This paper presents the employment of MedLlama, a decoder-only Large Language Model (LLM) trained within the medical domain, to create a knowledge graph of causal relationships from drug reviews. We leverage a dataset of causal narratives from clinical notes, MIMICause, to benchmark MedLlama for classifying causal narratives using instruction fine-tuning. The results show that it obtains satisfying performance, outperforming other encoder-only baselines. Furthermore, we validate our algorithm robustness and cross-domain generalization by testing it on the Drug Reviews dataset, a collection of patient reviews on specific drugs along with related conditions. We then deploy the model on a subset of around 19,000 Drug Reviews, generating a knowledge graph of 3,050 unique triples connecting 1,149 Drugs and 322 Conditions through the considered causal relations. The results highlight the role of a specific decoder-only LLM fine-tuned within the biomedical domain in advancing causal reasoning and generating valuable resources for real-world biomedical use cases. We make publicly available the drug-condition causal relation knowledge graph to support future research efforts in the field.
ZAVARELLA Vanni;
BERTOLINI Lorenzo;
CONSOLI Sergio;
FENU Gianni;
REFORGIATO RECUPERO Diego;
ZANI Alessandro;
2025-09-03
ELSEVIER
JRC141729
1613-0073 (online),
https://ceur-ws.org/Vol-4020/,
https://publications.jrc.ec.europa.eu/repository/handle/JRC141729,
| Name | Country | City | Type |
|---|
This document is only visible at the Commission level.
You are not authorized to publish or distribute it outside the European Commission.
This is a public document. You can share this publication.
Datasets
| ID | Title | Public URL |
|---|
Dataset collections
| ID | Acronym | Title | Public URL |
|---|
Scripts / source codes
| Description | Public URL |
|---|
Additional supporting files
| File name | Description | File type |
|---|