Beneficial design features include diverse, authentic case variation and immediate, individualized, actionable, transparent feedback, yet only 52.6% of studies incorporated feedback¶

Claim · All claims
Evidence · 1 study (2 entries) · review r2–r3 · q3
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? Feedback reported as beneficial was immediate, personalized, actionable and transparent, but only 52.6% (n = 51) of studies reported incorporating feedback as a feature, with no temporal association by publication era. → Fang Eric Kin Meng 2026 q3 i? Case diversity across clinical condition, cultural background, preferences, trust and patient personalities, tailored with progressively increasing complexity, aligned learning with authentic clinical practice. → Fang Eric Kin Meng 2026 (2)

Evidence¶

Fang Eric Kin Meng 2026¶

Fang Eric Kin Meng, Boon Yuru, Ho Jin Yang, Tey Natasha, Low Matthew Jian Wen. (2026). Artificial intelligence generated virtual patients in health professions education: a scoping review. BMC Medical Education. https://doi.org/10.1186/s12909-026-10028-w

q3 · i? · review · r2

Cross-study synthesis of beneficial design features charted from 97 included studies; the review reports that only "52.6% (n = 51) of studies reported incorporating feedback as a feature", with a Fisher exact test finding no temporal association (p = 0.79) across publication eras.

"Despite feedback being a beneficial feature, only 52.6% (n = 51) of studies reported incorporating feedback as a feature in the AI generated virtual patients that were developed."

Fang Eric Kin Meng 2026 (2)¶

Fang Eric Kin Meng, Boon Yuru, Ho Jin Yang, Tey Natasha, Low Matthew Jian Wen. (2026). Artificial intelligence generated virtual patients in health professions education: a scoping review. BMC Medical Education. https://doi.org/10.1186/s12909-026-10028-w

q3 · i? · review · r3

Qualitative synthesis of beneficial features across included studies, identifying case diversity across "various dimensions such as clinical condition encountered" and patient backgrounds, tailored to learners with progressively increasing complexity, as aligning with authentic practice.

"included diverse variation in cases across various dimensions such as clinical condition encountered [20, 60, 61, 66, 75, 84, 98], patients' geographical and cultural backgrounds [64, 95, 101], patients' preferences"

Discussion¶

Related Claims¶

• Students recommend integrating computer-based simulation cases into each course to make learning more concrete — related
• In a qualitative pilot with 10 speech-language pathology graduate students, most felt the Simucase assessment cases lacked authenticity because they included too few behavioral modifications — related
• Clearest LLM-teaching signals appear in settings with clearly defined tasks, immediate feedback, and repeated practice, such as simulated patients and structured feedback — possibly the same claim (merge candidate)
• Participants generally perceive NTS training programs as beneficial despite variations in teaching strategies — related
• Proposed course is the only compared course with individualized expert feedback on assignments — related