Auto-CORPus: A Natural Language Processing Tool for Standardising and Reusing Biomedical Literature

Hu, Yan; Sun, Shujian; Rowlands, Thomas; Beck, Tim; Posma, Joram M.

doi:10.1101/2021.01.08.425887

Cited by 3 publications

(4 citation statements)

References 23 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The rest were studies that belong to the 'general applicability' category, meaning they were tools or models not designed for specific health categories or diseases. They have general utilities for particular scenarios that might be applicable to a wide range of clinical use cases [50][51][52]54,57,[59][60][61]63,74,77,81,85,[104][105][106][109][110][111][112][113][114][119][120][121][122]124,125,131,136,137 .…”

Section: Literature Review Results On Publicationsmentioning

confidence: 99%

“…This category studies how ontologies and lexicons could be combined with other NLP methods to represent knowledge that can support clinicians. Studies include 33,41,[50][51][52]55,63,74,75,81,85,86,[104][105][106][107][108]110,114,119,131,132 .…”

Section: Literature Review Results On Publicationsmentioning

confidence: 99%

“…Classification containing 16 studies 34,48,49,58,60,79,80,100,112,116-118, 128,129,135,139 . Named Entity Recognition has been widely used in different clinical applications: 10 studies of Disease information & Classification 39,56,65,66,68,76,103,115,122,124 , 9 studies of Language discovery & knowledge 50,52,55,74,81,85,104,107,131 and 8 of Diagnostic surveillance 82,84,[87][88][89][90]92,133 . In particular, there were some areas (represented by small circles in the figure) that were clearly understudied, for example, Text Classification for Diagnostic surveillance 91,99 , Entity Normalisation for Diagnostic surveillance 126 and Natural Language Generation in any application domains 63 .…”

mentioning

confidence: 99%

See 2 more Smart Citations

A survey on clinical natural language processing in the United Kingdom from 2007 to 2022

Wang

et al. 2022

npj Digit. Med.

View full text Add to dashboard Cite

Much of the knowledge and information needed for enabling high-quality clinical research is stored in free-text format. Natural language processing (NLP) has been used to extract information from these sources at scale for several decades. This paper aims to present a comprehensive review of clinical NLP for the past 15 years in the UK to identify the community, depict its evolution, analyse methodologies and applications, and identify the main barriers. We collect a dataset of clinical NLP projects (n = 94; £ = 41.97 m) funded by UK funders or the European Union’s funding programmes. Additionally, we extract details on 9 funders, 137 organisations, 139 persons and 431 research papers. Networks are created from timestamped data interlinking all entities, and network analysis is subsequently applied to generate insights. 431 publications are identified as part of a literature review, of which 107 are eligible for final analysis. Results show, not surprisingly, clinical NLP in the UK has increased substantially in the last 15 years: the total budget in the period of 2019–2022 was 80 times that of 2007–2010. However, the effort is required to deepen areas such as disease (sub-)phenotyping and broaden application domains. There is also a need to improve links between academia and industry and enable deployments in real-world settings for the realisation of clinical NLP’s great potential in care delivery. The major barriers include research and development access to hospital data, lack of capable computational resources in the right places, the scarcity of labelled data and barriers to sharing of pretrained models.

show abstract

Section: Literature Review Results On Publicationsmentioning

confidence: 99%

Section: Literature Review Results On Publicationsmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

A survey on clinical natural language processing in the United Kingdom from 2007 to 2022

Wang

et al. 2022

npj Digit. Med.

View full text Add to dashboard Cite

show abstract

“…The broad variability in table structure makes them difficult to mine automatically. We have developed the Automated pipeline for Consistent Outputs from Research Publications (Auto-CORPus) text processing tool that converts publication full-text and tables to standardised machine-interpretable formats that can be analysed by text mining algorithms ( 37 ). In a collaboration with ELIXIR researchers, we are building Auto-CORPus into a text mining workflow to extract GWAS associations from the scientific literature at scale.…”

Section: Discussionmentioning

confidence: 99%

GWAS Central: an expanding resource for finding and visualising genotype and phenotype data from genome-wide association studies

Beck

Rowlands

Shorter

et al. 2022

Nucleic Acids Research

View full text Add to dashboard Cite

The GWAS Central resource gathers and curates extensive summary-level genome-wide association study (GWAS) data and puts a range of user-friendly but powerful website tools for the comparison and visualisation of GWAS data at the fingertips of researchers. Through our continued efforts to harmonise and import data received from GWAS authors and consortia, and data sets actively collected from public sources, the database now contains over 72.5 million P-values for over 5000 studies testing over 7.4 million unique genetic markers investigating over 1700 unique phenotypes. Here, we describe an update to integrate this extensive data collection with mouse disease model data to support insights into the functional impact of human genetic variation. GWAS Central has expanded to include mouse gene–phenotype associations observed during mouse gene knockout screens. To allow similar cross-species phenotypes to be compared, terms from mammalian and human phenotype ontologies have been mapped. New interactive interfaces to find, correlate and view human and mouse genotype–phenotype associations are included in the website toolkit. Additionally, the integrated browser for interrogating multiple association data sets has been updated and a GA4GH Beacon API endpoint has been added for discovering variants tested in GWAS. The GWAS Central resource is accessible at https://www.gwascentral.org/.

show abstract

An automatic system for extracting figure-caption pair from medical documents: a six-fold approach

Chaki

2023

PeerJ Computer Science

View full text Add to dashboard Cite

Background Figures and captions in medical documentation contain important information. As a result, researchers are becoming more interested in obtaining published medical figures from medical papers and utilizing the captions as a knowledge source. Methods This work introduces a unique and successful six-fold methodology for extracting figure-caption pairs. The A-torus wavelet transform is used to retrieve the first edge from the scanned page. Then, using the maximally stable extremal regions connected component feature, text and graphical contents are isolated from the edge document, and multi-layer perceptron is used to successfully detect and retrieve figures and captions from medical records. The figure-caption pair is then extracted using the bounding box approach. The files that contain the figures and captions are saved separately and supplied to the end useras theoutput of any investigation. The proposed approach is evaluated using a self-created database based on the pages collected from five open access books: Sergey Makarov, Gregory Noetscher and Aapo Nummenmaa’s book “Brain and Human Body Modelling 2021”, “Healthcare and Disease Burden in Africa” by Ilha Niohuru, “All-Optical Methods to Study Neuronal Function” by Eirini Papagiakoumou, “RNA, the Epicenter of Genetic Information” by John Mattick and Paulo Amaral and “Illustrated Manual of Pediatric Dermatology” by Susan Bayliss Mallory, Alanna Bree and Peggy Chern. Results Experiments and findings comparing the new method to earlier systems reveal a significant increase in efficiency, demonstrating the suggested technique’s robustness and efficiency.

show abstract

Auto-CORPus: A Natural Language Processing Tool for Standardising and Reusing Biomedical Literature

Cited by 3 publications

References 23 publications

A survey on clinical natural language processing in the United Kingdom from 2007 to 2022

A survey on clinical natural language processing in the United Kingdom from 2007 to 2022

GWAS Central: an expanding resource for finding and visualising genotype and phenotype data from genome-wide association studies

An automatic system for extracting figure-caption pair from medical documents: a six-fold approach

Contact Info

Product

Resources

About