NLP has a significant role in advancing healthcare and has been found to be
key in extracting structured information from radiology reports. Understanding
recent developments in NLP application to radiology is of significance but
recent reviews on this are limited. This study systematically assesses recent
literature in NLP applied to radiology reports. Our automated literature search
yields 4,799 results using automated filtering, metadata enriching steps and
citation search combined with manual review. Our analysis is based on 21
variables including radiology characteristics, NLP methodology, performance,
study, and clinical application characteristics. We present a comprehensive
analysis of the 164 publications retrieved with each categorised into one of 6
clinical application categories. Deep learning use increases but conventional
machine learning approaches are still prevalent. Deep learning remains
challenged when data is scarce and there is little evidence of adoption into
clinical practice. Despite 17% of studies reporting greater than 0.85 F1
scores, it is hard to comparatively evaluate these approaches given that most
of them use different datasets. Only 14 studies made their data and 15 their
code available with 10 externally validating results. Automated understanding
of clinical narratives of the radiology reports has the potential to enhance
the healthcare process but reproducibility and explainability of models are
important if the domain is to move applications into clinical use. More could
be done to share code enabling validation of methods on different institutional
data and to reduce heterogeneity in reporting of study properties allowing
inter-study comparisons. Our results have significance for researchers
providing a systematic synthesis of existing work to build on, identify gaps,
opportunities for collaboration and avoid duplication.
Beschreibung
[2102.09553] A Systematic Review of Natural Language Processing Applied to Radiology Reports
%0 Generic
%1 casey2021systematic
%A Casey, Arlene
%A Davidson, Emma
%A Poon, Michael
%A Dong, Hang
%A Duma, Daniel
%A Grivas, Andreas
%A Grover, Claire
%A Suárez-Paniagua, Víctor
%A Tobin, Richard
%A Whiteley, William
%A Wu, Honghan
%A Alex, Beatrice
%D 2021
%K clinical_nlp clinical_notes computational_linguistics edinburgh knowledge myown natural-language-processing nlp radiology radiology_reports review survey systematic_review usher
%T A Systematic Review of Natural Language Processing Applied to Radiology
Reports
%U http://arxiv.org/abs/2102.09553
%X NLP has a significant role in advancing healthcare and has been found to be
key in extracting structured information from radiology reports. Understanding
recent developments in NLP application to radiology is of significance but
recent reviews on this are limited. This study systematically assesses recent
literature in NLP applied to radiology reports. Our automated literature search
yields 4,799 results using automated filtering, metadata enriching steps and
citation search combined with manual review. Our analysis is based on 21
variables including radiology characteristics, NLP methodology, performance,
study, and clinical application characteristics. We present a comprehensive
analysis of the 164 publications retrieved with each categorised into one of 6
clinical application categories. Deep learning use increases but conventional
machine learning approaches are still prevalent. Deep learning remains
challenged when data is scarce and there is little evidence of adoption into
clinical practice. Despite 17% of studies reporting greater than 0.85 F1
scores, it is hard to comparatively evaluate these approaches given that most
of them use different datasets. Only 14 studies made their data and 15 their
code available with 10 externally validating results. Automated understanding
of clinical narratives of the radiology reports has the potential to enhance
the healthcare process but reproducibility and explainability of models are
important if the domain is to move applications into clinical use. More could
be done to share code enabling validation of methods on different institutional
data and to reduce heterogeneity in reporting of study properties allowing
inter-study comparisons. Our results have significance for researchers
providing a systematic synthesis of existing work to build on, identify gaps,
opportunities for collaboration and avoid duplication.
@misc{casey2021systematic,
abstract = {NLP has a significant role in advancing healthcare and has been found to be
key in extracting structured information from radiology reports. Understanding
recent developments in NLP application to radiology is of significance but
recent reviews on this are limited. This study systematically assesses recent
literature in NLP applied to radiology reports. Our automated literature search
yields 4,799 results using automated filtering, metadata enriching steps and
citation search combined with manual review. Our analysis is based on 21
variables including radiology characteristics, NLP methodology, performance,
study, and clinical application characteristics. We present a comprehensive
analysis of the 164 publications retrieved with each categorised into one of 6
clinical application categories. Deep learning use increases but conventional
machine learning approaches are still prevalent. Deep learning remains
challenged when data is scarce and there is little evidence of adoption into
clinical practice. Despite 17% of studies reporting greater than 0.85 F1
scores, it is hard to comparatively evaluate these approaches given that most
of them use different datasets. Only 14 studies made their data and 15 their
code available with 10 externally validating results. Automated understanding
of clinical narratives of the radiology reports has the potential to enhance
the healthcare process but reproducibility and explainability of models are
important if the domain is to move applications into clinical use. More could
be done to share code enabling validation of methods on different institutional
data and to reduce heterogeneity in reporting of study properties allowing
inter-study comparisons. Our results have significance for researchers
providing a systematic synthesis of existing work to build on, identify gaps,
opportunities for collaboration and avoid duplication.},
added-at = {2021-03-01T09:21:50.000+0100},
author = {Casey, Arlene and Davidson, Emma and Poon, Michael and Dong, Hang and Duma, Daniel and Grivas, Andreas and Grover, Claire and Suárez-Paniagua, Víctor and Tobin, Richard and Whiteley, William and Wu, Honghan and Alex, Beatrice},
biburl = {https://www.bibsonomy.org/bibtex/2e8a9c9b98f52c22782c57bd68b301cb6/hangdong},
description = {[2102.09553] A Systematic Review of Natural Language Processing Applied to Radiology Reports},
interhash = {dbe3da2ebe429f230f8663df8acfe3bb},
intrahash = {e8a9c9b98f52c22782c57bd68b301cb6},
keywords = {clinical_nlp clinical_notes computational_linguistics edinburgh knowledge myown natural-language-processing nlp radiology radiology_reports review survey systematic_review usher},
note = {cite arxiv:2102.09553},
timestamp = {2021-03-01T09:21:50.000+0100},
title = {A Systematic Review of Natural Language Processing Applied to Radiology
Reports},
url = {http://arxiv.org/abs/2102.09553},
year = 2021
}