JMIR Publications

ABSTRACT

Background:

The addition of simulated patients to medical and nursing training makes it possible to create a link between theory and practice. This makes what has been learned more realistic and allows the complexity and multi-layered nature of many illnesses to be reflected in a real-life setting. However, the selection, training and supervision of actors as simulation patients is time-consuming and expensive. As part of the requirements analysis for a robot simulation patient for medical education, we interviewed the head of the acting patient program at the University of Oldenburg in detail. In this article, we investigate how differently students and nurses perceive two different methods of patient simulation.

Objective:

The aim of this research is to investigate whether a humanoid robot can reproduce patient behavior so that participants can identify symptoms and make a diagnosis based on them. As a comparison, we let a second group of participants make a diagnosis based on a video with a human patient actor. We want to find out whether the robot is equally or less suitable as a simulated patient for making a diagnosis.

Methods:

For this reason, we asked the participants (n=21) in our study to collect a psychopathological assessment. Group 1 (n1=11) used the humanoid robot as a patient simulator, group 2 (n2=10) watched the identical symptoms in a video with a professional human actor as a patient simulator.

Results:

The participants (medical students and nurses) were on mean 28.7 years old, the students in their 6th semester and had on average 7.5 years of professional experience in the medical field. The correct diagnosis was made 9 times correctly in the video with the human patient actor, and 10 times with the robot. One participant in each group made the wrong diagnosis, in total an error rate of 9.5%. Nine participants can identify the symptoms shown in the video by the human actor, ten participants can identify the symptoms shown by the robot patient. One participant from each group cannot identify all symptoms shown by the robot/video. In general, participants with the humanoid robot patient felt more confident that their diagnosis was correct compared to those with the human patient (robot patient: neutral-very confident: 9; uncertain-very uncertain: 2), human patient: neutral-very confident: 9; uncertain: unsure: 1).

Conclusions:

The simulations of the human patient actor in the video were judged to be more realistic overall than the humanoid robot patient. However, the differences between the simulation methods in relation to the result (diagnosis) were very small. The results of our study shows a good performance of the robot in the simulation of selected psychiatric patient cases. We concluded that a humanoid robot patient could be a useful addition to patient simulators in medical education and discuss future directions. Clinical Trial: Permission was granted from a university medical ethics committee to undertake this study (2024-016).