Breaking bad news with reflective AI virtual experience (BRAVE): development and evaluation of a generative AI-based simulation tool

Abstract

Breaking bad news (BBN) to patients is complex and emotionally and cognitively demanding. The way bad news is delivered has implications for patients, their significant others, and healthcare professionals. Despite the development of structured BBN protocols, many health professionals report insufficient training and low self-efficacy for conducting these conversations. While best-practice BBN education exist, opportunities for repeated practice with high-quality feedback are limited, representing a critical barrier to scalability and global health equity, particularly in resource-constrained settings. We developed BRAVE (Breaking Bad News with AI Reflective Virtual Experience), a generative AI-based simulator that includes a written BBN encounter with a virtual patient. Unlike prior AI simulators that primarily offered structured summary feedback, BRAVE explicitly combines a prompted, dialogic reflective debrief followed by personalized feedback mapped to the SPwICES protocol. A prospective, single arm, pre-post design, which incorporates both quantitative and qualitative measures. Ninety-nine senior medical students completed one BRAVE session following a required BBN course. Pre/post questionnaires assessed self-efficacy, willingness to engage in BBN, and intention to apply the BBN protocol. User experience was rated on a 5-point scale. Quantitative analysis included paired-sample t-tests and descriptive statistics. Qualitative data from open-ended responses were analyzed using immersion/crystallization. Self-efficacy increased from M = 6.95 to M = 7.62 (p<.001), willingness from M = 5.80 to M = 6.51 (p<.001), and intention to apply the protocol from M = 8.20 to M = 8.41 (p=.005). User experience was positive: interaction quality (M = 4.27), structured feedback (M = 4.19), reflective dialogue (M = 3.91), and interest in future use (M = 3.81). Qualitative analysis showed most students described the simulator as realistic, useful, and safe for practice, emphasizing opportunities to think, reread, and make mistakes with reduced embarrassment; a minority noted limits of the written modality (restricted nonverbal cues and occasional recognition errors), which were addressed during refinement. A brief text-based GenAI simulation integrating dialogic reflection with protocol-based feedback yielded improvements in learners’ confidence and willingness to conduct BBN and was well-received. BRAVE can complement existing curricula by offering scalable, psychologically safe, and feedback-rich practice; future controlled studies with performance-based outcomes are warranted.

Ähnliche Arbeiten