Artificial Intelligence-Powered Simulation for Telehealth Communication Training: Bridging Traditional Simulation and...

Area of Science:

• Healthcare Education Technology
• Artificial Intelligence in Medicine
• Simulation-Based Training

Background:

• Traditional communication training is resource-intensive and difficult to scale.
• Artificial intelligence (AI) and large language models offer potential solutions for healthcare education.
• A methodological blueprint for integrating AI simulation into quality improvement (QI) frameworks is lacking.

Purpose of the Study:

• To present a 5-phase methodological blueprint for implementing AI-powered simulation training.
• To provide evaluatory evidence for enhancing transitional care communication skills using AI.
• To integrate AI simulation within operational QI frameworks.

Main Methods:

• A 5-phase framework was developed, integrating AI simulation with QI and educational principles.
• Phases included content validation, simulation development (cognitive load theory), platform selection, structured implementation, and outcome measurement (statistical process control).
• The framework was grounded in the Donabedian model.

Main Results:

• AI systems struggled with traditional debriefing methods (advocacy-inquiry, plus-delta).
• Microdebriefing with rubric-focused feedback was identified as optimal for AI-mediated learning.
• AI demonstrated strengths in consistent, structured feedback delivery within its limitations.

Conclusions:

• The 5-phase blueprint offers a scalable, cost-effective approach for AI-powered communication training in healthcare.
• Embedding AI simulation within QI infrastructure enhances communication skills systematically and maintains educational rigor.
• AI serves as a scalable alternative to traditional training for foundational communication skills, benefiting simulation science and telehealth education.