Expert evaluation found the virtual patient realistic and immediate ACT feedback increased therapists' awareness of intervention choices¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2026 · checked against its sources 2026-10-15 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i? Two practicing psychologists rated the virtual patient as realistic and reported that turn-by-turn ACT feedback and the retry mechanism increased awareness of therapeutic language and intervention choices. → Pascal Riachi 2026

Evidence¶

Pascal Riachi 2026¶

Pascal Riachi, Sofie Kamber, Stella Brogna, Andrew Gloster, Rafael Wampfler. (2026). Toward Accessible Psychotherapy Training Using AI-Driven Interactive Patient Avatars. https://arxiv.org/abs/2606.17786 doi:10.48550/arxiv.2606.17786

q2 · i? · design · r2

Mixed-methods expert evaluation with two female psychologists (ages 25–30), one licensed with 4–7 years of experience and one in training with 1–3 years, each using the system for approximately 90 minutes. Participants reported that the feedback mechanism "increased awareness of therapeutic language and intervention choices". No effect sizes were reported.

"Both participants valued the immediate, turn-by-turn ACT feedback, reporting that the visual ACT score and retry/continue mechanism increased awareness of therapeutic language and intervention choices."

Discussion¶

Related Claims¶

• Simulation Based Education With Deliberate Practice Improves Clinical Outcomes — related
• The adaptive virtual patient produces a steadily climbing disclosure trajectory across a session while a prompt-only baseline with the same LLM and persona stays flat — related
• In the AVP, per-turn disclosure change responds to trainee exploration but not measurably to trainee empathy, and the static baseline shows no significant joint response — related
• Post-session subjective ratings favored the adaptive system for the expressive persona but showed a reversed adaptivity disadvantage for the guarded persona — related
• Simulation Based Education Improves Outcomes — related
• GPT-4o mini showed progressive turn-level convergence with accumulating context while larger models showed increasing or stable error — related
• Formative participants preferred post-session debriefing over in-session interruption, with timing treated as contingent on error severity — related
• Participants rated SOPHIE 2.0 as engaging, easy to use, and clinically relevant in a self-service format — related
• Student satisfaction with virtual patients is generally positive, with item-level comparisons dominating and some confidence exceptions — related