@inproceedings{romero-etal-2025-insightbuddy,
title = "{INSIGHTBUDDY}-{AI}: Medication Extraction and Entity Linking using Pre-Trained Language Models and Ensemble Learning",
author = "Romero, Pablo and
Han, Lifeng and
Nenadic, Goran",
editor = "Ebrahimi, Abteen and
Haider, Samar and
Liu, Emmy and
Haider, Sammar and
Leonor Pacheco, Maria and
Wein, Shira",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = apr,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-srw.2/",
doi = "10.18653/v1/2025.naacl-srw.2",
pages = "18--27",
ISBN = "979-8-89176-192-6",
abstract = "This paper presents our system, InsightBuddy-AI, designed for extracting medication mentions and their associated attributes, and for linking these entities to established clinical terminology resources, including SNOMED-CT, the British National Formulary (BNF), ICD, and the Dictionary of Medicines and Devices (dm+d).To perform medication extraction, we investigated various ensemble learning approaches, including stacked and voting ensembles (using first, average, and max voting methods) built upon eight pre-trained language models (PLMs). These models include general-domain PLMs{---}BERT, RoBERTa, and RoBERTa-Large{---}as well as domain-specific models such as BioBERT, BioClinicalBERT, BioMedRoBERTa, ClinicalBERT, and PubMedBERT.The system targets the extraction of drug-related attributes such as adverse drug effects (ADEs), dosage, duration, form, frequency, reason, route, and strength.Experiments conducted on the n2c2-2018 shared task dataset demonstrate that ensemble learning methods outperformed individually fine-tuned models, with notable improvements of 2.43{\%} in Precision and 1.35{\%} in F1-score.We have also developed cross-platform desktop applications for both entity recognition and entity linking, available for Windows and macOS.The InsightBuddy-AI application is freely accessible for research use at \url{https://github.com/HECTA-UoM/InsightBuddy-AI}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="romero-etal-2025-insightbuddy">
<titleInfo>
<title>INSIGHTBUDDY-AI: Medication Extraction and Entity Linking using Pre-Trained Language Models and Ensemble Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Romero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Nenadic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abteen</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sammar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Leonor Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shira</namePart>
<namePart type="family">Wein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-192-6</identifier>
</relatedItem>
<abstract>This paper presents our system, InsightBuddy-AI, designed for extracting medication mentions and their associated attributes, and for linking these entities to established clinical terminology resources, including SNOMED-CT, the British National Formulary (BNF), ICD, and the Dictionary of Medicines and Devices (dm+d).To perform medication extraction, we investigated various ensemble learning approaches, including stacked and voting ensembles (using first, average, and max voting methods) built upon eight pre-trained language models (PLMs). These models include general-domain PLMs—BERT, RoBERTa, and RoBERTa-Large—as well as domain-specific models such as BioBERT, BioClinicalBERT, BioMedRoBERTa, ClinicalBERT, and PubMedBERT.The system targets the extraction of drug-related attributes such as adverse drug effects (ADEs), dosage, duration, form, frequency, reason, route, and strength.Experiments conducted on the n2c2-2018 shared task dataset demonstrate that ensemble learning methods outperformed individually fine-tuned models, with notable improvements of 2.43% in Precision and 1.35% in F1-score.We have also developed cross-platform desktop applications for both entity recognition and entity linking, available for Windows and macOS.The InsightBuddy-AI application is freely accessible for research use at https://github.com/HECTA-UoM/InsightBuddy-AI.</abstract>
<identifier type="citekey">romero-etal-2025-insightbuddy</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-srw.2</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-srw.2/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>18</start>
<end>27</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T INSIGHTBUDDY-AI: Medication Extraction and Entity Linking using Pre-Trained Language Models and Ensemble Learning
%A Romero, Pablo
%A Han, Lifeng
%A Nenadic, Goran
%Y Ebrahimi, Abteen
%Y Haider, Samar
%Y Liu, Emmy
%Y Haider, Sammar
%Y Leonor Pacheco, Maria
%Y Wein, Shira
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-192-6
%F romero-etal-2025-insightbuddy
%X This paper presents our system, InsightBuddy-AI, designed for extracting medication mentions and their associated attributes, and for linking these entities to established clinical terminology resources, including SNOMED-CT, the British National Formulary (BNF), ICD, and the Dictionary of Medicines and Devices (dm+d).To perform medication extraction, we investigated various ensemble learning approaches, including stacked and voting ensembles (using first, average, and max voting methods) built upon eight pre-trained language models (PLMs). These models include general-domain PLMs—BERT, RoBERTa, and RoBERTa-Large—as well as domain-specific models such as BioBERT, BioClinicalBERT, BioMedRoBERTa, ClinicalBERT, and PubMedBERT.The system targets the extraction of drug-related attributes such as adverse drug effects (ADEs), dosage, duration, form, frequency, reason, route, and strength.Experiments conducted on the n2c2-2018 shared task dataset demonstrate that ensemble learning methods outperformed individually fine-tuned models, with notable improvements of 2.43% in Precision and 1.35% in F1-score.We have also developed cross-platform desktop applications for both entity recognition and entity linking, available for Windows and macOS.The InsightBuddy-AI application is freely accessible for research use at https://github.com/HECTA-UoM/InsightBuddy-AI.
%R 10.18653/v1/2025.naacl-srw.2
%U https://aclanthology.org/2025.naacl-srw.2/
%U https://doi.org/10.18653/v1/2025.naacl-srw.2
%P 18-27
Markdown (Informal)
[INSIGHTBUDDY-AI: Medication Extraction and Entity Linking using Pre-Trained Language Models and Ensemble Learning](https://aclanthology.org/2025.naacl-srw.2/) (Romero et al., NAACL 2025)
ACL