Functional complementarity model of AI and human roles in clinical skills education¶

Design · All designs
Evidence · 2 claims (2 for) · 1 study (1 causal), q3 · 1 of 1 report an effect size · 2 claims rest on one study

Description¶

The article proposes that AI and human educators need not perform identical instructional work: "AI agents may be especially useful for repetitive practice, consistent role-play, checklist monitoring, Socratic prompting, and the generation of preliminary formative feedback," while faculty and human standardized patients contribute contextual interpretation, nuanced emotional response, individualized remediation, and judgments about learner readiness. On this account, partial substitution is acceptable only for specific, bounded tasks, with the boundary set by error consequences, task uncertainty, relational sensitivity, and availability of human review.

Design Implications¶

Context¶

Requirements¶

meaningful human review of consequential judgments
AI systems that scaffold rather than substitute student reasoning

Constraints¶

the system should not autonomously determine whether a learner is clinically competent, make progression or credentialing decisions, or replace human-led remediation in emotionally or professionally complex cases

Target Learners¶

medical students in early clinical training

Learning Goals¶

simulated clinical interviewing
independent clinical reasoning
empathic communication

Claims¶

Examples¶

-

Key Sources¶

Yang, L., Liu, H., Li, S., Jia, R., Xiao, Y., Chen, G., & Lu, L. (2026). Evaluating Scaffolding-Oriented Multi-Agent Large Language Model System for Clinical Interview Training. https://arxiv.org/abs/2609.10939. doi:10.48550/arxiv.2609.10939

Page metadata

Field	Value
`type`	`design`
`id`	`functional-complementarity-ai-human-clinical-education`
`title`	`Functional complementarity model of AI and human roles in clinical skills education`
`description`	`The article proposes that AI and human educators need not perform identical instructional work: "AI agents may be especially useful for repetitive practice, consistent role-play, checklist monitoring, Socratic prompti...`
`status`	`review`
`generated`	by `process:settle-candidates` on `2026-10-10`
`trust`	unverified — no one has confirmed this page's content
`sources`	1 — `yang-2026`

Frontmatter is the page's machine-readable record — see the Schema & Guide.