@inproceedings{nkolele-2020-mapping,
title = "Mapping of Narrative Text Fields To {ICD}-10 Codes Using Natural Language Processing and Machine Learning",
author = "Nkolele, Risuna",
editor = "Cunha, Rossana and
Shaikh, Samira and
Varis, Erika and
Georgi, Ryan and
Tsai, Alicia and
Anastasopoulos, Antonios and
Chandu, Khyathi Raghavi",
booktitle = "Proceedings of the Fourth Widening Natural Language Processing Workshop",
month = jul,
year = "2020",
address = "Seattle, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.winlp-1.35",
doi = "10.18653/v1/2020.winlp-1.35",
pages = "131--135",
abstract = "The assignment of ICD-10 codes is done manually, which is laborious and prone to errors. The use of natural language processing and machine learning approaches have been receiving increasing attention on automating the task of assigning ICD-10 codes. In this study, we investigate the effect of different approaches on automating the task of assigning ICD-10 codes. To do this we use the South African clinical dataset containing three narrative text fields (Clinical Summary, Presenting Complaints, and Examination Findings). The following traditional machine learning algorithms, namely: Logistic Regression, Multinomial Naive Bayes, Support Vector Machine, Decision Tree, RandomForest, and Extreme Gradient Boost were used as our classifiers. Our study results show the strong potential of automated ICD-10 coding from the narrative text fields. ExtremeGradient Boost outperformed other classifiers in automating the task of assigning ICD-10 codes based on the three narrative text fields with an accuracy of 79{\%}, precision of75{\%}, and recall of 78{\%}. While our worst classifier (Decision Tree) achieved the accuracy of 54{\%}, precision of 60{\%} and recall of 56{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nkolele-2020-mapping">
<titleInfo>
<title>Mapping of Narrative Text Fields To ICD-10 Codes Using Natural Language Processing and Machine Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Risuna</namePart>
<namePart type="family">Nkolele</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Widening Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rossana</namePart>
<namePart type="family">Cunha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samira</namePart>
<namePart type="family">Shaikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erika</namePart>
<namePart type="family">Varis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Georgi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="given">Raghavi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The assignment of ICD-10 codes is done manually, which is laborious and prone to errors. The use of natural language processing and machine learning approaches have been receiving increasing attention on automating the task of assigning ICD-10 codes. In this study, we investigate the effect of different approaches on automating the task of assigning ICD-10 codes. To do this we use the South African clinical dataset containing three narrative text fields (Clinical Summary, Presenting Complaints, and Examination Findings). The following traditional machine learning algorithms, namely: Logistic Regression, Multinomial Naive Bayes, Support Vector Machine, Decision Tree, RandomForest, and Extreme Gradient Boost were used as our classifiers. Our study results show the strong potential of automated ICD-10 coding from the narrative text fields. ExtremeGradient Boost outperformed other classifiers in automating the task of assigning ICD-10 codes based on the three narrative text fields with an accuracy of 79%, precision of75%, and recall of 78%. While our worst classifier (Decision Tree) achieved the accuracy of 54%, precision of 60% and recall of 56%.</abstract>
<identifier type="citekey">nkolele-2020-mapping</identifier>
<identifier type="doi">10.18653/v1/2020.winlp-1.35</identifier>
<location>
<url>https://aclanthology.org/2020.winlp-1.35</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>131</start>
<end>135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mapping of Narrative Text Fields To ICD-10 Codes Using Natural Language Processing and Machine Learning
%A Nkolele, Risuna
%Y Cunha, Rossana
%Y Shaikh, Samira
%Y Varis, Erika
%Y Georgi, Ryan
%Y Tsai, Alicia
%Y Anastasopoulos, Antonios
%Y Chandu, Khyathi Raghavi
%S Proceedings of the Fourth Widening Natural Language Processing Workshop
%D 2020
%8 July
%I Association for Computational Linguistics
%C Seattle, USA
%F nkolele-2020-mapping
%X The assignment of ICD-10 codes is done manually, which is laborious and prone to errors. The use of natural language processing and machine learning approaches have been receiving increasing attention on automating the task of assigning ICD-10 codes. In this study, we investigate the effect of different approaches on automating the task of assigning ICD-10 codes. To do this we use the South African clinical dataset containing three narrative text fields (Clinical Summary, Presenting Complaints, and Examination Findings). The following traditional machine learning algorithms, namely: Logistic Regression, Multinomial Naive Bayes, Support Vector Machine, Decision Tree, RandomForest, and Extreme Gradient Boost were used as our classifiers. Our study results show the strong potential of automated ICD-10 coding from the narrative text fields. ExtremeGradient Boost outperformed other classifiers in automating the task of assigning ICD-10 codes based on the three narrative text fields with an accuracy of 79%, precision of75%, and recall of 78%. While our worst classifier (Decision Tree) achieved the accuracy of 54%, precision of 60% and recall of 56%.
%R 10.18653/v1/2020.winlp-1.35
%U https://aclanthology.org/2020.winlp-1.35
%U https://doi.org/10.18653/v1/2020.winlp-1.35
%P 131-135
Markdown (Informal)
[Mapping of Narrative Text Fields To ICD-10 Codes Using Natural Language Processing and Machine Learning](https://aclanthology.org/2020.winlp-1.35) (Nkolele, WiNLP 2020)
ACL