Using AI-generated suggestions from ChatGPT to optimize clinical decision support
Watch the Recording
Presenters
Siru Liu, PhD
Aileen Wright, MD
Manager
Lu He, BS
Statement of Purpose
Alert fatigue is a pressing issue. In this study, we evaluated the feasibility of using ChatGPT to generate suggestions for improving the specificity of alert logic. The suggestions generated by AI were found to offer unique perspectives and were evaluated as highly understandable and relevant, with moderate usefulness, low acceptance, bias, inversion, redundancy, and low ability to improve clinical workflow. Therefore, these AI-generated suggestions could be an important complementary part of optimizing CDS alerts, can identify potential improvements to alert logic and support their implementation, and may even be able to assist experts in formulating their own suggestions for CDS improvement. Overall, ChatGPT shows great potential for using large language models and reinforcement learning from human feedback to improve CDS alert logic and potentially other medical areas involving complex, clinical logic, a key step in the development of an advanced learning health system.
Learning Objectives
- Understand the potential benefits and limitations of using artificial intelligence tools, such as ChatGPT, for generating suggestions to improve clinical decision support (CDS) logic.
- Learn about the potential of AI-generated suggestions to assist experts in formulating their own suggestions for CDS improvement.
- Develop an understanding of how large language models and reinforcement learning can be used to improve CDS alert logic and other medical areas.