Navigating the potential and pitfalls of large language models in patient-centered medication guidance and self-decision support

Потенциал и риски больших языковых моделей в ориентированном на пациента консультировании по применению лекарственных средств и поддержке самостоятельного принятия решений
Mert Karabacak, Victoria Vlachos, Konstantinos D. Margetis, Serhat Aydin
2025-01-23

large language modelsmedication guidancepatient educationregulatory oversightself-medication decisions
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 AI-generated 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.
1
By supporting patient education, LLMs may enhance autonomy in medication-related healthcare decision-making.
2
LLM-generated medication guidance risks misinformation and cannot reliably account for individual patient data and clinical context.
3
LLMs can provide accessible, comprehensive medication information covering drug interactions, side effects, and emergency-care protocols.
4
Regulatory oversight is needed to ensure LLMs supplement rather than replace professional healthcare guidance.
5
Safety risks are especially pronounced when patients rely solely on AI advice for self-medication decisions.

large language models used for patient-centered medication guidance and self-decision support

their capabilities, limitations, safety risks, and potential integration into medication guidance, particularly for drug information and self-medication decisions

Publication Details
Publication Date
2025-01-23
Journal
Publisher
ISSN
Cited by
27
Access Type
Author Information
Authors
Mert Karabacak
Victoria Vlachos
Konstantinos D. Margetis
Serhat Aydin
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%