Sequence interview training stepwise from AI-VPs to standardized patients to real patients¶

Strategy · All strategies
Evidence · 5 claims (4 for, 1 mixed) · 3 studies (2 review, 1 quant-synthesis), q2–q3 · 1 of 3 report an effect size · 5 claims rest on one study

Description¶

The review proposes a progressive training pathway in which learners begin clinical interview practice with AI-VPs, move to standardized patients, and finish with real patient encounters. The authors state "A stepwise training pathway could be implemented, whereby students initiate their learning of clinical interviews with AI-VPs, subsequently progress to standardized patients, and ultimately transition to real patient encounters." This sequencing is intended to promote gradual complexity increase, reduce initial anxiety, allow consequence-free repetition, and consolidate interpersonal and clinical skills, aligning with experiential learning principles.

Design Implications¶

Context¶

Requirements¶

• AI-VPs must offer a standardized, repeatable, and immersive experience suitable for acquiring basic communication skills before real-patient complexity

Constraints¶

• The review presents this as a proposed model, not a tested intervention; it is framed as in line with experiential learning principles rather than empirically validated

Target Learners¶

• healthcare students
• medical and nursing students
• healthcare professionals in interview training

Target Learning Goals¶

• clinical interview skills
• communication skills
• empathy
• reduced performance anxiety before clinical practice

Claims¶

• AI-VPs delivering immediate, targeted feedback improve empathic communication in subsequent human-based interviews [+W]
• Repeated exposure to AI-VPs is associated with improved perceived self-efficacy and more positive attitudes toward communication training [+W]
• Evidence of transfer from AI-VP training to real clinical practice is scarce, and one cohort study found lower field assessment scores after AI-VP training [~W]
• Live simulations with real patients showed the greatest effects among simulation types (g = 2.27, medical education only) [+W]
• Controlled GenAI virtual-patient and communication studies reported short-term skill gains, but positive findings were not universal [+W]

Related Strategies¶

• Tiered ECE implementation: virtual and case-based learning first, then simulated patient interaction, then supervised real patient contact
• Use structured training pathways with supervised early practice and experience-informed patient counselling in hip arthroscopy

Examples¶

-

Key Sources¶

• Gilbert Valentin, Philip Pierre, Llorca Pierre-Michel, Samalin Ludovic. (2026). Use of artificial intelligence–enhanced virtual patients in educational approaches to medical interview training: a systematic review. BMC Medical Education. https://doi.org/10.1186/s12909-026-08804-9