@inproceedings{deepak-etal-2026-ltrc,
title = "{LTRC}-Medicom at {MEDIQA}-{SYNUR} 2026: Schema-Guided Clinical Information Extraction with Hybrid Clustering-{SFT}-Verification",
author = "Deepak, Pasumarthy and
Marimuthu, Sushvin and
Krishnamurthy, Parameswari",
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-1.25/",
doi = "10.63317/4oou5ss2efr6",
pages = "228--234",
abstract = "Extracting structured clinical data from unstructured patient transcripts is challenging due to large target schemas and inherent linguistic ambiguity. We address the extraction of 193 heterogeneous clinical attributes from nursing notes and clinician{--}patient dialogues, and demonstrate that zero-shot large language models (LLMs) are ineffective in this setting, achieving an F1 score below 0.15 due to context window saturation and hallucination. We propose a four-stage framework that combines semantic schema clustering, role-based chain-of-thought prompting, supervised fine-tuning of Llama-3.1-8B, and transcript-verified post-processing. Our approach achieves an F1 score of 0.66, representing a 4.4x improvement over the baseline, by balancing high recall from generative models with high precision from verification. These results highlight the effectiveness of hybrid pipelines for high-stakes clinical information extraction."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deepak-etal-2026-ltrc">
<titleInfo>
<title>LTRC-Medicom at MEDIQA-SYNUR 2026: Schema-Guided Clinical Information Extraction with Hybrid Clustering-SFT-Verification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pasumarthy</namePart>
<namePart type="family">Deepak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sushvin</namePart>
<namePart type="family">Marimuthu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</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>Extracting structured clinical data from unstructured patient transcripts is challenging due to large target schemas and inherent linguistic ambiguity. We address the extraction of 193 heterogeneous clinical attributes from nursing notes and clinician–patient dialogues, and demonstrate that zero-shot large language models (LLMs) are ineffective in this setting, achieving an F1 score below 0.15 due to context window saturation and hallucination. We propose a four-stage framework that combines semantic schema clustering, role-based chain-of-thought prompting, supervised fine-tuning of Llama-3.1-8B, and transcript-verified post-processing. Our approach achieves an F1 score of 0.66, representing a 4.4x improvement over the baseline, by balancing high recall from generative models with high precision from verification. These results highlight the effectiveness of hybrid pipelines for high-stakes clinical information extraction.</abstract>
<identifier type="citekey">deepak-etal-2026-ltrc</identifier>
<identifier type="doi">10.63317/4oou5ss2efr6</identifier>
<location>
<url>https://aclanthology.org/2026.clinicalnlp-1.25/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>228</start>
<end>234</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LTRC-Medicom at MEDIQA-SYNUR 2026: Schema-Guided Clinical Information Extraction with Hybrid Clustering-SFT-Verification
%A Deepak, Pasumarthy
%A Marimuthu, Sushvin
%A Krishnamurthy, Parameswari
%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 deepak-etal-2026-ltrc
%X Extracting structured clinical data from unstructured patient transcripts is challenging due to large target schemas and inherent linguistic ambiguity. We address the extraction of 193 heterogeneous clinical attributes from nursing notes and clinician–patient dialogues, and demonstrate that zero-shot large language models (LLMs) are ineffective in this setting, achieving an F1 score below 0.15 due to context window saturation and hallucination. We propose a four-stage framework that combines semantic schema clustering, role-based chain-of-thought prompting, supervised fine-tuning of Llama-3.1-8B, and transcript-verified post-processing. Our approach achieves an F1 score of 0.66, representing a 4.4x improvement over the baseline, by balancing high recall from generative models with high precision from verification. These results highlight the effectiveness of hybrid pipelines for high-stakes clinical information extraction.
%R 10.63317/4oou5ss2efr6
%U https://aclanthology.org/2026.clinicalnlp-1.25/
%U https://doi.org/10.63317/4oou5ss2efr6
%P 228-234
Markdown (Informal)
[LTRC-Medicom at MEDIQA-SYNUR 2026: Schema-Guided Clinical Information Extraction with Hybrid Clustering-SFT-Verification](https://aclanthology.org/2026.clinicalnlp-1.25/) (Deepak et al., ClinicalNLP 2026)
ACL