AI-generated Feedback Following Social Robotic Virtual Patient Interactions and Medical Student Performance: Nonrandomized Quasi-Experimental Study
AI-generated feedback following social robotic VP interactions significantly improved medical students' OSCE-based performance, particularly in generic medical history taking. These findings support integrating validated AI feedback systems as a supplement to expert-led teaching during VP simulations for clinical training and demonstrate the feasibility of scalable, automated feedback in medical education. The domain-specific improvements in generic medical history highlight the importance of targeted, competency-specific feedback design in VP platforms.
Authors
- Carina Georg (ORCID: https://orcid.org/0000-0001-8444-7624)
- Mini Ruiz (ORCID: https://orcid.org/0000-0002-9910-8809)
- Viking Huss (ORCID: https://orcid.org/0000-0002-9764-6435)
- Cidem Gentline
- Gabriel Skantze (ORCID: https://orcid.org/0000-0002-8579-1790)
- Benjamin Jobs (ORCID: https://orcid.org/0009-0002-2391-8087)
- Jonathan Schiött (ORCID: https://orcid.org/0009-0001-0445-630X)
- William Ivegren (ORCID: https://orcid.org/0009-0004-8417-6106)
- Anna Margareta Hugelius
- Alexander Borg
- Samuel Edelbring
Institutions
- Karolinska University Hospital (SE)
- Örebro University (SE)
- Royal College of Music in Stockholm (SE)
- Karolinska Institutet (SE)
- Mälardalen University (SE)
- KTH Royal Institute of Technology (SE)
Publication Details
- Journal
- JMIR Medical Education
- Published
- 2026-02-26
- DOI
- https://doi.org/10.2196/90368
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00