Year: 2025
Type: conference-paper
Abstract: Medicine shortages pose a significant threat to healthcare systems worldwide, disrupting patient care and increasing costs. Social media platforms, with their real-time user-posted content, offer a valuable opportunity to detect early signs of such shortages. This paper introduces MedShort, a novel framework that leverages large language models (LLMs) to monitor, analyze, and detect Medicine Shortages from social media data while preserving user privacy. Key features include filtering relevant posts, extracting specific medicines and geographic insights, and providing actionable analytics for stakeholders. Experimental results show MedShort's effectiveness, with refined LLMs achieving high accuracy, precision, and recall across several medicines. By integrating privacy-preserving mechanisms, MedShort ensures ethical data handling, enabling near real-time and scalable monitoring of medicine shortages.
Authors: Xueping Peng, Peng Yan, Tao Shen, Ming Xie, Guodong Long
Institution: University of Technology Sydney
Language: English
Subfield: Epidemiology
Field: Medicine
Domain: Health Sciences
Open Access status: gold
OpenAlex ID: W4410637133