Agentic education · Learning science

Actionable companion · Feedback & scaffolding

Learning with agency: AI-generated Feedback Following Social Robotic Virtual Patient Interactions and Medical Student Performance: Nonrandomized Quasi-Experimental Study

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paperSearch paper agentCC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Higher education. Health-professions learning must be distinguished from K–12 instruction.

Original authors’ abstract, reproduced under the linked source license:

Background Virtual patients (VPs) demonstrate effectiveness in improving clinical reasoning skills; however, traditional VP platforms often lack individualized feedback mechanisms. Advances in large language models (LLMs) enable automated analysis of student-VP interactions, providing scalable feedback on clinical performance. While artificial intelligence (AI)–enhanced social robotic VP platforms show promise for clinical reasoning training, no studies have examined whether AI-generated feedback integrated in such platforms improves clinical performance in standardized assessments. Objective This study evaluated whether AI-generated postconsultation feedback integrated into social robotic VP interactions improves medical students’ clinical performance, emphasizing medical history taking and communication. Methods A quasi-experimental study with 115 sixth-semester medical students (N=157, 73.2% of eligible students) was conducted at Karolinska Institutet, Stockholm, Sweden, during spring 2025. Students were allocated by hospital site to receive (n=61, 53%) or not receive (n=54, 46.9%) AI-generated feedback following interactions with a Social AI-Enhanced Robotic Interface. All students completed 9 VP cases; the intervention group received approximately 1 page of structured feedback after each VP case. The feedback system used multiple LLMs following a 2-stage algorithm: assessing student-VP dialogues using an assessment rubric, then generating structured feedback on history-taking performance. Both groups participated in case-specific follow-up seminars led by consultant rheumatologists following each VP encounter. Clinical performance was assessed through an 8-minute objective structured clinical examination (OSCE)-based evaluation, with a standardized patient portraying axial spondylarthritis, evaluated by a blinded consultant rheumatologist using a 10-point rubric across 5 domains: communication at consultation start, generic medical history, targeted medical history, diagnostics and management reasoning, and communication at consultation end. Results Students receiving AI-generated feedback achieved significantly higher total OSCE scores (mean 7.39, SD 0.86 vs mean 6.68, SD 1.04 points; mean difference 0.70; 95% CI 0.35-1.06; P<.001; Cohen d=0.74). Domain-specific analysis revealed significant improvement in generic medical history after Bonferroni correction (mean 2.46, SD 0.65 vs mean 2.03, SD 0.79 points; P=.004; r=0.27), while other domains showed no significant differences: communication at start (P=.13; r=0.14), targeted medical history taking (P=.60; r=0.05), diagnostics and management (P=.14; r=0.14), and communication at consultation end (P=.31; r=0.09). Pass rates were significantly higher in the feedback group (96.7% vs 79.6%; odds ratio 7.55, 95% CI 1.51-72.2; P=.006), with a number needed to assess of 6 students, that is, for every 6 students receiving feedback, 1 additional student passed the assessment. Conclusions AI-generated feedback following social robotic VP interactions significantly improved medical students’ OSCE-based performance, particularly in generic medical history taking. These findings support integrating validated AI feedback systems as a supplement to expert-led teaching during VP simulations for clinical training and demonstrate the feasibility of scalable, automated feedback in medical education. The domain-specific improvements in generic medical history highlight the importance of targeted, competency-specific feedback design in VP platforms.

What kind of evidence is this?

Embodied learning agents · Randomized study reported

Stage: Higher education. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Study methods · source passage

We conducted a quasi-experimental study to evaluate whether AI-generated feedback following social robotic VP interaction improves medical students’ clinical performance in medical history taking. The study was conducted at Karolinska Institutet, Stockholm, Sweden, during spring 2025, following the Transparent Reporting of Evaluations with Nonrandomized Designs reporting guidelines [26].

Limitations and uncertainty · source passage

The quasi-experimental design with sequential allocation may have introduced selection bias, although baseline characteristics were well balanced between groups. Assessment was limited to 1 OSCE-based rheumatology evaluation, potentially limiting generalizability to other clinical settings and specialties. Although the coauthors portrayed standardized patients, the consultant rheumatologist assessors were blinded to intervention status, minimizing potential bias. Furthermore, there were no statistically significant differences in grading between the assessors, indicating that the standardized OSCE rubric and the clear instructions mitigated the risk of subjectivity for the intended purpose. The single-institution design and use of English for VP interactions and feedback while conducting assessments in Swedish may affect the external validity and represent methodological considerations for future research. Although a statistically significant benefit was only observed in the generic medical history–taking domain, the AI-generated feedback group showed numerical advantages in most assessment domains. This pattern suggests that the study may have been underpowered to detect smaller effect sizes in secondary outcomes. Alternatively, a ceiling effect may have contributed, as both groups generally performed well across other areas of the evaluation rubric.

Design the system before the pilot

Compare the embodied interaction with an equivalent human-led or screen-based activity. Separate the effects of novelty and social presence from learning. Review physical access, sensory needs and adult supervision.

  • Give feedback on the learner’s reasoning, then fade hints. Record whether the learner can complete the next task without that scaffold.
  • Use common rubrics, blind scoring where feasible and a fresh unaided reasoning task. Document permissible assistance and avoid treating AI-detector scores as proof of misconduct.

A 90-day district pilot

  1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
  2. Days 16–30 · Design. Choose one disciplinary task. Require a first attempt, a documented AI consultation, a critique of the output and an independent explanation. Align the comparison group and scoring rubric with the same objective. Name an accountable owner and set the baseline, success threshold and budget before implementation.
  3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
  4. Days 61–90 · Decide. Blind-score reasoning and accuracy on a new task without AI. Distinguish model examination scores, student perceptions and actual learner gains; only the last directly tests educational benefit. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Alexander Borg; Jonathan Schiött; William Ivegren; Cidem Gentline; Viking Huss; Anna Margareta Hugelius; Benjamin Jobs; Mini Ruiz; Samuel Edelbring; Carina Georg; Gabriel Skantze; Ioannis Parodis. AI-generated Feedback Following Social Robotic Virtual Patient Interactions and Medical Student Performance: Nonrandomized Quasi-Experimental Study. JMIR Medical Education (2026-03-25). https://doi.org/10.2196/90368

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.