Using Artificial Intelligence for Identifying Quality Improvement Interventions in Clinical Medical Clerkships: AI...

Area of Science:

• Medical Education
• Artificial Intelligence
• Quality Improvement

Background:

• Medical student feedback is crucial for identifying areas needing improvement in clinical rotations.
• Analyzing qualitative feedback manually is time-consuming and resource-intensive.
• Scalable solutions are needed to efficiently process and act on educational feedback.

Purpose of the Study:

• To develop and evaluate an Artificial Intelligence (AI) process for identifying quality improvement interventions from medical student feedback.
• To compare the accuracy and efficiency of AI versus human analysis in categorizing feedback and suggesting improvements.
• To assess the scalability of an AI approach for enhancing clinical education.

Main Methods:

• A novel process utilizing AI was developed to analyze qualitative feedback from medical students on clinical rotations.
• AI algorithms were trained to categorize comments and identify actionable quality improvement suggestions.
• The AI's performance was benchmarked against human accuracy in categorization and intervention proposal.

Main Results:

• The AI process demonstrated accuracy comparable to human analysis in categorizing student feedback.
• AI effectively identified actionable quality improvement interventions from the feedback data.
• The AI approach significantly reduced the time required for feedback analysis compared to manual methods.

Conclusions:

• Artificial Intelligence offers a viable and accurate method for processing medical student feedback to drive quality improvements.
• This AI-driven process provides a scalable solution for enhancing the quality of medical education at clinical sites.
• Implementing AI can streamline the analysis of qualitative data, leading to more efficient educational program enhancements.