AI-Enhanced Social Robotic Versus Computer-Based Virtual Patients for Clinical Reasoning Training in Medical...

Area of Science:

• Medical Education Technology
• Artificial Intelligence in Healthcare
• Clinical Reasoning Training

Background:

• Virtual patient (VP) simulations are crucial for clinical reasoning (CR) practice.
• Conventional computer-based VPs often lack realism and engagement.
• AI-enhanced social robotic VPs show promise but lack quantitative comparative data.

Purpose of the Study:

• To quantitatively compare medical students' experiences with AI-enhanced social robotic VPs versus conventional computer-based VPs.
• To assess how platform design characteristics facilitate CR skill training.

Main Methods:

• An observational crossover cohort study involving 178 medical students.
• Students used both a social artificial intelligence-enhanced robotic interface (SARI) and a virtual interactive case (VIC) platform.
• VP design and CR training preferences were evaluated using validated questionnaires and Visual Analogue Scales.

Main Results:

• SARI outperformed VIC across all evaluated design domains: authenticity, professional approach, coaching quality, learning effect, and overall judgment.
• Students overwhelmingly preferred SARI for CR training (72% vs. 14%).
• Preference for SARI was consistent across most subgroups, with some exceptions for students with prior VP experience or those initially introduced to VIC.

Conclusions:

• AI-enhanced social robotic VPs offer superior design characteristics for CR training compared to conventional platforms.
• These findings support the integration of AI-driven social robots in medical education to enhance student preparedness for clinical practice.
• This study provides the first quantitative comparison of design characteristics between AI-enhanced social robotic and conventional computer-based VPs.