People
The system serves medical learners, educators, and clinicians who need low-friction ways to rehearse patient communication without requiring live standardized patients every time.
NBME · Clinical AI · 2025
A virtual standardized patient system for practicing clinical conversations, surfacing communication patterns, and making patient-centered competence observable through repeatable AI roleplay.
At a Glance
People
The system serves medical learners, educators, and clinicians who need low-friction ways to rehearse patient communication without requiring live standardized patients every time.
Product
The product is an OSCE-style simulator with scenario-specific patient personas, text and voice interaction, transcript-aware dialogue, and structured formative feedback.
Problem
Clinical communication failures often happen inside the interaction: rushed pacing, missed emotion, jargon density, weak follow-up questions, and lack of repair when patients stop following.
Process
I moved from domain research to product scoping, scenario design, state architecture, LLM behavior control, clinician testing, and feedback-system iteration.
The goal was not simply to simulate a patient. It was to create a structured environment where communication patterns could become visible, discussable, and improvable.
Clinical communication is not a soft skill in this framing. It is observable clinical behavior under constraint: how a learner asks, listens, repairs, explains, manages uncertainty, and preserves patient autonomy while still gathering enough information to reason clinically.
Learner selects a scenario, enters a text or voice encounter, and practices under realistic patient constraints.
Personas vary by emotional state, cooperation, disclosure behavior, tone, and response style.
Evaluation turns transcript behavior into developmental language, not just a score.
In clinical environments, providers are trained to diagnose. They are not always trained to notice when the patient has stopped following the conversation, when discharge language is functionally unreadable, or when the interaction has become about throughput rather than understanding.
This was the lived problem that shaped the product: communication failure is often a predictable output of systems that reward speed, certainty, and documentation over trust, disclosure, and reflection.
Clinical language, rushed pacing, dense explanation, or unacknowledged uncertainty.
The intent may be competent, but the interaction fails.
Confusion, anxiety, guarded disclosure, low adherence, or emotional shutdown.
The outcome depends on what was understood, not only what was said.
Learners need a rehearsal environment for the interaction itself, not only another knowledge check.
OSCE-style simulation makes behavior visible.
I worked across product, research, design, and engineering: defining the simulation loop, building the functional prototype, testing with clinicians, and using those findings to adjust scenario fidelity, persona behavior, architecture, and feedback usefulness.
15 clinician user tests, persona validation, scenario complexity calibration, and feedback usability review.
0-to-1 lifecycle ownership, MVP scoping, feature prioritization, and feasibility testing.
State architecture, RAG implementation, LLM behavior control, and ASR / STT / TTS workflows.
The system only became reliable once scenario, patient, conversation, and evaluator states were separated. Without that separation, the model's default helpfulness caused the patient persona to drift into advice-giving or clinician-like behavior.
Defines the clinical prompt, task frame, OSCE-style requirements, patient overview, and encounter setup.
Independent from persona behavior.
Maintains emotion, cooperation, disclosure pattern, tone, and role fidelity throughout the encounter.
No evaluator rubric access.
Stores visible turn-taking, transcript context, learner messages, patient responses, and voice/text interaction state.
Transcript-aware dialogue.
Assesses the full session after the encounter using clinical, communication, and professionalism criteria.
Post-session formative feedback.
The key architecture insight: helpfulness and role-persistence are in tension. Training simulation needs explicit boundaries around what each model state knows and when it is allowed to act.
Each patient persona is defined by emotional state and cooperation level. Those variables are not decorative traits; they control disclosure, response length, resistance, tone, and whether the clinician has to earn the information needed for diagnosis.
A low cooperation score does not mean the session is impossible. It means the clinician's communication quality becomes the variable that unlocks the encounter.
Anxious, fearful, annoyed, frustrated, demotivated, blunt, or otherwise distressed in ways that affect dialogue.
A continuous behavioral scale that changes how easily the patient discloses information and stays on task.
Behavioral realism shows up through pacing, resistance, short answers, venting, and spoken delivery, not just text content.
The original build surfaced a core AI design problem: the model's helpfulness can become a simulation vulnerability. When patient and evaluator context were not separated, the faux patient began optimizing toward resolution, clarifying too much, or advising the clinician.
Patient accumulates evaluator context, model optimizes toward helpful resolution, and the patient persona begins behaving like a clinician. The simulation collapses because the test starts helping the learner pass.
Patient receives only the patient-relevant context, stays within persona, forces the clinician to adapt, and leaves evaluation to a separate post-session state.
Any AI system where role fidelity matters needs explicit architectural separation between what the model knows and what role it is currently playing.
