Skip to main content

PERSPECTIVE article

Front. Med.
Sec. Regulatory Science
Volume 12 - 2025 | doi: 10.3389/fmed.2025.1527864
This article is part of the Research Topic Large Language Models for Medical Applications View all 10 articles

Navigating the Potential and Pitfalls of Large Language Models in Patient-Centered Medication Guidance and Self-Decision Support

Provisionally accepted
Serhat Aydin Serhat Aydin 1Mert Karabacak Mert Karabacak 2Victoria Vlachos Victoria Vlachos 3Konstantinos Margetis Konstantinos Margetis 2*
  • 1 School of Medicine, Koç University, Sarıyer, Türkiye
  • 2 Mount Sinai Health System, New York, New York, United States
  • 3 College of Human Ecology, Cornell University, Ithaca, New York, United States

The final, formatted version of the article will be published soon.

    Large Language Models (LLMs) are transforming patient education in medication management by providing accessible information to support healthcare decision-making. Building on our recent scoping review of LLMs in patient education, this perspective examines their specific role in medication guidance. These artificial intelligence (AI)-driven tools can generate comprehensive responses about drug interactions, side effects, and emergency care protocols, potentially enhancing patient autonomy in medication decisions. However, significant challenges exist, including the risk of misinformation and the complexity of providing accurate drug information without access to individual patient data. Safety concerns are particularly acute when patients rely solely on AIgenerated advice for self-medication decisions. This perspective analyzes current capabilities, examines critical limitations, and raises questions regarding the possible integration of LLMs in medication guidance. We emphasize the need for regulatory oversight to ensure these tools serve as supplements to, rather than replacements for, professional healthcare guidance.

    Keywords: Large Language Models1, ChatGPT2, patient education3, self-medication4, Artificial Intelligence5, machine learning6, Deep Learning7

    Received: 13 Nov 2024; Accepted: 09 Jan 2025.

    Copyright: © 2025 Aydin, Karabacak, Vlachos and Margetis. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Konstantinos Margetis, Mount Sinai Health System, New York, New York, United States

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.