Breaking Bad News Skills, Clinical Communication, Medical Education
Conditions
Keywords
Virtual Patient, Real-Time Voice Interaction, Clinical Communication, Resident Physicians, Medical Education, Generative Artificial Intelligence
Brief summary
This study evaluated whether an emotionally and interactionally adaptive real-time voice virtual patient can improve clinical communication training for resident physicians. Communication with patients in emotionally challenging situations, such as breaking bad news, requires clinicians to deliver information clearly, recognize emotional cues, respond empathically, and maintain a coherent interaction. Standardized patient training can support these skills but is resource intensive and difficult to provide repeatedly. Real-time voice virtual patients may offer scalable practice opportunities, but simple spoken interaction alone may not provide patient responses that change meaningfully according to the learner's communication. The adaptive virtual patient used in this study was designed to update the patient's emotional tone, openness, defensiveness, and interactional style during the conversation based on the learner's communication behavior. The study compared this adaptive virtual patient training with a non-adaptive real-time voice virtual patient and with standardized patient training. Resident physicians were randomly assigned in a 1:1:1 ratio to one of three groups: emotionally and interactionally adaptive virtual patient training, non-adaptive virtual patient training, or standardized patient training. Participants completed two communication training sessions focused on breaking bad news. After training, participants completed learner-reported measures of perceived response contingency and patient realism. Approximately four weeks later, participants completed a mini-objective structured clinical examination using a human standardized patient to assess communication performance in a delayed near-transfer setting. The primary outcome was the total mini-OSCE communication score at four weeks. Secondary outcomes included mini-OSCE domain scores for structured delivery, emotional responsiveness, and interactional process; learner-reported response contingency and patient realism; and expert-rated behavioral consistency and clinical credibility of virtual patient interactions.
Interventions
BEHAVIORALAdaptive Real-Time Voice Virtual Patient Training
Participants completed two breaking-bad-news communication training sessions with an emotionally and interactionally adaptive real-time voice virtual patient. The virtual patient interacted with participants through continuous spoken dialogue and dynamically updated its emotional tone, openness, defensiveness, and interactional style based on the participant's communication behavior. The adaptive mechanism was designed to provide behavior-contingent patient responses during the encounter.
BEHAVIORALNon-Adaptive Real-Time Voice Virtual Patient Training
Participants completed two breaking-bad-news communication training sessions with a non-adaptive real-time voice virtual patient. The platform, case structure, spoken interaction format, training exposure, and communication tasks were matched to the adaptive virtual patient condition. Unlike the adaptive condition, the virtual patient did not dynamically update its emotional or interactional state based on the participant's communication behavior.
BEHAVIORALStandardized Patient Training
Participants completed two breaking-bad-news communication training sessions with trained human standardized patients. The cases, training objectives, session duration, and communication tasks were structurally matched to the virtual patient training conditions. Standardized patients were trained to portray the assigned clinical communication scenarios using standardized case scripts and interactional guidance.
Sponsors
Wang Shalong
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
OTHER
Masking
SINGLE (Outcomes Assessor)
Masking description
Participants and training facilitators could not be masked because the intervention modalities were visibly different. Outcome assessors who rated the four-week mini-OSCE recordings were masked to group assignment. Expert raters evaluating virtual patient interaction quality were also masked to condition where applicable.
Intervention model description
Participants were randomized in a 1:1:1 ratio to one of three parallel groups: emotionally and interactionally adaptive real-time voice virtual patient training, non-adaptive real-time voice virtual patient training, or standardized patient training. All groups completed two structurally matched breaking-bad-news communication training sessions, followed by a four-week delayed mini-OSCE assessment using a human standardized patient.
Eligibility
Sex/Gender
ALL
Healthy volunteers
Yes
Inclusion criteria
* Resident physicians in postgraduate years 1-3. * Participants who had received basic clinical communication training or related instruction. * Participants who had not received systematic, specialized training in breaking bad news communication. * Able to complete two training sessions and the four-week follow-up mini-OSCE assessment. * Willing to participate and able to provide written informed consent.
Exclusion criteria
* Prior systematic training in breaking bad news, advanced communication skills, or similar specialized communication training. * Prior participation in pilot testing or system testing related to this study. * Unable to complete the required training sessions or follow-up assessment. * Unwilling to have training or assessment sessions recorded for research scoring and analysis. * Concurrent participation in another communication-skills intervention study that could affect communication performance. * Any other condition judged by the investigators to make participation inappropriate.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Four-Week Mini-OSCE Total Communication Score | 4 weeks after completion of training | Communication performance was assessed approximately four weeks after training using a mini-objective structured clinical examination with a human standardized patient. The total score was based on a 9-item structured communication rating scale covering structured delivery, emotional responsiveness, and interactional process. Each item was rated from 1 to 5, yielding a total score range of 9 to 45. Higher scores indicate better clinical communication performance. Scores from two blinded expert raters were averaged to generate participant-level total scores. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Four-Week Mini-OSCE Domain Scores | 4 weeks after completion of training | Domain scores from the four-week mini-OSCE were calculated for three communication domains: structured delivery, emotional responsiveness, and interactional process. Each domain included three items rated from 1 to 5, yielding a domain score range of 3 to 15. Higher scores indicate better performance in the corresponding communication domain. |
| Learner-Reported Perceived Response Contingency and Patient Realism | Immediately after training session 2 (each session was 45 minutes) | Learner-reported interaction measures were assessed after training using 7-point Likert-scale items. Perceived response contingency was calculated as the mean of two items evaluating whether the patient's emotional or interpersonal responses changed during the conversation and whether these changes appeared to depend on how the participant communicated. Perceived patient realism was assessed using a single item evaluating whether the patient's emotional and interpersonal responses felt realistic for a real patient in a clinical conversation. Higher scores indicate stronger perceived response contingency and greater perceived patient realism. |
| Expert-Rated Behavioral Consistency and Clinical Credibility of Virtual Patient Interactions | Training session 2(each session was 45 minutes) | Virtual patient interactions recorded during training session 2 were later assessed by blinded expert raters using 7-point Likert-scale items. Behavioral consistency evaluated whether the virtual patient's emotional tone, interpersonal stance, and overall behavior remained coherent with the case background and internally consistent throughout the interaction. Clinical credibility evaluated whether the virtual patient's emotional and interactional responses were clinically believable for a real patient in the corresponding situation. Higher scores indicate greater behavioral consistency and clinical credibility. This outcome was assessed only for the two virtual patient groups. |
Countries
China
Outcome results
None listed