Handoffs and escalation
Make the transfer of responsibility a conversation you can examine
Last updated: October 2026
Residents and fellows practice transfer calls and disagreements between teams with AI characters who respond to what is said. Each conversation is scored against I-PASS, SBAR, or your institution's handoff policy, with the participant's own words under every score.
Who owns the handoff
Responsibility for a patient changes hands at every shift change, every transfer, and every call for help. GME offices answer for resident handoffs, nursing education for escalation, and patient safety teams review the safety events that involve a transfer of care. What none of them usually has is a record of how the conversation itself sounded.
The best-known evidence is for a bundled program. In a nine-hospital study of the I-PASS handoff program, which combined a mnemonic, handoff and communication training, faculty development and observation, and a sustainability campaign, the medical error rate fell from 24.5 to 18.8 per 100 admissions and preventable adverse events from 4.7 to 3.3, across 10,740 admissions (Starmer et al., New England Journal of Medicine, 2014).
Those results belong to that whole program. They are not evidence about ClinicalSim, and practice in simulation is one piece a program like that might include.
Conversations your teams can practice
Each is a published case in the ClinicalSim catalog. The AI character on the other end responds to how clearly the participant states severity, the plan, and what to watch for.
Floor-to-ICU Transfer During Clinical Deterioration (Pediatric)
A pediatric floor resident calls a tired, rushed PICU fellow at shift change to transfer an 8-year-old with pneumonia who has deteriorated into septic shock. The case asks for a safe, structured handoff.
ICU Transfer Handoff for Rapidly Deteriorating Septic Shock (Adult)
An internal medicine resident calls the MICU at evening sign-out about a 67-year-old with urosepsis who is still hypotensive after fluids and antibiotics, with transport ten minutes away. The case is scored on I-PASS principles, starting with illness severity.
Escalation Disagreement Between PICU and Pediatric Surgery Teams
A PICU fellow who wants urgent surgery for an 11-year-old with perforated appendicitis talks with a pediatric surgery fellow who favors antibiotics and drainage first. The teams disagree, and the conversation has to reach a plan.
What a program gets
Participants get feedback they can use on the next attempt, while programs review agreed individual or cohort views.
Your handoff tool, scored as written
Send the I-PASS adaptation, SBAR template, or escalation policy your institution teaches. The report scores each element the case gave the participant a chance to show.
The words behind every score
Each rating quotes what the participant said, so an educator can see whether illness severity and the contingency plan were stated without replaying the call.
On demand, not on schedule
Voice-based AI patient encounters available 24/7 from any device. No standardized patient to recruit, no sim center to book, no faculty observer required to practice.
A program view for coaching
Review repeated practice and transcript-linked feedback by participant or cohort, with institution-defined access, so coaches can see strengths and choose the next practice focus.
The frameworks behind the score
Each AI patient case names the published framework or institution-defined standard used for feedback. The report shows strengths and areas for practice, with the participant's own words behind each score.
I-PASS: Handoff communication
I-PASS Study Group and Agency for Healthcare Research and QualityIllness severity, patient summary, action list, situation awareness and contingency planning, and synthesis by the receiver structure a handoff.
SBAR: Structured communication
Agency for Healthcare Research and Quality, TeamSTEPPSSituation, background, assessment, and recommendation structure a concise clinical escalation or handoff.
Your own handoff or escalation policy
YoursSend the policy or tool your institution already teaches. We use its element definitions as written.
How scoring against a framework works, including the scope rule
Frequently asked questions
Does handoff practice in ClinicalSim reduce medical errors?
No study shows that. The I-PASS results come from a bundled program in nine hospitals that combined a mnemonic, training, faculty observation, and a sustainability campaign (Starmer et al., New England Journal of Medicine, 2014). ClinicalSim scores a simulated handoff against the tool you teach and gives participants another attempt.
Can a ClinicalSim score be used in an incident review?
No. A finding from these conversations can justify education, a workflow change, or further investigation. It never establishes the cause of an incident, and practice scores stay formative.
Who plays the receiving clinician or the other team?
An AI character the participant talks to by voice. Our clinical team writes each case, including how the character reacts when a handoff leaves out severity or a disagreement goes unresolved.
Can we score against our own handoff tool?
Yes. Send the I-PASS adaptation, SBAR template, or escalation policy you use. The report scores the elements a case gave the participant a chance to show and quotes the words behind each score.
Key terms
What this page does not claim
ClinicalSim is not endorsed by, affiliated with, or approved by the I-PASS Study Group or AHRQ. Scores map to published frameworks; they do not establish compliance with any standard, which a surveyor determines against the institution's own policy.
ClinicalSim output is formative. It is evidence that informs program judgment, and it is not intended for employment, credentialing, privileging, licensure, or other high-stakes decisions.
Consistency between model runs is not the same thing as agreement with expert human raters. Faculty-rater validation on a customer's own rubric is the gate before any high-stakes use, and that work has not been done.
ClinicalSim does not predict patient experience scores, readmissions, safety events, claims, or other clinical or business outcomes. Any comparison with institution-held outcome data requires a separate study plan.
Formative scores must not be used for employment decisions, discipline, compensation, credentialing, privileging, or licensure. Institutions should set access, retention, and reporting rules before staff participate.
A finding from these conversations can justify education, a workflow change, or further investigation. It never establishes the cause of an incident. The I-PASS results cited on this page describe a bundled program and are not evidence about ClinicalSim.