PACES Scenario Generator
A research pilot exploring whether AI-generated PACES scenario drafts — covering patient demographics, presenting complaint, personality and ICE — can meaningfully reduce the time burden on clinical examiners and scenario writers.
| Status | Pilot — active research |
| Exam context | MRCP Part 2 PACES — Practical Assessment of Clinical Examination Skills |
| Team | Adrian Cowell, Ehigie, Naomi E, Corey Briffa |
| Tech stack | Vite, React, TypeScript, Netlify, Claude AI |
| Live app | paces-generator-7b40ef.netlify.app |
The Challenge
PACES examinations require a substantial library of realistic simulated patient scenarios. Each scenario must specify a presenting complaint, relevant history, personality and affect, and — critically — the patient’s Ideas, Concerns, and Expectations (ICE): the structured framework that underpins the communication skills station.
Writing these from scratch is time-consuming, and recruiting clinical examiners for a full scenario-writing session is logistically difficult. The question this pilot set out to explore: can AI-generated drafts serve as a credible starting point, reducing the editing burden to something that fits within a shorter, more practical working session?
What the Tool Does
The generator takes a structured set of inputs and produces a complete scenario draft. Clinicians provide the clinical framing; the AI handles the narrative expansion.
Clinical inputs
- Scenario title
- Patient age & gender
- Presenting complaint
- Occupation
- Personality & affect
ICE framework
- Ideas — patient’s beliefs about their condition
- Concerns — worries or fears they hold
- Expectations — what they hope from the consultation
Try the App
The pilot build is live. Fill in the clinical parameters and generate a scenario draft in under a minute.
Open PACES Scenario Generator →Research Approach
The pilot is exploring a core question about examiner time and cognitive load: is it faster and more sustainable to edit a generated draft than to write a scenario from a blank page? The hypothesis is that AI pre-drafting lowers the barrier to scenario contribution — making it feasible for busy clinicians to engage in shorter, focused review sessions rather than extended writing workshops.
The research also considers quality: whether AI-generated ICE narratives are clinically plausible enough to serve as a meaningful starting point, or whether they require substantial reworking. Findings will inform whether a larger-scale deployment would offer a genuine efficiency gain.
Potential Next Steps
Depending on pilot findings, potential directions include a structured time-comparison study (draft-and-edit vs. write-from-scratch), expansion of the scenario parameter set to cover more PACES stations, and integration with existing scenario management or exam platform workflows.