Guardado en:
Detalles Bibliográficos
Autores principales: Barone, Mariano, Laudante, Antonio, Riccio, Giuseppe, Romano, Antonio, Postiglione, Marco, Moscato, Vincenzo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2510.18475
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917029484691456
author Barone, Mariano
Laudante, Antonio
Riccio, Giuseppe
Romano, Antonio
Postiglione, Marco
Moscato, Vincenzo
author_facet Barone, Mariano
Laudante, Antonio
Riccio, Giuseppe
Romano, Antonio
Postiglione, Marco
Moscato, Vincenzo
contents The extraction of pharmacological knowledge from regulatory documents has become a key focus in biomedical natural language processing, with applications ranging from adverse event monitoring to AI-assisted clinical decision support. However, research in this field has predominantly relied on English-language corpora such as DrugBank, leaving a significant gap in resources tailored to other healthcare systems. To address this limitation, we introduce DART (Drug Annotation from Regulatory Texts), the first structured corpus of Italian Summaries of Product Characteristics derived from the official repository of the Italian Medicines Agency (AIFA). The dataset was built through a reproducible pipeline encompassing web-scale document retrieval, semantic segmentation of regulatory sections, and clinical summarization using a few-shot-tuned large language model with low-temperature decoding. DART provides structured information on key pharmacological domains such as indications, adverse drug reactions, and drug-drug interactions. To validate its utility, we implemented an LLM-based drug interaction checker that leverages the dataset to infer clinically meaningful interactions. Experimental results show that instruction-tuned LLMs can accurately infer potential interactions and their clinical implications when grounded in the structured textual fields of DART. We publicly release our code on GitHub: https://github.com/PRAISELab-PicusLab/DART.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18475
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DART: A Structured Dataset of Regulatory Drug Documents in Italian for Clinical NLP
Barone, Mariano
Laudante, Antonio
Riccio, Giuseppe
Romano, Antonio
Postiglione, Marco
Moscato, Vincenzo
Computation and Language
The extraction of pharmacological knowledge from regulatory documents has become a key focus in biomedical natural language processing, with applications ranging from adverse event monitoring to AI-assisted clinical decision support. However, research in this field has predominantly relied on English-language corpora such as DrugBank, leaving a significant gap in resources tailored to other healthcare systems. To address this limitation, we introduce DART (Drug Annotation from Regulatory Texts), the first structured corpus of Italian Summaries of Product Characteristics derived from the official repository of the Italian Medicines Agency (AIFA). The dataset was built through a reproducible pipeline encompassing web-scale document retrieval, semantic segmentation of regulatory sections, and clinical summarization using a few-shot-tuned large language model with low-temperature decoding. DART provides structured information on key pharmacological domains such as indications, adverse drug reactions, and drug-drug interactions. To validate its utility, we implemented an LLM-based drug interaction checker that leverages the dataset to infer clinically meaningful interactions. Experimental results show that instruction-tuned LLMs can accurately infer potential interactions and their clinical implications when grounded in the structured textual fields of DART. We publicly release our code on GitHub: https://github.com/PRAISELab-PicusLab/DART.
title DART: A Structured Dataset of Regulatory Drug Documents in Italian for Clinical NLP
topic Computation and Language
url https://arxiv.org/abs/2510.18475