More realism does not automatically create a better training system. If everything varies, evaluation becomes inconsistent and feedback loses meaning. The system chose evaluability as the constraint and realism as the target within it.
Variation, emotional nuance, unpredictable patient behavior, and clinical conversation texture.
Controlled variation, stable rubric language, comparable sessions, and feedback that remains useful across users.
Evaluation uses a hierarchy: clinical competency functions as the hard constraint, communication behavior is assessed as observable interaction quality, and dialogue quality captures tone, pacing, sequencing, and repair.
Given this patient and context, what should the clinician have noticed, asked, or repaired?
In this specific transcript moment, what alternative response would improve the interaction?
Across a session, what communication pattern is emerging and what should the learner practice next?
The reflections from the simulated patient and evaluator pointed toward a more mature product artifact: a shared language for what good communication means in a simulated encounter.
Reflects, summarizes, asks clarifying questions. Failure mode: premature advice.
Acknowledges uncertainty without losing clinical authority. Failure mode: false certainty.
Offers choice, asks permission, frames change collaboratively. Failure mode: compliance pressure.
Names emotion and validates fear, frustration, or resistance. Failure mode: efficiency theater.
Uses plain language, paces information, checks understanding. Failure mode: jargon dump.
Notices bias, fatigue, defensiveness, and premature closure. Failure mode: performative professionalism.
After the system had played both standardized patient and conversational evaluator, the reflections became a useful qualitative artifact. They named the latent dimensions the simulator was already trying to assess.
Patient satisfaction, adherence, disclosure, and trust depend on how clinicians listen, reflect, and explain, not only what they prescribe.
When communication is treated as an early-course checkbox, empathy decays. When it becomes a formal competency, behavior can improve.
Under time pressure, learners reveal what has been internalized: curiosity or checklist thinking, empathy or efficiency theater.
Autonomy before compliance, meaning before metrics. The simulator can make that difference observable in transcript behavior.
The deeper claim: if medicine wants fewer unheard patients, the answer is not only more content. It is better conversations, rigorously taught and repeatedly practiced.
The MVP shipped as a working simulator and was tested with 15 clinicians. The most important shift was not a prettier scorecard; it was a change in how clinicians structured questions, paced information, repaired confusion, and turned feedback into practice language.
Shipped a live clinical roleplay loop with scenario selection, transcript behavior, and formative feedback.
Used clinician sessions to evaluate realism, feedback usefulness, scenario fidelity, and role behavior.
Designed state separation, RAG-supported context, voice/text workflows, and evaluator isolation.
The project matured through a product loop: domain research, architecture decisions, prototype delivery, clinician testing, and a roadmap for longitudinal skill growth.
Literature and domain review established the gap between clinical knowledge assessment and patient-centered communication practice.
Communication training gap.
Scenario, patient, conversation, and evaluator states were separated to prevent role drift and evaluation leakage.
State separation.
Built the roleplay loop with persona behavior, transcript-aware dialogue, RAG-supported context, and structured feedback.
Shipped MVP.
Clinician sessions focused on realism, feedback usefulness, scenario fidelity, and communication behavior changes.
15 clinician tests.
Next iteration: profiles, saved evaluations, shared rubric language, deeper clinical complexity, and challenge scenarios.
Longitudinal progress.
Track clinician improvement across personas over time so growth becomes visible rather than session-by-session.
Create stable competency language across handoffs, coaching, and repeated encounters.
Increase diagnostic nuance without sacrificing evaluation consistency or turning the simulator into an unreliable assessment environment.
The simulator gives learners a low-friction way to practice patient communication without live standardized patients. Learners choose a patient scenario, interact through text or voice, and receive structured formative feedback at the end of the session.
The product direction keeps the original generic virtual-standardized-patient concept, then extends it with stronger case structure, transcript memory, optional voice workflows, prompt customization, and evaluation reporting.
OSCE-style practice is expensive, scheduled, and difficult to repeat. Basic chat demos are easier to access, but they often lack scenario fidelity, patient consistency, and useful evaluation. The product bridges those gaps with a lightweight simulation environment.
The MVP includes fixed scenarios with patient demographics, chief complaint, communication focus, description, allergies, medical history, medications, vital signs, and avatar image.
Scenario design should preserve role fidelity while allowing enough emotional and conversational variation for realistic practice.
Evaluation covers history taking, communication skills, rapport building, clinical reasoning, and professionalism, with overall score, grade, strengths, priority improvements, and specific recommendations.
The evaluation is formative, not credentialing. It should make patterns observable and give learners language they can practice against.