@inproceedings{ji-marttinen-2023-patient,
title = "Patient Outcome and Zero-shot Diagnosis Prediction with Hypernetwork-guided Multitask Learning",
author = "Ji, Shaoxiong and
Marttinen, Pekka",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.43",
doi = "10.18653/v1/2023.eacl-main.43",
pages = "589--598",
abstract = "Multitask deep learning has been applied to patient outcome prediction from text, taking clinical notes as input and training deep neural networks with a joint loss function of multiple tasks. However, the joint training scheme of multitask learning suffers from inter-task interference, and diagnosis prediction among the multiple tasks has the generalizability issue due to rare diseases or unseen diagnoses. To solve these challenges, we propose a hypernetwork-based approach that generates task-conditioned parameters and coefficients of multitask prediction heads to learn task-specific prediction and balance the multitask learning. We also incorporate semantic task information to improve the generalizability of our task-conditioned multitask model. Experiments on early and discharge notes extracted from the real-world MIMIC database show our method can achieve better performance on multitask patient outcome prediction than strong baselines in most cases. Besides, our method can effectively handle the scenario with limited information and improve zero-shot prediction on unseen diagnosis categories.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ji-marttinen-2023-patient">
<titleInfo>
<title>Patient Outcome and Zero-shot Diagnosis Prediction with Hypernetwork-guided Multitask Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shaoxiong</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pekka</namePart>
<namePart type="family">Marttinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multitask deep learning has been applied to patient outcome prediction from text, taking clinical notes as input and training deep neural networks with a joint loss function of multiple tasks. However, the joint training scheme of multitask learning suffers from inter-task interference, and diagnosis prediction among the multiple tasks has the generalizability issue due to rare diseases or unseen diagnoses. To solve these challenges, we propose a hypernetwork-based approach that generates task-conditioned parameters and coefficients of multitask prediction heads to learn task-specific prediction and balance the multitask learning. We also incorporate semantic task information to improve the generalizability of our task-conditioned multitask model. Experiments on early and discharge notes extracted from the real-world MIMIC database show our method can achieve better performance on multitask patient outcome prediction than strong baselines in most cases. Besides, our method can effectively handle the scenario with limited information and improve zero-shot prediction on unseen diagnosis categories.</abstract>
<identifier type="citekey">ji-marttinen-2023-patient</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.43</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.43</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>589</start>
<end>598</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Patient Outcome and Zero-shot Diagnosis Prediction with Hypernetwork-guided Multitask Learning
%A Ji, Shaoxiong
%A Marttinen, Pekka
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F ji-marttinen-2023-patient
%X Multitask deep learning has been applied to patient outcome prediction from text, taking clinical notes as input and training deep neural networks with a joint loss function of multiple tasks. However, the joint training scheme of multitask learning suffers from inter-task interference, and diagnosis prediction among the multiple tasks has the generalizability issue due to rare diseases or unseen diagnoses. To solve these challenges, we propose a hypernetwork-based approach that generates task-conditioned parameters and coefficients of multitask prediction heads to learn task-specific prediction and balance the multitask learning. We also incorporate semantic task information to improve the generalizability of our task-conditioned multitask model. Experiments on early and discharge notes extracted from the real-world MIMIC database show our method can achieve better performance on multitask patient outcome prediction than strong baselines in most cases. Besides, our method can effectively handle the scenario with limited information and improve zero-shot prediction on unseen diagnosis categories.
%R 10.18653/v1/2023.eacl-main.43
%U https://aclanthology.org/2023.eacl-main.43
%U https://doi.org/10.18653/v1/2023.eacl-main.43
%P 589-598
Markdown (Informal)
[Patient Outcome and Zero-shot Diagnosis Prediction with Hypernetwork-guided Multitask Learning](https://aclanthology.org/2023.eacl-main.43) (Ji & Marttinen, EACL 2023)
ACL