@inproceedings{grundmann-etal-2022-attention,
title = "Attention Networks for Augmenting Clinical Text with Support Sets for Diagnosis Prediction",
author = {Grundmann, Paul and
Oberhauser, Tom and
Gers, Felix and
L{\"o}ser, Alexander},
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.422",
pages = "4765--4775",
abstract = "Diagnosis prediction on admission notes is a core clinical task. However, these notes may incompletely describe the patient. Also, clinical language models may suffer from idiosyncratic language or imbalanced vocabulary for describing diseases or symptoms. We tackle the task of diagnosis prediction, which consists of predicting future patient diagnoses from clinical texts at the time of admission. We improve the performance on this task by introducing an additional signal from support sets of diagnostic codes from prior admissions or as they emerge during differential diagnosis. To enhance the robustness of diagnosis prediction methods, we propose to augment clinical text with potentially complementary set data from diagnosis codes from previous patient visits or from codes that emerge from the current admission as they become available through diagnostics. We discuss novel attention network architectures and augmentation strategies to solve this problem. Our experiments reveal that support sets improve the performance drastically to predict less common diagnosis codes. Our approach clearly outperforms the previous state-of-the-art PubMedBERT baseline by up 3{\%} points. Furthermore, we find that support sets drastically improve the performance for pregnancy- and gynecology-related diagnoses up to 32.9{\%} points compared to the baseline.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grundmann-etal-2022-attention">
<titleInfo>
<title>Attention Networks for Augmenting Clinical Text with Support Sets for Diagnosis Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Grundmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Oberhauser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Gers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Löser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Diagnosis prediction on admission notes is a core clinical task. However, these notes may incompletely describe the patient. Also, clinical language models may suffer from idiosyncratic language or imbalanced vocabulary for describing diseases or symptoms. We tackle the task of diagnosis prediction, which consists of predicting future patient diagnoses from clinical texts at the time of admission. We improve the performance on this task by introducing an additional signal from support sets of diagnostic codes from prior admissions or as they emerge during differential diagnosis. To enhance the robustness of diagnosis prediction methods, we propose to augment clinical text with potentially complementary set data from diagnosis codes from previous patient visits or from codes that emerge from the current admission as they become available through diagnostics. We discuss novel attention network architectures and augmentation strategies to solve this problem. Our experiments reveal that support sets improve the performance drastically to predict less common diagnosis codes. Our approach clearly outperforms the previous state-of-the-art PubMedBERT baseline by up 3% points. Furthermore, we find that support sets drastically improve the performance for pregnancy- and gynecology-related diagnoses up to 32.9% points compared to the baseline.</abstract>
<identifier type="citekey">grundmann-etal-2022-attention</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.422</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4765</start>
<end>4775</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Attention Networks for Augmenting Clinical Text with Support Sets for Diagnosis Prediction
%A Grundmann, Paul
%A Oberhauser, Tom
%A Gers, Felix
%A Löser, Alexander
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F grundmann-etal-2022-attention
%X Diagnosis prediction on admission notes is a core clinical task. However, these notes may incompletely describe the patient. Also, clinical language models may suffer from idiosyncratic language or imbalanced vocabulary for describing diseases or symptoms. We tackle the task of diagnosis prediction, which consists of predicting future patient diagnoses from clinical texts at the time of admission. We improve the performance on this task by introducing an additional signal from support sets of diagnostic codes from prior admissions or as they emerge during differential diagnosis. To enhance the robustness of diagnosis prediction methods, we propose to augment clinical text with potentially complementary set data from diagnosis codes from previous patient visits or from codes that emerge from the current admission as they become available through diagnostics. We discuss novel attention network architectures and augmentation strategies to solve this problem. Our experiments reveal that support sets improve the performance drastically to predict less common diagnosis codes. Our approach clearly outperforms the previous state-of-the-art PubMedBERT baseline by up 3% points. Furthermore, we find that support sets drastically improve the performance for pregnancy- and gynecology-related diagnoses up to 32.9% points compared to the baseline.
%U https://aclanthology.org/2022.coling-1.422
%P 4765-4775
Markdown (Informal)
[Attention Networks for Augmenting Clinical Text with Support Sets for Diagnosis Prediction](https://aclanthology.org/2022.coling-1.422) (Grundmann et al., COLING 2022)
ACL