Virtual standardized patient chatbot – a tool for performance improvement in undergraduate medical students
Virtual standardized patients (VSP) offer unique opportunities to simulate clinical scenarios in a risk-free environment, providing both faculty members and undergraduate medical students with a tool for developing clinical skills, vital for day-to-day clinical practice. However, most VSPs have a binary path type that only provides predefined options of interaction to the student (branching narrative), not allowing a reliable representation of real patient interaction. In this work, a conjugation of chatbots and VSP capable of producing a dynamic dialogue using Natural Language Processing will be developed. The user perspective will also be considered, and this tool’s impact in test anxiety and overall clinical skills development.
For this project we have established the following tasks:
1.Model implementation and concept testing: The system will be composed of software that controls the medical student and patient’s interaction. This system will then be reviewed and improved with teaching staff and students (ICVS/iCognitus).
2.Impact upon the student learning experience and effect on training analysis: The key indicators of the nature of the student’s learning experience will be evaluated. A qualitative perspective of the students attitude towards the system and overall experience will also be studied through written/verbally obtained feedback (ICVS).
3.Impact on students’ performance on regular OSCE assessment: Impact of training with the system will be assessed trough Randomized Controlled Trial (ICVS).
Main Project Outcomes
S. Queirós, “Right ventricular segmentation in multi-view cardiac MRI using a unified U-net model”, in E. Puyol Antón et al. (eds) Statistical Atlases and Computational Models of the Heart. Multi-Disease, Multi-View, and Multi-Center Right Ventricular Segmentation in Cardiac MRI Challenge. STACOM 2021. Lecture Notes in Computer Science, vol 13131, pp. 287-295, Springer, Cham, 2022.
“Best Paper Award in the M&Ms-2 Challenge”, by M&Ms2 Challenge organizers and the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society.
Main Project Outcomes
Outputs: A systematic review on the use of chatbots in education is in preparation.