@inproceedings{nguyen-etal-2024-carer,
title = "{CARER} - {C}linic{A}l Reasoning-Enhanced Representation for Temporal Health Risk Prediction",
author = "Nguyen, Tuan Dung and
Huynh, Thanh Trung and
Phan, Minh Hieu and
Nguyen, Quoc Viet Hung and
Nguyen, Phi Le",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.580/",
doi = "10.18653/v1/2024.emnlp-main.580",
pages = "10392--10407",
abstract = "The increasing availability of multimodal data from electronic health records (EHR) has paved the way for deep learning methods to improve diagnosis accuracy. However, deep learning models are data-driven, requiring large-scale datasets to achieve high generalizability. Inspired by how human experts leverage reasoning for medical diagnosis, we propose CARER, a novel health risk prediction framework, that enhances deep learning models with clinical rationales derived from medically proficient Large Language Models (LLMs). In addition, we provide a cross-view alignment loss which aligns the {\textquotedblleft}local{\textquotedblright} view from the patient`s health status with the {\textquotedblleft}global{\textquotedblright} view from the external LLM`s clinical reasoning to boost the mutual feature learning. Through extensive experiments on two predictive tasks using two popular EHR datasets, our CARER`s significantly exceeds the performance of state-of-the-art models by up to 11.2{\%}, especially in improving data efficiency and generalizability. Our code is available at https://github.com/tuandung2812/CARER-EMNLP-2024"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2024-carer">
<titleInfo>
<title>CARER - ClinicAl Reasoning-Enhanced Representation for Temporal Health Risk Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tuan</namePart>
<namePart type="given">Dung</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thanh</namePart>
<namePart type="given">Trung</namePart>
<namePart type="family">Huynh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minh</namePart>
<namePart type="given">Hieu</namePart>
<namePart type="family">Phan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quoc</namePart>
<namePart type="given">Viet</namePart>
<namePart type="given">Hung</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phi</namePart>
<namePart type="given">Le</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The increasing availability of multimodal data from electronic health records (EHR) has paved the way for deep learning methods to improve diagnosis accuracy. However, deep learning models are data-driven, requiring large-scale datasets to achieve high generalizability. Inspired by how human experts leverage reasoning for medical diagnosis, we propose CARER, a novel health risk prediction framework, that enhances deep learning models with clinical rationales derived from medically proficient Large Language Models (LLMs). In addition, we provide a cross-view alignment loss which aligns the “local” view from the patient‘s health status with the “global” view from the external LLM‘s clinical reasoning to boost the mutual feature learning. Through extensive experiments on two predictive tasks using two popular EHR datasets, our CARER‘s significantly exceeds the performance of state-of-the-art models by up to 11.2%, especially in improving data efficiency and generalizability. Our code is available at https://github.com/tuandung2812/CARER-EMNLP-2024</abstract>
<identifier type="citekey">nguyen-etal-2024-carer</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.580</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.580/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>10392</start>
<end>10407</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CARER - ClinicAl Reasoning-Enhanced Representation for Temporal Health Risk Prediction
%A Nguyen, Tuan Dung
%A Huynh, Thanh Trung
%A Phan, Minh Hieu
%A Nguyen, Quoc Viet Hung
%A Nguyen, Phi Le
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F nguyen-etal-2024-carer
%X The increasing availability of multimodal data from electronic health records (EHR) has paved the way for deep learning methods to improve diagnosis accuracy. However, deep learning models are data-driven, requiring large-scale datasets to achieve high generalizability. Inspired by how human experts leverage reasoning for medical diagnosis, we propose CARER, a novel health risk prediction framework, that enhances deep learning models with clinical rationales derived from medically proficient Large Language Models (LLMs). In addition, we provide a cross-view alignment loss which aligns the “local” view from the patient‘s health status with the “global” view from the external LLM‘s clinical reasoning to boost the mutual feature learning. Through extensive experiments on two predictive tasks using two popular EHR datasets, our CARER‘s significantly exceeds the performance of state-of-the-art models by up to 11.2%, especially in improving data efficiency and generalizability. Our code is available at https://github.com/tuandung2812/CARER-EMNLP-2024
%R 10.18653/v1/2024.emnlp-main.580
%U https://aclanthology.org/2024.emnlp-main.580/
%U https://doi.org/10.18653/v1/2024.emnlp-main.580
%P 10392-10407
Markdown (Informal)
[CARER - ClinicAl Reasoning-Enhanced Representation for Temporal Health Risk Prediction](https://aclanthology.org/2024.emnlp-main.580/) (Nguyen et al., EMNLP 2024)
ACL