A Web-Based Telehealth Training Platform Incorporating Automated Nonverbal Behavior Feedback for Teaching Communication Skills to Medical Students: A Randomized Crossover Study

BACKGROUND In the interests of patient health outcomes, it is important for medical students to develop clinical communication skills. We previously proposed a telehealth communication skills training platform (EQClinic) with automated nonverbal behavior feedback for medical students, and it was able to improve medical students' awareness of their nonverbal communication. OBJECTIVE This study aimed to evaluate the effectiveness of EQClinic to improve clinical communication skills of medical students. METHODS We conducted a 2-group randomized crossover trial between February and June 2016. Participants were second-year medical students enrolled in a clinical communication skills course at an Australian university. Students were randomly allocated to complete online EQClinic training during weeks 1-5 (group A) or to complete EQClinic training during weeks 8-11 (group B). EQClinic delivered an automated visual presentation of students' nonverbal behavior coupled with human feedback from a standardized patient (SP). All students were offered two opportunities to complete face-to-face consultations with SPs. The two face-to-face consultations were conducted in weeks 6-7 and 12-13 for both groups, and were rated by tutors who were blinded to group allocation. Student-Patient Observed Communication Assessment (SOCA) was collected by blinded assessors (n=28) at 2 time points and also by an SP (n=83). Tutor-rated clinical communications skill in face-to-face consultations was the primary outcome and was assessed with the SOCA. We used t tests to examine the students' performance during face-to-face consultations pre- and postexposure to EQClinic. RESULTS We randomly allocated 268 medical students to the 2 groups (group A: n=133; group B: n=135). SOCA communication skills measures (score range 4-16) from the first face-to-face consultation were significantly higher for students in group A who had completed EQClinic training and reviewed the nonverbal behavior feedback, compared with group B, who had completed only the course curriculum components (P=.04). Furthermore, at the second face-to-face assessment, the group that completed a teleconsultation between the two face-to-face consultations (group B) showed improved communication skills (P=.005), and the one that had teleconsultations before the first face-to-face consultation (group A) did not show improvement. CONCLUSIONS The EQClinic is a useful tool for medical students' clinical communication skills training that can be applied to university settings to improve students clinical communication skills development.