Emergency Assessment
Practise a psychiatric emergency assessment, from first contact to plan
Three emergency presentations, two of them with relatives to interview. The patients are AI-simulated: an AI language model plays each one from a case written by clinicians. You take the history, assess risk, gather collateral, form a mental state examination and formulation, and give your plan.
Browsing is open. Starting a conversation needs a free account, and signing up takes under a minute.
Who you can meet
- Carl Eriksson, 22
- Daniel Svensson, 27
- Alex, 41
- Tiina Koskinen, 44
What you practise
- Conduct a comprehensive psychiatric history in an emergency setting
- Perform a structured suicide risk assessment including risk and protective factors
- Formulate a mental status examination based on clinical interview
- Develop differential diagnoses with clinical reasoning
- Create a biopsychosocial formulation and management plan
- Communicate assessment and plan to patients using clear, compassionate language
Who it is for
Doctors in psychiatry, residents on call and medical students on placement.
Feedback while you practise, and on the whole conversation
During the conversation you get a short tip after your replies on what to keep and what to try next. After the conversation, with an account, an AI supervisor reads the whole conversation and writes you a review: one thing to practise, moments replayed with a reply to try instead, what to keep and rethink, how the patient reacted, and what to read.
What the feedback looks at
- Comprehensiveness
- Clinical reasoning
- Rapport and empathy
- Communication clarity
- Risk assessment
- Formulation and plan
- Pacing and structure
- Clarity and accessibility
Read the feedback as suggestions to think over. An AI model can misread a moment, so weigh it against your own judgement and take what matters to a supervisor or colleague.
Built on: Standard teaching on the psychiatric interview and the mental state examination, and NICE guidance on self-harm, which advises against risk scales for prediction.
The feedback is produced by an AI model: training feedback, not a certificate of competence.
Deliberate practice: patients who adapt to your level
The lab follows how your replies land. When it goes well it suggests the next level, and when it gets hard, an easier one. A conversation you leave is kept for 30 days, your level is saved for each patient, and your reviews are saved so you can compare with last week.
Clinical lead: David Boardman, MD, psychiatrist
Frequently asked questions
- What does an emergency assessment session include?
- Meeting the patient, taking the history, assessing risk, gathering collateral from relatives, forming a mental state examination and formulation, and communicating the plan, with feedback at each stage.
- Who are the cases?
- Carl, 22, with a first episode of psychosis and his parents Ingrid and Thomas, and Daniel, 27, in a manic episode with his girlfriend Sarah as collateral.
- Does the lab teach a risk score?
- No. The feedback follows suicide-risk assessment guidance that rejects predictive risk scales, and looks at how risk and protective factors are explored.
This lab is for clinical training. The patient is generated by an AI language model from a written case; no real patient and no patient data are involved. Browsing is open; starting a session needs a free account.
For clinical decision support only. Not a substitute for professional judgment.