Utilizing Real-time Human-Assisted Virtual Humans to Increase Real-world Interaction Empathy

Empathy is an important aspect of interpersonal communication skills. These skills are emphasized in medical education. The standard source of training is interviews with standardized patients. Standardized patients are trained actors who evaluate students on the effectiveness of their interviews and diagnosis. One source of additional training is interviews with virtual humans. Virtual humans can be used in conjunction with standardized patients to help train medical students with empathy. In this case, empathy training took place as part of a virtual human interaction that represented a patient suffering from depression. However, computers cannot accurately rate empathy, and we thus propose a hybrid experience. We propose a hybrid virtual human approach where hidden workers assist the virtual human. Hidden workers provide real-time empathetic feedback that is shown to the students after their interaction with the virtual human. The students then interview a standardized patient. All empathetic feedback and ratings are based on the Empathic Communication and Coding System (ECCS) as developed for medical student interviews. Fifty-two students took part in the study. The results suggest that students who received feedback after their virtual patient interview did provide more empathetic statements, were more likely to develop good rapport, and did act more warm and caring as compared to the control group that did not receive feedback.