address the challenges posed by BioNER, seven machine learning models were implemented comparing a transfer learning approach based on fine-tuned BERT with Bi-LSTM based neural models and a CRF model used as baseline. Precision, Recall and F1-score were used as performance scores evaluating the models on two well-known biomedical corpora: JNLPBA and BIOCREATIVE IV (BC-IV). Strict and partial matching were considered as evaluation criteria. The reported results show that a transfer learning approach based on fine-tuned BERT outperforms all others methods achieving the highest scores for all metrics on both corpora.

Improving Information Extraction from Pathology Reports using Named Entity Recognition

“…Furthermore, we fine-tuned our model for the NER task, offering a flexible and scalable solution for many applications 35 . While TF-IDF 32 and LSTM 33 have been successful in text classification, large language models (LLM) such as BERT have produced state-of-the-art performances on more complex tasks such as NER 36,37 . One of the key advantages of BERT over other approaches is its ability to capture the context and meaning of words in a sentence, by considering the surrounding contexts of each word and understanding the nuances of natural language.…”

An Automatic Generation of Heterogeneous Knowledge Graph for Global Disease Support: A Demonstration of a Cancer Use Case

“…Currently, these are the best models for NLP systems that provide reliable annotating and mapping of the text of biomedical and medical terms and documents to UMLS concepts, which is a comprehensive resource of medically relevant concepts and relationships. The pretrained model adopted is based on BERT [67], as BERT-based models have proved to have better precision, recall, and F1 score in the biomedical domain, the BERT-based models are now considered one of the benchmarks for biomedical name entity recognition [68,69]. The model annotates the text using the concept unique identifier (CUI) of UMLS giving a similarity score.…”

A BERT-based ensemble learning approach for the BioCreative VII challenges: full-text chemical identification and multi-label classification in PubMed articles

“…Moreover, the biomedical domain is a rapidly evolving field in which new concepts and names are coined on a regular basis. As biomedical concepts are investigated in different disciplines of medicine with distinct naming conventions, new variations are always produced for already existing concepts ( 8 ). These new names and concepts make it difficult to extract, classify and comprehend the various formats of terms and often result in the misrecognition of relevant biological entities.…”