@inproceedings{blankemeier-etal-2023-efficient,
title = "Efficient Diagnosis Assignment Using Unstructured Clinical Notes",
author = "Blankemeier, Louis and
Fries, Jason and
Tinn, Robert and
Preston, Joseph and
Shah, Nigam and
Chaudhari, Akshay",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-short.42",
doi = "10.18653/v1/2023.acl-short.42",
pages = "485--494",
abstract = "Electronic phenotyping entails using electronic health records (EHRs) to identify patients with specific health outcomes and determine when those outcomes occurred. Unstructured clinical notes, which contain a vast amount of information, are a valuable resource for electronic phenotyping. However, traditional methods, such as rule-based labeling functions or neural networks, require significant manual effort to tune and may not generalize well to multiple indications. To address these challenges, we propose \textit{HyDE} (hybrid diagnosis extractor). HyDE is a simple framework for electronic phenotyping that integrates labeling functions and a disease-agnostic neural network to assign diagnoses to patients. By training HyDE{'}s model to correct predictions made by labeling functions, we are able to disambiguate hypertension true positives and false positives with a supervised area under the precision-recall curve (AUPRC) of 0.85. We extend this hypertension-trained model to zero-shot evaluation of four other diseases, generating AUPRC values ranging from 0.82 - 0.95 and outperforming a labeling function baseline by 44 points in F1 score and a Word2Vec baseline by 24 points in F1 score on average. Furthermore, we demonstrate a speedup of {\textgreater}4x by pruning the length of inputs into our language model to {\textasciitilde}2.3{\%} of the full clinical notes, with negligible impact to the AUPRC. HyDE has the potential to improve the efficiency and efficacy of interpreting large-scale unstructured clinical notes for accurate EHR phenotyping.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="blankemeier-etal-2023-efficient">
<titleInfo>
<title>Efficient Diagnosis Assignment Using Unstructured Clinical Notes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Louis</namePart>
<namePart type="family">Blankemeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Fries</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Tinn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Preston</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nigam</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akshay</namePart>
<namePart type="family">Chaudhari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Electronic phenotyping entails using electronic health records (EHRs) to identify patients with specific health outcomes and determine when those outcomes occurred. Unstructured clinical notes, which contain a vast amount of information, are a valuable resource for electronic phenotyping. However, traditional methods, such as rule-based labeling functions or neural networks, require significant manual effort to tune and may not generalize well to multiple indications. To address these challenges, we propose HyDE (hybrid diagnosis extractor). HyDE is a simple framework for electronic phenotyping that integrates labeling functions and a disease-agnostic neural network to assign diagnoses to patients. By training HyDE’s model to correct predictions made by labeling functions, we are able to disambiguate hypertension true positives and false positives with a supervised area under the precision-recall curve (AUPRC) of 0.85. We extend this hypertension-trained model to zero-shot evaluation of four other diseases, generating AUPRC values ranging from 0.82 - 0.95 and outperforming a labeling function baseline by 44 points in F1 score and a Word2Vec baseline by 24 points in F1 score on average. Furthermore, we demonstrate a speedup of \textgreater4x by pruning the length of inputs into our language model to ~2.3% of the full clinical notes, with negligible impact to the AUPRC. HyDE has the potential to improve the efficiency and efficacy of interpreting large-scale unstructured clinical notes for accurate EHR phenotyping.</abstract>
<identifier type="citekey">blankemeier-etal-2023-efficient</identifier>
<identifier type="doi">10.18653/v1/2023.acl-short.42</identifier>
<location>
<url>https://aclanthology.org/2023.acl-short.42</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>485</start>
<end>494</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Diagnosis Assignment Using Unstructured Clinical Notes
%A Blankemeier, Louis
%A Fries, Jason
%A Tinn, Robert
%A Preston, Joseph
%A Shah, Nigam
%A Chaudhari, Akshay
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F blankemeier-etal-2023-efficient
%X Electronic phenotyping entails using electronic health records (EHRs) to identify patients with specific health outcomes and determine when those outcomes occurred. Unstructured clinical notes, which contain a vast amount of information, are a valuable resource for electronic phenotyping. However, traditional methods, such as rule-based labeling functions or neural networks, require significant manual effort to tune and may not generalize well to multiple indications. To address these challenges, we propose HyDE (hybrid diagnosis extractor). HyDE is a simple framework for electronic phenotyping that integrates labeling functions and a disease-agnostic neural network to assign diagnoses to patients. By training HyDE’s model to correct predictions made by labeling functions, we are able to disambiguate hypertension true positives and false positives with a supervised area under the precision-recall curve (AUPRC) of 0.85. We extend this hypertension-trained model to zero-shot evaluation of four other diseases, generating AUPRC values ranging from 0.82 - 0.95 and outperforming a labeling function baseline by 44 points in F1 score and a Word2Vec baseline by 24 points in F1 score on average. Furthermore, we demonstrate a speedup of \textgreater4x by pruning the length of inputs into our language model to ~2.3% of the full clinical notes, with negligible impact to the AUPRC. HyDE has the potential to improve the efficiency and efficacy of interpreting large-scale unstructured clinical notes for accurate EHR phenotyping.
%R 10.18653/v1/2023.acl-short.42
%U https://aclanthology.org/2023.acl-short.42
%U https://doi.org/10.18653/v1/2023.acl-short.42
%P 485-494
Markdown (Informal)
[Efficient Diagnosis Assignment Using Unstructured Clinical Notes](https://aclanthology.org/2023.acl-short.42) (Blankemeier et al., ACL 2023)
ACL
- Louis Blankemeier, Jason Fries, Robert Tinn, Joseph Preston, Nigam Shah, and Akshay Chaudhari. 2023. Efficient Diagnosis Assignment Using Unstructured Clinical Notes. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 485–494, Toronto, Canada. Association for Computational Linguistics.