@inproceedings{zhong-etal-2022-improving-precancerous,
title = "Improving Precancerous Case Characterization via Transformer-based Ensemble Learning",
author = "Zhong, Yizhen and
Xiao, Jiajie and
Vetterli, Thomas and
Matin, Mahan and
Loo, Ellen and
Lin, Jimmy and
Bourgon, Richard and
Shapira, Ofer",
editor = "Li, Yunyao and
Lazaridou, Angeliki",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-industry.38",
doi = "10.18653/v1/2022.emnlp-industry.38",
pages = "379--389",
abstract = "The application of natural language processing (NLP) to cancer pathology reports has been focused on detecting cancer cases, largely ignoring precancerous cases. Improving the characterization of precancerous adenomas assists in developing diagnostic tests for early cancer detection and prevention, especially for colorectal cancer (CRC). Here we developed transformer-based deep neural network NLP models to perform the CRC phenotyping, with the goal of extracting precancerous lesion attributes and distinguishing cancer and precancerous cases. We achieved 0.914 macro-F1 scores for classifying patients into negative, non-advanced adenoma, advanced adenoma and CRC. We further improved the performance to 0.923 using an ensemble of classifiers for cancer status classification and lesion size named-entity recognition (NER). Our results demonstrated the potential of using NLP to leverage real-world health record data to facilitate the development of diagnostic tests for early cancer prevention.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhong-etal-2022-improving-precancerous">
<titleInfo>
<title>Improving Precancerous Case Characterization via Transformer-based Ensemble Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yizhen</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajie</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Vetterli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahan</namePart>
<namePart type="family">Matin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Loo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimmy</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Bourgon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ofer</namePart>
<namePart type="family">Shapira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angeliki</namePart>
<namePart type="family">Lazaridou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The application of natural language processing (NLP) to cancer pathology reports has been focused on detecting cancer cases, largely ignoring precancerous cases. Improving the characterization of precancerous adenomas assists in developing diagnostic tests for early cancer detection and prevention, especially for colorectal cancer (CRC). Here we developed transformer-based deep neural network NLP models to perform the CRC phenotyping, with the goal of extracting precancerous lesion attributes and distinguishing cancer and precancerous cases. We achieved 0.914 macro-F1 scores for classifying patients into negative, non-advanced adenoma, advanced adenoma and CRC. We further improved the performance to 0.923 using an ensemble of classifiers for cancer status classification and lesion size named-entity recognition (NER). Our results demonstrated the potential of using NLP to leverage real-world health record data to facilitate the development of diagnostic tests for early cancer prevention.</abstract>
<identifier type="citekey">zhong-etal-2022-improving-precancerous</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-industry.38</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-industry.38</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>379</start>
<end>389</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Precancerous Case Characterization via Transformer-based Ensemble Learning
%A Zhong, Yizhen
%A Xiao, Jiajie
%A Vetterli, Thomas
%A Matin, Mahan
%A Loo, Ellen
%A Lin, Jimmy
%A Bourgon, Richard
%A Shapira, Ofer
%Y Li, Yunyao
%Y Lazaridou, Angeliki
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F zhong-etal-2022-improving-precancerous
%X The application of natural language processing (NLP) to cancer pathology reports has been focused on detecting cancer cases, largely ignoring precancerous cases. Improving the characterization of precancerous adenomas assists in developing diagnostic tests for early cancer detection and prevention, especially for colorectal cancer (CRC). Here we developed transformer-based deep neural network NLP models to perform the CRC phenotyping, with the goal of extracting precancerous lesion attributes and distinguishing cancer and precancerous cases. We achieved 0.914 macro-F1 scores for classifying patients into negative, non-advanced adenoma, advanced adenoma and CRC. We further improved the performance to 0.923 using an ensemble of classifiers for cancer status classification and lesion size named-entity recognition (NER). Our results demonstrated the potential of using NLP to leverage real-world health record data to facilitate the development of diagnostic tests for early cancer prevention.
%R 10.18653/v1/2022.emnlp-industry.38
%U https://aclanthology.org/2022.emnlp-industry.38
%U https://doi.org/10.18653/v1/2022.emnlp-industry.38
%P 379-389
Markdown (Informal)
[Improving Precancerous Case Characterization via Transformer-based Ensemble Learning](https://aclanthology.org/2022.emnlp-industry.38) (Zhong et al., EMNLP 2022)
ACL
- Yizhen Zhong, Jiajie Xiao, Thomas Vetterli, Mahan Matin, Ellen Loo, Jimmy Lin, Richard Bourgon, and Ofer Shapira. 2022. Improving Precancerous Case Characterization via Transformer-based Ensemble Learning. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 379–389, Abu Dhabi, UAE. Association for Computational Linguistics.