AIHealthcare Analytics

Research Stage and Trajectory

Research on generative AI (GAI) in clinical skills training is characterized as early-stage but rapidly expanding. Bibliometric analysis reveals growing scholarly attention concentrated on language-model-driven educational applications, with a parallel rise in publications addressing ethical dimensions of GAI use in training environments.

Knowledge Structure and Thematic Priorities

The bibliometric findings map the field's knowledge structure and thematic priorities rather than providing direct evidence of educational effectiveness. Dominant themes include language model applications for simulated patient interaction, procedural training support, and competency assessment. Ethical concerns — including academic integrity, bias in training data, and equity of access — are increasingly prominent in the literature.

Methodological Gaps

A central critique is that existing research lacks rigorous empirical designs. Most published work is descriptive or exploratory, limiting conclusions about whether GAI tools actually improve clinical skill acquisition or patient safety outcomes. Standardized evaluation frameworks for assessing educational effectiveness and safety are notably absent from the current literature.

Recommendations

Future research is urged to adopt controlled empirical methodologies and develop standardized outcome metrics capable of distinguishing genuine educational benefit from novelty effects. Safety assessment — including the risk of trainees over-relying on AI-generated guidance — is identified as an underexplored priority requiring dedicated study designs.