MiNER Enhances Malaria Biomedical Entity Recognition in Clinical Texts.

The vast and growing body of scientific literature on malaria presents a significant challenge for researchers seeking to extract crucial biomedical information. To address this, a new fine-tuned biomedical natural language processing (NLP) model, MiNER, has been developed. This system aims to streamline the extraction of clinically significant entities related to malaria. MiNER's methodology involves selecting and preprocessing a large corpus of malaria articles, which are then meticulously annotated with relevant entities. It utilizes BioBERT, a leading pre-trained language model, and fine-tunes it with these domain-specific annotations through supervised learning. Extensive evaluations demonstrate that MiNER substantially surpasses other encoding and machine learning algorithms in terms of precision, recall, and accuracy. The researchers have also made their human-labeled dataset publicly available to support further advancements in malaria information extraction.