Patient understanding
Understand how clearly your teams explain what happens next
Last updated: October 2026
Residents and fellows explain a discharge plan, a procedure, or a change in care to an AI patient or parent. The report scores the explanation and the check of understanding against teach-back or your own standard, with the clinician's words under every score.
Who owns the explanation
Every discharge, procedure, and change of plan ends with someone explaining what happens next. Nursing education, patient experience, and the residency programs that staff the floors each own part of that conversation. The usual check, "Do you have any questions?", invites a polite yes, and AHRQ's Health Literacy Universal Precautions Toolkit says plainly that yes-or-no questions are not teach-back.
The published evidence points at the end of the conversation. When 90 preoperative conversations were recorded and scored, surgeons reliably described the illness, the operation, and the complications, and were least likely to check whether the patient had understood any of it (Journal of the American College of Surgeons, 2021). Adult spinal deformity patients who received both a verbal and a video risk discussion recalled a median 45% of the risks immediately afterward and 18% at six to eight weeks (Spine, 2015, n=56).
Limited English proficiency raises the stakes. A parent who says okay to avoid asking questions in English can leave with a plan nobody confirmed she understood, and one of the cases below is written around exactly that parent.
Conversations your teams can practice
Each is a published case in the ClinicalSim catalog. The AI patient or parent responds to how clearly the clinician explains and whether they check what landed.
Limited English Proficiency Discharge Counseling After PICU Asthma Admission
A pediatric resident counsels a mother who primarily speaks Spanish and has declined an interpreter, two hours before her 6-year-old goes home on a controller and a rescue inhaler. The resident covers the medications, return precautions, and follow-up in a way she can understand.
Informed Consent Discussion for Central Venous Catheter Placement in the PICU
A PICU fellow explains a central line to the anxious mother of a 5-year-old in septic shock. She is a medical assistant who knows what an IV is but not why a central line is different, and the case asks the fellow to confirm her understanding with teach-back.
PICU escalation
A pediatric hospital medicine fellow tells the mother of a 4-year-old with severe cerebral palsy, who speaks limited English, that her son needs to move to the intensive care unit, and works toward a shared understanding of the plan.
What a program gets
Participants get feedback they can use on the next attempt, while programs review agreed individual or cohort views.
Teach-back scored when the case asks for it
When your standard includes teach-back, the report scores whether the clinician asked for the patient's own account and quotes the question they used.
Your discharge standard, scored as written
Send the discharge teaching standard or script your units use. The rubric scores each element a case gave the clinician a chance to show.
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.
Teach-back
Agency for Healthcare Research and QualityThe listener explains the information back in their own words, so the speaker can check what landed and correct what didn't.
Your own discharge or procedure teaching standard
YoursSend the standard, script, or checklist your units already teach. We use its element definitions as written.
How scoring against a framework works, including the scope rule
Frequently asked questions
Does ClinicalSim measure what a real patient understood?
No. ClinicalSim scores the simulated conversation: whether the clinician explained the plan in plain language and checked understanding the way the case and your standard ask. It does not measure what a real patient later understood, remembered, or did after discharge.
Can a case include a patient or parent with limited English proficiency?
Yes. The asthma discharge case is written around a mother with limited English proficiency who has declined an interpreter. The conversation itself runs in English, because ClinicalSim is English only, so the case practices plain language and checking understanding rather than working through an interpreter.
Why practice teach-back if clinicians already know the method?
Knowing the method and asking for the patient's own words at the end of a busy explanation are different things. AHRQ's toolkit warns that "Do you understand?" and "Does that make sense?" invite a yes whether or not the patient understood. A scored practice conversation shows which question the clinician actually asked.
What can a finding from these conversations justify?
A finding can justify education, a workflow change, or further investigation. It never establishes the cause of an incident, and scores from practice conversations stay formative.
Key terms
What this page does not claim
ClinicalSim is not endorsed by, affiliated with, or approved by AHRQ or the American College of Surgeons. 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, and it does not measure what a real patient understood after discharge.