@inproceedings{liu-etal-2026-cru,
title = "{CRU}-Reason: Knowledge Graph-Grounded and Interpretable Clinical Prediction with Clinical Rationale Units",
author = "Liu, Zihang and
Luo, Linhao and
Qiu, Zhangchi and
Chen, Shigeng and
Wang, Haishuai",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.26/",
pages = "568--584",
ISBN = "979-8-89176-459-0",
abstract = "Healthcare prediction using electronic health records (EHRs) is a cornerstone of modern clinical decision support. Conventional machine learning (ML) models achieve strong predictive performance but rarely provide knowledge-grounded, human-readable explanations. Large language models (LLMs) incorporated with medical knowledge graphs (KGs) offer advanced reasoning and explainability with encoded clinical facts, yet existing approaches typically perform monolithic reasoning over entire patient records, mixing task-irrelevant context and obscuring disease-specific attribution. To bridge these gaps, we propose CRU-Reason, a novel framework that integrates ML models, medical KGs, and LLMs through Clinical Rationale Units (CRUs) for knowledge-grounded and interpretable healthcare prediction. CRU is a localized structure that explicitly captures clinically meaningful communities among EHR concepts, thereby enabling LLMs to perform disease-centered, fine-grained reasoning. Experiments on two public clinical datasets demonstrate that CRU-Reason improves over the strongest evaluated EHR-prediction baselines by an average of +9.4{\%} across drug recommendation and diagnosis prediction, while exhibiting improved rationale quality and cross-dataset robustness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-cru">
<titleInfo>
<title>CRU-Reason: Knowledge Graph-Grounded and Interpretable Clinical Prediction with Clinical Rationale Units</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zihang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linhao</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhangchi</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shigeng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haishuai</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Healthcare prediction using electronic health records (EHRs) is a cornerstone of modern clinical decision support. Conventional machine learning (ML) models achieve strong predictive performance but rarely provide knowledge-grounded, human-readable explanations. Large language models (LLMs) incorporated with medical knowledge graphs (KGs) offer advanced reasoning and explainability with encoded clinical facts, yet existing approaches typically perform monolithic reasoning over entire patient records, mixing task-irrelevant context and obscuring disease-specific attribution. To bridge these gaps, we propose CRU-Reason, a novel framework that integrates ML models, medical KGs, and LLMs through Clinical Rationale Units (CRUs) for knowledge-grounded and interpretable healthcare prediction. CRU is a localized structure that explicitly captures clinically meaningful communities among EHR concepts, thereby enabling LLMs to perform disease-centered, fine-grained reasoning. Experiments on two public clinical datasets demonstrate that CRU-Reason improves over the strongest evaluated EHR-prediction baselines by an average of +9.4% across drug recommendation and diagnosis prediction, while exhibiting improved rationale quality and cross-dataset robustness.</abstract>
<identifier type="citekey">liu-etal-2026-cru</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.26/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>568</start>
<end>584</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CRU-Reason: Knowledge Graph-Grounded and Interpretable Clinical Prediction with Clinical Rationale Units
%A Liu, Zihang
%A Luo, Linhao
%A Qiu, Zhangchi
%A Chen, Shigeng
%A Wang, Haishuai
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F liu-etal-2026-cru
%X Healthcare prediction using electronic health records (EHRs) is a cornerstone of modern clinical decision support. Conventional machine learning (ML) models achieve strong predictive performance but rarely provide knowledge-grounded, human-readable explanations. Large language models (LLMs) incorporated with medical knowledge graphs (KGs) offer advanced reasoning and explainability with encoded clinical facts, yet existing approaches typically perform monolithic reasoning over entire patient records, mixing task-irrelevant context and obscuring disease-specific attribution. To bridge these gaps, we propose CRU-Reason, a novel framework that integrates ML models, medical KGs, and LLMs through Clinical Rationale Units (CRUs) for knowledge-grounded and interpretable healthcare prediction. CRU is a localized structure that explicitly captures clinically meaningful communities among EHR concepts, thereby enabling LLMs to perform disease-centered, fine-grained reasoning. Experiments on two public clinical datasets demonstrate that CRU-Reason improves over the strongest evaluated EHR-prediction baselines by an average of +9.4% across drug recommendation and diagnosis prediction, while exhibiting improved rationale quality and cross-dataset robustness.
%U https://aclanthology.org/2026.emnlp-main.26/
%P 568-584
Markdown (Informal)
[CRU-Reason: Knowledge Graph-Grounded and Interpretable Clinical Prediction with Clinical Rationale Units](https://aclanthology.org/2026.emnlp-main.26/) (Liu et al., EMNLP 2026)
ACL