DART: A Structured Dataset of Regulatory Drug Documents in Italian for Clinical NLP

TL;DR

This paper introduces DART, a structured Italian dataset of regulatory drug documents, enabling improved clinical NLP tasks like drug interaction inference using large language models.

Contribution

DART is the first structured Italian corpus of regulatory drug documents, created through a reproducible pipeline and validated with an LLM-based drug interaction checker.

Findings

LLMs can accurately infer drug interactions using DART

DART enables extraction of key pharmacological information

The dataset supports clinical NLP applications in Italian healthcare

Abstract

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.