@inproceedings{jeeballah-etal-2026-squcs,
title = "{SQUCS} at {MEDIQA}-{SYNUR} 2026: A Multi-Agent Open Source {LLM} System for Nursing Observation Extraction",
author = "JeebAllah, Riham and
AlZaabi, Adhari and
AAlAbdulsalam, Abdulrahman Khalifa",
editor = "Ben Abacha, Asma and
Bethard, Steven and
Bitterman, Danielle and
Naumann, Tristan and
Roberts, Kirk",
booktitle = "Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical {NLP}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.clinicalnlp-1.14/",
doi = "10.63317/3cuv6m9wb5pm",
pages = "125--135",
abstract = "Clinical nursing documentation contains detailed observational information that is essential for patient monitoring and clinical decision-making, yet this information is predominantly recorded in free-text form. The MEDIQA-SYNUR shared task addresses this challenge by requiring systems to extract structured nursing observations from clinical transcripts under strict constraints on evidence grounding and value normalization. In this work, we present a multi-agent large language model (LLM){--}based system for the MEDIQA-SYNUR task. We utilize the Llama3 open source LLM for this purpose for ease of local deployment within hospital digital infrastructure. Our system decomposes the extraction process into specialized agents responsible for schema-guided extraction, rule-based validation, and precision-oriented filtering. Starting from a baseline multi-agent pipeline, we conduct a systematic error analysis over the entire development set, examining all false positive and false negative predictions. Our final configuration, selected after extensive exploration and error analysis, combined transcript segmentation, the precision agent, and a suppression table derived from development-set analysis. On the development set, this setup achieved an F1 score of 0.6930 (precision = 0.6427, recall = 0.7518). Applying the same configuration directly to the test set, without any additional tuning, yielded an F1 score of 0.5923 (precision = 0.5292, recall = 0.6725). These results represent the most effective balance of precision and recall achieved through our iterative refinements and reflect the final state of the system as submitted for the competition"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jeeballah-etal-2026-squcs">
<titleInfo>
<title>SQUCS at MEDIQA-SYNUR 2026: A Multi-Agent Open Source LLM System for Nursing Observation Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Riham</namePart>
<namePart type="family">JeebAllah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adhari</namePart>
<namePart type="family">AlZaabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulrahman</namePart>
<namePart type="given">Khalifa</namePart>
<namePart type="family">AAlAbdulsalam</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 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</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>Clinical nursing documentation contains detailed observational information that is essential for patient monitoring and clinical decision-making, yet this information is predominantly recorded in free-text form. The MEDIQA-SYNUR shared task addresses this challenge by requiring systems to extract structured nursing observations from clinical transcripts under strict constraints on evidence grounding and value normalization. In this work, we present a multi-agent large language model (LLM)–based system for the MEDIQA-SYNUR task. We utilize the Llama3 open source LLM for this purpose for ease of local deployment within hospital digital infrastructure. Our system decomposes the extraction process into specialized agents responsible for schema-guided extraction, rule-based validation, and precision-oriented filtering. Starting from a baseline multi-agent pipeline, we conduct a systematic error analysis over the entire development set, examining all false positive and false negative predictions. Our final configuration, selected after extensive exploration and error analysis, combined transcript segmentation, the precision agent, and a suppression table derived from development-set analysis. On the development set, this setup achieved an F1 score of 0.6930 (precision = 0.6427, recall = 0.7518). Applying the same configuration directly to the test set, without any additional tuning, yielded an F1 score of 0.5923 (precision = 0.5292, recall = 0.6725). These results represent the most effective balance of precision and recall achieved through our iterative refinements and reflect the final state of the system as submitted for the competition</abstract>
<identifier type="citekey">jeeballah-etal-2026-squcs</identifier>
<identifier type="doi">10.63317/3cuv6m9wb5pm</identifier>
<location>
<url>https://aclanthology.org/2026.clinicalnlp-1.14/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>125</start>
<end>135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SQUCS at MEDIQA-SYNUR 2026: A Multi-Agent Open Source LLM System for Nursing Observation Extraction
%A JeebAllah, Riham
%A AlZaabi, Adhari
%A AAlAbdulsalam, Abdulrahman Khalifa
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Bitterman, Danielle
%Y Naumann, Tristan
%Y Roberts, Kirk
%S Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F jeeballah-etal-2026-squcs
%X Clinical nursing documentation contains detailed observational information that is essential for patient monitoring and clinical decision-making, yet this information is predominantly recorded in free-text form. The MEDIQA-SYNUR shared task addresses this challenge by requiring systems to extract structured nursing observations from clinical transcripts under strict constraints on evidence grounding and value normalization. In this work, we present a multi-agent large language model (LLM)–based system for the MEDIQA-SYNUR task. We utilize the Llama3 open source LLM for this purpose for ease of local deployment within hospital digital infrastructure. Our system decomposes the extraction process into specialized agents responsible for schema-guided extraction, rule-based validation, and precision-oriented filtering. Starting from a baseline multi-agent pipeline, we conduct a systematic error analysis over the entire development set, examining all false positive and false negative predictions. Our final configuration, selected after extensive exploration and error analysis, combined transcript segmentation, the precision agent, and a suppression table derived from development-set analysis. On the development set, this setup achieved an F1 score of 0.6930 (precision = 0.6427, recall = 0.7518). Applying the same configuration directly to the test set, without any additional tuning, yielded an F1 score of 0.5923 (precision = 0.5292, recall = 0.6725). These results represent the most effective balance of precision and recall achieved through our iterative refinements and reflect the final state of the system as submitted for the competition
%R 10.63317/3cuv6m9wb5pm
%U https://aclanthology.org/2026.clinicalnlp-1.14/
%U https://doi.org/10.63317/3cuv6m9wb5pm
%P 125-135
Markdown (Informal)
[SQUCS at MEDIQA-SYNUR 2026: A Multi-Agent Open Source LLM System for Nursing Observation Extraction](https://aclanthology.org/2026.clinicalnlp-1.14/) (JeebAllah et al., ClinicalNLP 2026)
ACL