@inproceedings{shimizu-etal-2025-recordtwin,
title = "{R}ecord{T}win: Towards Creating Safe Synthetic Clinical Corpora",
author = "Shimizu, Seiji and
Baroud, Ibrahim and
Raithel, Lisa and
Yada, Shuntaro and
Wakamiya, Shoko and
Aramaki, Eiji",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.759/",
doi = "10.18653/v1/2025.findings-acl.759",
pages = "14714--14726",
ISBN = "979-8-89176-256-5",
abstract = "The scarcity of publicly available clinical corpora hinders developing and applying NLP tools in clinical research. While existing work tackles this issue by utilizing generative models to create high-quality synthetic corpora, their methods require learning from the original in-hospital clinical documents, turning them unfeasible in practice. To address this problem, we introduce RecordTwin, a novel synthetic corpus creation method designed to generate synthetic documents from anonymized clinical entities. In this method, we first extract and anonymize entities from in-hospital documents to ensure the information contained in the synthetic corpus is restricted. Then, we use a large language model to fill the context between anonymized entities. To do so, we use a small, privacy-preserving subset of the original documents to mimic their formatting and writing style. This approach only requires anonymized entities and a small subset of original documents in the generation process, making it more feasible in practice. To evaluate the synthetic corpus created with our method, we conduct a proof-of-concept study using a publicly available clinical database. Our results demonstrate that the synthetic corpus has a utility comparable to the original data and a safety advantage over baselines, highlighting the potential of RecordTwin for privacy-preserving synthetic corpus creation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shimizu-etal-2025-recordtwin">
<titleInfo>
<title>RecordTwin: Towards Creating Safe Synthetic Clinical Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seiji</namePart>
<namePart type="family">Shimizu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Baroud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Raithel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuntaro</namePart>
<namePart type="family">Yada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shoko</namePart>
<namePart type="family">Wakamiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiji</namePart>
<namePart type="family">Aramaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>The scarcity of publicly available clinical corpora hinders developing and applying NLP tools in clinical research. While existing work tackles this issue by utilizing generative models to create high-quality synthetic corpora, their methods require learning from the original in-hospital clinical documents, turning them unfeasible in practice. To address this problem, we introduce RecordTwin, a novel synthetic corpus creation method designed to generate synthetic documents from anonymized clinical entities. In this method, we first extract and anonymize entities from in-hospital documents to ensure the information contained in the synthetic corpus is restricted. Then, we use a large language model to fill the context between anonymized entities. To do so, we use a small, privacy-preserving subset of the original documents to mimic their formatting and writing style. This approach only requires anonymized entities and a small subset of original documents in the generation process, making it more feasible in practice. To evaluate the synthetic corpus created with our method, we conduct a proof-of-concept study using a publicly available clinical database. Our results demonstrate that the synthetic corpus has a utility comparable to the original data and a safety advantage over baselines, highlighting the potential of RecordTwin for privacy-preserving synthetic corpus creation.</abstract>
<identifier type="citekey">shimizu-etal-2025-recordtwin</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.759</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.759/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>14714</start>
<end>14726</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RecordTwin: Towards Creating Safe Synthetic Clinical Corpora
%A Shimizu, Seiji
%A Baroud, Ibrahim
%A Raithel, Lisa
%A Yada, Shuntaro
%A Wakamiya, Shoko
%A Aramaki, Eiji
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F shimizu-etal-2025-recordtwin
%X The scarcity of publicly available clinical corpora hinders developing and applying NLP tools in clinical research. While existing work tackles this issue by utilizing generative models to create high-quality synthetic corpora, their methods require learning from the original in-hospital clinical documents, turning them unfeasible in practice. To address this problem, we introduce RecordTwin, a novel synthetic corpus creation method designed to generate synthetic documents from anonymized clinical entities. In this method, we first extract and anonymize entities from in-hospital documents to ensure the information contained in the synthetic corpus is restricted. Then, we use a large language model to fill the context between anonymized entities. To do so, we use a small, privacy-preserving subset of the original documents to mimic their formatting and writing style. This approach only requires anonymized entities and a small subset of original documents in the generation process, making it more feasible in practice. To evaluate the synthetic corpus created with our method, we conduct a proof-of-concept study using a publicly available clinical database. Our results demonstrate that the synthetic corpus has a utility comparable to the original data and a safety advantage over baselines, highlighting the potential of RecordTwin for privacy-preserving synthetic corpus creation.
%R 10.18653/v1/2025.findings-acl.759
%U https://aclanthology.org/2025.findings-acl.759/
%U https://doi.org/10.18653/v1/2025.findings-acl.759
%P 14714-14726
Markdown (Informal)
[RecordTwin: Towards Creating Safe Synthetic Clinical Corpora](https://aclanthology.org/2025.findings-acl.759/) (Shimizu et al., Findings 2025)
ACL
- Seiji Shimizu, Ibrahim Baroud, Lisa Raithel, Shuntaro Yada, Shoko Wakamiya, and Eiji Aramaki. 2025. RecordTwin: Towards Creating Safe Synthetic Clinical Corpora. In Findings of the Association for Computational Linguistics: ACL 2025, pages 14714–14726, Vienna, Austria. Association for Computational Linguistics.