Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

EasyNER: A Customizable Easy-to-Use Pipeline for Deep Learning- and Dictionary-based Named Entity Recognition from Medical Text

Ahmed, Rafsan LU orcid ; Berntsson, Petter ; Skafte, Alexander ; Kazemi Rashed, Salma LU ; Klang, Marcus LU orcid ; Barvesten, Adam ; Olde, Ola ; Lindholm, William ; Lamarca Arrizabalaga, Antton and Nugues, Pierre LU orcid , et al. (2023)
Abstract
Medical research generates a large number of publications with the PubMed database already containing >35 million research articles. Integration of the knowledge scattered across this large body of literature could provide key insights into physiological mechanisms and disease processes leading to novel medical interventions. However, it is a great challenge for researchers to utilize this information in full since the scale and complexity of the data greatly surpasses human processing abilities. This becomes especially problematic in cases of extreme urgency like the COVID-19 pandemic. Automated text mining can help extract and connect information from the large body of medical research articles. The first step in text mining is... (More)
Medical research generates a large number of publications with the PubMed database already containing >35 million research articles. Integration of the knowledge scattered across this large body of literature could provide key insights into physiological mechanisms and disease processes leading to novel medical interventions. However, it is a great challenge for researchers to utilize this information in full since the scale and complexity of the data greatly surpasses human processing abilities. This becomes especially problematic in cases of extreme urgency like the COVID-19 pandemic. Automated text mining can help extract and connect information from the large body of medical research articles. The first step in text mining is typically the identification of specific classes of keywords (e.g., all protein or disease names), so called Named Entity Recognition (NER). Here we present an end-to-end pipeline for NER of typical entities found in medical research articles, including diseases, cells, chemicals, genes/proteins, and species. The pipeline can access and process large medical research article collections (PubMed, CORD-19) or raw text and incorporates a series of deep learning models fine-tuned on the HUNER corpora collection. In addition, the pipeline can perform dictionary-based NER related to COVID-19 and other medical topics. Users can also load their own NER models and dictionaries to include additional entities. The output consists of publication-ready ranked lists and graphs of detected entities and files containing the annotated texts. An associated script allows rapid inspection of the results for specific entities of interest. As model use cases, the pipeline was deployed on two collections of autophagy-related abstracts from PubMed and on the CORD19 dataset, a collection of 764 398 research article abstracts related to COVID-19. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Working paper/Preprint
publication status
published
subject
keywords
Named Entity Recognition, medical text mining, natural language processing, BioNLP, COVID-19, autophagy, SARS-CoV2, BioBERT
publisher
arXiv.org
DOI
10.48550/arXiv.2304.07805
project
Lund University AI Research
Biomedical text mining for systems biology
Environmental toxins as cause of lysosomal damage-induced cell death in animals and humans
LU Land
Artificial intelligence-based text mining for COVID-19 and other areas of medicine
Lysosomes in cell death - from molecular mechanisms to new treatment strategies
Studying COVID-19 with artificial intelligence
Using artificial intelligence and advanced computational tools to identify biological pathways, disease mechanisms and therapeutic opportunities
language
English
LU publication?
yes
id
51067a26-2291-43ee-aa76-23a7bf63720c
date added to LUP
2023-05-12 15:03:29
date last changed
2024-02-14 14:10:57
@misc{51067a26-2291-43ee-aa76-23a7bf63720c,
  abstract     = {{Medical research generates a large number of publications with the PubMed database already containing >35 million research articles. Integration of the knowledge scattered across this large body of literature could provide key insights into physiological mechanisms and disease processes leading to novel medical interventions. However, it is a great challenge for researchers to utilize this information in full since the scale and complexity of the data greatly surpasses human processing abilities. This becomes especially problematic in cases of extreme urgency like the COVID-19 pandemic. Automated text mining can help extract and connect information from the large body of medical research articles. The first step in text mining is typically the identification of specific classes of keywords (e.g., all protein or disease names), so called Named Entity Recognition (NER). Here we present an end-to-end pipeline for NER of typical entities found in medical research articles, including diseases, cells, chemicals, genes/proteins, and species. The pipeline can access and process large medical research article collections (PubMed, CORD-19) or raw text and incorporates a series of deep learning models fine-tuned on the HUNER corpora collection. In addition, the pipeline can perform dictionary-based NER related to COVID-19 and other medical topics. Users can also load their own NER models and dictionaries to include additional entities. The output consists of publication-ready ranked lists and graphs of detected entities and files containing the annotated texts. An associated script allows rapid inspection of the results for specific entities of interest. As model use cases, the pipeline was deployed on two collections of autophagy-related abstracts from PubMed and on the CORD19 dataset, a collection of 764 398 research article abstracts related to COVID-19.}},
  author       = {{Ahmed, Rafsan and Berntsson, Petter and Skafte, Alexander and Kazemi Rashed, Salma and Klang, Marcus and Barvesten, Adam and Olde, Ola and Lindholm, William and Lamarca Arrizabalaga, Antton and Nugues, Pierre and Aits, Sonja}},
  keywords     = {{Named Entity Recognition; medical text mining; natural language processing; BioNLP; COVID-19; autophagy; SARS-CoV2; BioBERT}},
  language     = {{eng}},
  month        = {{04}},
  note         = {{Preprint}},
  publisher    = {{arXiv.org}},
  title        = {{EasyNER: A Customizable Easy-to-Use Pipeline for Deep Learning- and Dictionary-based Named Entity Recognition from Medical Text}},
  url          = {{http://dx.doi.org/10.48550/arXiv.2304.07805}},
  doi          = {{10.48550/arXiv.2304.07805}},
  year         = {{2023}},
}