@inproceedings{bahrololloomi-etal-2025-transformer,
title = "Transformer-Based Medical Statement Classification in Doctor-Patient Dialogues",
author = "Bahrololloomi, Farnod and
Luderschmidt, Johannes and
Fu, Biying",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Miwa, Makoto and
Tsujii, Junichi",
booktitle = "Proceedings of the 24th Workshop on Biomedical Language Processing",
month = aug,
year = "2025",
address = "Viena, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.bionlp-1.7/",
doi = "10.18653/v1/2025.bionlp-1.7",
pages = "63--73",
ISBN = "979-8-89176-275-6",
abstract = "The classification of medical statements in German doctor-patient interactions presents significant challenges for automated medical information extraction, particularly due to complex domain-specific terminology and the limited availability of specialized training data. To address this, we introduce a manually annotated dataset specifically designed for distinguishing medical from non-medical statements. This dataset incorporates the nuances of German medical terminology and provides a valuable foundation for further research in this domain. We systematically evaluate Transformer-based models and multimodal embedding techniques, comparing them against traditional embedding-based machine learning (ML) approaches and domain-specific models such as medBERT.de. Our empirical results show that Transformer-based architectures, such as the Sentence-BERT model combined with a support vector machine (SVM), achieve the highest accuracy of 79.58{\%} and a weighted F1-Score of 78.81{\%}, demonstrating an average performance improvement of up to 10{\%} over domain-specific counterparts. Additionally, we highlight the potential of lightweight ML-models for resource-efficient deployment on mobile devices, enabling real-time medical information processing in practical settings. These findings emphasize the importance of embedding selection for optimizing classification performance in the medical domain and establish a robust foundation for the development of advanced, domain-adapted German language models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bahrololloomi-etal-2025-transformer">
<titleInfo>
<title>Transformer-Based Medical Statement Classification in Doctor-Patient Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Farnod</namePart>
<namePart type="family">Bahrololloomi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Luderschmidt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biying</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Workshop on Biomedical Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</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">Makoto</namePart>
<namePart type="family">Miwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Viena, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-275-6</identifier>
</relatedItem>
<abstract>The classification of medical statements in German doctor-patient interactions presents significant challenges for automated medical information extraction, particularly due to complex domain-specific terminology and the limited availability of specialized training data. To address this, we introduce a manually annotated dataset specifically designed for distinguishing medical from non-medical statements. This dataset incorporates the nuances of German medical terminology and provides a valuable foundation for further research in this domain. We systematically evaluate Transformer-based models and multimodal embedding techniques, comparing them against traditional embedding-based machine learning (ML) approaches and domain-specific models such as medBERT.de. Our empirical results show that Transformer-based architectures, such as the Sentence-BERT model combined with a support vector machine (SVM), achieve the highest accuracy of 79.58% and a weighted F1-Score of 78.81%, demonstrating an average performance improvement of up to 10% over domain-specific counterparts. Additionally, we highlight the potential of lightweight ML-models for resource-efficient deployment on mobile devices, enabling real-time medical information processing in practical settings. These findings emphasize the importance of embedding selection for optimizing classification performance in the medical domain and establish a robust foundation for the development of advanced, domain-adapted German language models.</abstract>
<identifier type="citekey">bahrololloomi-etal-2025-transformer</identifier>
<identifier type="doi">10.18653/v1/2025.bionlp-1.7</identifier>
<location>
<url>https://aclanthology.org/2025.bionlp-1.7/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>63</start>
<end>73</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Transformer-Based Medical Statement Classification in Doctor-Patient Dialogues
%A Bahrololloomi, Farnod
%A Luderschmidt, Johannes
%A Fu, Biying
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Miwa, Makoto
%Y Tsujii, Junichi
%S Proceedings of the 24th Workshop on Biomedical Language Processing
%D 2025
%8 August
%I Association for Computational Linguistics
%C Viena, Austria
%@ 979-8-89176-275-6
%F bahrololloomi-etal-2025-transformer
%X The classification of medical statements in German doctor-patient interactions presents significant challenges for automated medical information extraction, particularly due to complex domain-specific terminology and the limited availability of specialized training data. To address this, we introduce a manually annotated dataset specifically designed for distinguishing medical from non-medical statements. This dataset incorporates the nuances of German medical terminology and provides a valuable foundation for further research in this domain. We systematically evaluate Transformer-based models and multimodal embedding techniques, comparing them against traditional embedding-based machine learning (ML) approaches and domain-specific models such as medBERT.de. Our empirical results show that Transformer-based architectures, such as the Sentence-BERT model combined with a support vector machine (SVM), achieve the highest accuracy of 79.58% and a weighted F1-Score of 78.81%, demonstrating an average performance improvement of up to 10% over domain-specific counterparts. Additionally, we highlight the potential of lightweight ML-models for resource-efficient deployment on mobile devices, enabling real-time medical information processing in practical settings. These findings emphasize the importance of embedding selection for optimizing classification performance in the medical domain and establish a robust foundation for the development of advanced, domain-adapted German language models.
%R 10.18653/v1/2025.bionlp-1.7
%U https://aclanthology.org/2025.bionlp-1.7/
%U https://doi.org/10.18653/v1/2025.bionlp-1.7
%P 63-73
Markdown (Informal)
[Transformer-Based Medical Statement Classification in Doctor-Patient Dialogues](https://aclanthology.org/2025.bionlp-1.7/) (Bahrololloomi et al., BioNLP 2025)
ACL