Managing Conflict of Interest in Clinical Practice Guidelines With Artificial Intelligence: Insights From Large Language Models and Beyond

Abstract

Background: Conflict of interest (COI) management is critical for ensuring the scientific integrity and fairness of clinical practice guidelines (CPGs). Large language models (LLMs) have great potential in strengthening COI management, particularly in information collection, assessment, and supporting guideline development groups. Objective: To explore LLMs’ role in COI management during CPG development, focusing on applications, challenges, and future directions. Methods: We examined how LLMs can support COI management by designing and testing a set of simulated COI scenarios based on established management principles. Results: LLMs can improve efficiency in data collection (e.g., in analyzing disclosures), objectivity in risk assessment, and transparency in reporting. However, privacy risks (e.g., data breaches) and technical issues (e.g., model bias) hinder the adoption of LLM based approaches. Setting up policy frameworks, research collaboration, and enhanced security, such as differential privacy levels, can enhance reliability. Conclusion: LLMs can support COI management in CPG development if ethical issues are adequately considered, but validation in real-world settings is still needed.