@inproceedings{lilli-etal-2024-lupus,
title = "Lupus Alberto: A Transformer-Based Approach for {SLE} Information Extraction from {I}talian Clinical Reports",
author = "Lilli, Livia and
Antenucci, Laura and
Ortolan, Augusta and
Bosello, Silvia Laura and
D{'}agostino, Maria Antonietta and
Patarnello, Stefano and
Masciocchi, Carlotta and
Lenkowicz, Jacopo",
editor = "Dell'Orletta, Felice and
Lenci, Alessandro and
Montemagni, Simonetta and
Sprugnoli, Rachele",
booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
month = dec,
year = "2024",
address = "Pisa, Italy",
publisher = "CEUR Workshop Proceedings",
url = "https://aclanthology.org/2024.clicit-1.60/",
pages = "510--516",
ISBN = "979-12-210-7060-6",
abstract = "Natural Language Processing (NLP) is widely used across several fields, particularly in medicine, where information often originates from unstructured data sources. This creates the need for automated systems, in order to classify text and extract information from Electronic Health Records (EHRs). However, a significant challenge lies in the limited availability of pre-trained models for less common languages, such as Italian, and for specific medical domains.Our study aims to develop an NLP approach to extract Systemic Lupus Erythematosus (SLE) information from Italian EHRs at Gemelli Hospital in Rome. We then introduce Lupus Alberto, a fine-tuned version of AlBERTo, trained for classifying categories derived from three distinct domains: Diagnosis, Therapy and Symptom. We evaluated Lupus Alberto`s performance by comparing it with other baseline approaches, selecting from available BERT-based models for the Italian language and fine-tuning them for the same tasks.Evaluation results show that Lupus Alberto achieves overall F-Scores equal to 79{\%}, 87{\%}, and 76{\%} for the Diagnosis, Therapy, and Symptom domains, respectively. Furthermore, our approach outperformed other baseline models in the Diagnosis and Symptom domains, demonstrating superior performance in identifying and categorizing relevant SLE information, thereby improving clinical decision-making and patient management."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lilli-etal-2024-lupus">
<titleInfo>
<title>Lupus Alberto: A Transformer-Based Approach for SLE Information Extraction from Italian Clinical Reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Livia</namePart>
<namePart type="family">Lilli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Antenucci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Augusta</namePart>
<namePart type="family">Ortolan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silvia</namePart>
<namePart type="given">Laura</namePart>
<namePart type="family">Bosello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Antonietta</namePart>
<namePart type="family">D’agostino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefano</namePart>
<namePart type="family">Patarnello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlotta</namePart>
<namePart type="family">Masciocchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacopo</namePart>
<namePart type="family">Lenkowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>CEUR Workshop Proceedings</publisher>
<place>
<placeTerm type="text">Pisa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-12-210-7060-6</identifier>
</relatedItem>
<abstract>Natural Language Processing (NLP) is widely used across several fields, particularly in medicine, where information often originates from unstructured data sources. This creates the need for automated systems, in order to classify text and extract information from Electronic Health Records (EHRs). However, a significant challenge lies in the limited availability of pre-trained models for less common languages, such as Italian, and for specific medical domains.Our study aims to develop an NLP approach to extract Systemic Lupus Erythematosus (SLE) information from Italian EHRs at Gemelli Hospital in Rome. We then introduce Lupus Alberto, a fine-tuned version of AlBERTo, trained for classifying categories derived from three distinct domains: Diagnosis, Therapy and Symptom. We evaluated Lupus Alberto‘s performance by comparing it with other baseline approaches, selecting from available BERT-based models for the Italian language and fine-tuning them for the same tasks.Evaluation results show that Lupus Alberto achieves overall F-Scores equal to 79%, 87%, and 76% for the Diagnosis, Therapy, and Symptom domains, respectively. Furthermore, our approach outperformed other baseline models in the Diagnosis and Symptom domains, demonstrating superior performance in identifying and categorizing relevant SLE information, thereby improving clinical decision-making and patient management.</abstract>
<identifier type="citekey">lilli-etal-2024-lupus</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.60/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>510</start>
<end>516</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lupus Alberto: A Transformer-Based Approach for SLE Information Extraction from Italian Clinical Reports
%A Lilli, Livia
%A Antenucci, Laura
%A Ortolan, Augusta
%A Bosello, Silvia Laura
%A D’agostino, Maria Antonietta
%A Patarnello, Stefano
%A Masciocchi, Carlotta
%A Lenkowicz, Jacopo
%Y Dell’Orletta, Felice
%Y Lenci, Alessandro
%Y Montemagni, Simonetta
%Y Sprugnoli, Rachele
%S Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)
%D 2024
%8 December
%I CEUR Workshop Proceedings
%C Pisa, Italy
%@ 979-12-210-7060-6
%F lilli-etal-2024-lupus
%X Natural Language Processing (NLP) is widely used across several fields, particularly in medicine, where information often originates from unstructured data sources. This creates the need for automated systems, in order to classify text and extract information from Electronic Health Records (EHRs). However, a significant challenge lies in the limited availability of pre-trained models for less common languages, such as Italian, and for specific medical domains.Our study aims to develop an NLP approach to extract Systemic Lupus Erythematosus (SLE) information from Italian EHRs at Gemelli Hospital in Rome. We then introduce Lupus Alberto, a fine-tuned version of AlBERTo, trained for classifying categories derived from three distinct domains: Diagnosis, Therapy and Symptom. We evaluated Lupus Alberto‘s performance by comparing it with other baseline approaches, selecting from available BERT-based models for the Italian language and fine-tuning them for the same tasks.Evaluation results show that Lupus Alberto achieves overall F-Scores equal to 79%, 87%, and 76% for the Diagnosis, Therapy, and Symptom domains, respectively. Furthermore, our approach outperformed other baseline models in the Diagnosis and Symptom domains, demonstrating superior performance in identifying and categorizing relevant SLE information, thereby improving clinical decision-making and patient management.
%U https://aclanthology.org/2024.clicit-1.60/
%P 510-516
Markdown (Informal)
[Lupus Alberto: A Transformer-Based Approach for SLE Information Extraction from Italian Clinical Reports](https://aclanthology.org/2024.clicit-1.60/) (Lilli et al., CLiC-it 2024)
ACL
- Livia Lilli, Laura Antenucci, Augusta Ortolan, Silvia Laura Bosello, Maria Antonietta D’agostino, Stefano Patarnello, Carlotta Masciocchi, and Jacopo Lenkowicz. 2024. Lupus Alberto: A Transformer-Based Approach for SLE Information Extraction from Italian Clinical Reports. In Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024), pages 510–516, Pisa, Italy. CEUR Workshop Proceedings.