@inproceedings{stockl-etal-2026-compressed,
title = "Compressed Representations of Patient Records: A Comparative Study of Template-Based and {LLM}-Based Methods for Clinical Data Summarization and Visualization",
author = {St{\"o}ckl, Andreas and
Krauss, Oliver and
Bauernfeind, Sophie},
editor = "Gupta, Deepak and
Thompson, Paul and
Ananiadou, Sophia and
Demner-Fushman, Dina",
booktitle = "Proceedings of the Third Workshop on Patient-Oriented Language Processing ({CL}4{H}ealth) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.cl4health-1.9/",
doi = "10.63317/4ph9cddo4vbn",
pages = "96--106",
abstract = "Electronic Health Records (EHRs) contain comprehensive patient information that is often voluminous and challenging to review efficiently. This paper presents a systematic evaluation of multiple methods for compressing patient records into standardized, comparable formats. Four compression approaches are implemented and compared: two template-based methods (structured extraction, extractive key-phrase) and two LLM-based methods (LLM, and hybrid LLM with 8 different models). Using a synthetic cohort of 75 patient records generated with realistic clinical patterns, each method is evaluated on information preservation (diagnosis, medication, allergy, lab value recall, and vital accuracy), compression efficiency, and output quality. Across methods, diagnosis recall ranged from 0.637 to 1.000, with medication and allergy recall consistently exceeding 0.880. In the test setup, the template-based approach yielded the highest compression ratio (7.6{\texttimes}), while the hybrid methods provided the most balanced trade-off between compression and clinical utility. These results suggest that combining structured extraction with LLM-generated summaries can be an effective strategy for scenarios requiring both compact representations and contextual clinical information."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stockl-etal-2026-compressed">
<titleInfo>
<title>Compressed Representations of Patient Records: A Comparative Study of Template-Based and LLM-Based Methods for Clinical Data Summarization and Visualization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Stöckl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Krauss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Bauernfeind</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Electronic Health Records (EHRs) contain comprehensive patient information that is often voluminous and challenging to review efficiently. This paper presents a systematic evaluation of multiple methods for compressing patient records into standardized, comparable formats. Four compression approaches are implemented and compared: two template-based methods (structured extraction, extractive key-phrase) and two LLM-based methods (LLM, and hybrid LLM with 8 different models). Using a synthetic cohort of 75 patient records generated with realistic clinical patterns, each method is evaluated on information preservation (diagnosis, medication, allergy, lab value recall, and vital accuracy), compression efficiency, and output quality. Across methods, diagnosis recall ranged from 0.637 to 1.000, with medication and allergy recall consistently exceeding 0.880. In the test setup, the template-based approach yielded the highest compression ratio (7.6×), while the hybrid methods provided the most balanced trade-off between compression and clinical utility. These results suggest that combining structured extraction with LLM-generated summaries can be an effective strategy for scenarios requiring both compact representations and contextual clinical information.</abstract>
<identifier type="citekey">stockl-etal-2026-compressed</identifier>
<identifier type="doi">10.63317/4ph9cddo4vbn</identifier>
<location>
<url>https://aclanthology.org/2026.cl4health-1.9/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>96</start>
<end>106</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Compressed Representations of Patient Records: A Comparative Study of Template-Based and LLM-Based Methods for Clinical Data Summarization and Visualization
%A Stöckl, Andreas
%A Krauss, Oliver
%A Bauernfeind, Sophie
%Y Gupta, Deepak
%Y Thompson, Paul
%Y Ananiadou, Sophia
%Y Demner-Fushman, Dina
%S Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F stockl-etal-2026-compressed
%X Electronic Health Records (EHRs) contain comprehensive patient information that is often voluminous and challenging to review efficiently. This paper presents a systematic evaluation of multiple methods for compressing patient records into standardized, comparable formats. Four compression approaches are implemented and compared: two template-based methods (structured extraction, extractive key-phrase) and two LLM-based methods (LLM, and hybrid LLM with 8 different models). Using a synthetic cohort of 75 patient records generated with realistic clinical patterns, each method is evaluated on information preservation (diagnosis, medication, allergy, lab value recall, and vital accuracy), compression efficiency, and output quality. Across methods, diagnosis recall ranged from 0.637 to 1.000, with medication and allergy recall consistently exceeding 0.880. In the test setup, the template-based approach yielded the highest compression ratio (7.6×), while the hybrid methods provided the most balanced trade-off between compression and clinical utility. These results suggest that combining structured extraction with LLM-generated summaries can be an effective strategy for scenarios requiring both compact representations and contextual clinical information.
%R 10.63317/4ph9cddo4vbn
%U https://aclanthology.org/2026.cl4health-1.9/
%U https://doi.org/10.63317/4ph9cddo4vbn
%P 96-106
Markdown (Informal)
[Compressed Representations of Patient Records: A Comparative Study of Template-Based and LLM-Based Methods for Clinical Data Summarization and Visualization](https://aclanthology.org/2026.cl4health-1.9/) (Stöckl et al., CL4Health 2026)
ACL