Skip to main content
ClinicalSim

Goals of care

Goals of care conversation practice with AI patients

A goals of care conversation asks a clinician to find out what matters to a patient or family and to recommend care that fits it. Clinicians practice that conversation out loud with an AI patient or family member, and each report scores it against REMAP, the Serious Illness Conversation Guide, or your own standard, with the clinician's words quoted under every score.

Last updated: November 2026

What a goals of care conversation asks of a clinician

Goals of care are the overarching aims of medical care for a patient, informed by the patient's values and priorities and used to guide decisions about specific medical interventions. That definition comes from a review of 214 texts in the healthcare literature (Secunda et al., Journal of General Internal Medicine, 2020).

This is a different conversation from delivering serious news. Serious news is something the patient or family did not know, and SPIKES is the usual structure for telling them. A goals of care conversation comes after the family knows where things stand, and the clinician's work is to ask what matters, listen to the answer, and recommend a plan that fits it.

A hospital comparing goals of care training can ask three questions: which published structure it teaches, such as REMAP or the Serious Illness Conversation Guide, how often each clinician says the words out loud, and whether the feedback quotes what the clinician said.

Workshops and standardized patient sessions teach the structure, and they stay part of the training. Clinicians add repetitions with AI patients between those sessions, so they have asked the question out loud before they ask it at a bedside. Extend your SP program, don't replace it.

How a ClinicalSim goals of care case works

  1. Choose the case The program picks or approves a case, including who the patient is, who the clinician will talk to, and which framework the conversation is scored against.
  2. Talk to the AI patient or family member The clinician opens the case in a browser and speaks out loud to the AI patient or family member.
  3. Respond to what happens The patient or family member answers in character, with questions, emotion, and silence, so the clinician has to listen and adjust as the conversation moves.
  4. Read the report The clinician gets a report with strengths, next steps, and a score for each framework step, each one backed by quoted lines from the transcript.
  5. Repeat and review The clinician runs the case again, and can share the report with a coach or educator to choose the next focus.

Scored against the framework your teams already use

Each case names the framework it is scored against. A health system can add its own standard, and it gets its own score.

FrameworkWhat it coversWhat the report shows
REMAP (Childers et al., 2017)Reframe the situation, expect emotion, map the future, align with values, and plan treatment around those valuesA score from 1 to 5 for each step with the clinician's words behind it. Both published examples use REMAP.
Serious Illness Conversation Guide (Ariadne Labs)Setup, understanding and information preferences, prognosis, goals and tradeoffs, and a recommendation with follow upA score for each step, with the clinician's words quoted. Neither published example uses this guide yet.
NURSE (VitalTalk)Naming, understanding, respecting, supporting, and exploring emotionWhich of the five responses the clinician used and where, with their words quoted. NURSE responses are reported, not scored.
Your own standardThe serious illness or family meeting model your system already teachesA separate score, kept apart from the published frameworks
Scored against the framework your teams already use

One REMAP step from a published report

In the osteosarcoma example, the report scored step P, the plan, at 4 out of 5 (Very good). This is one of the lines it quoted as evidence.

"there's also another option, which is to briefly put a needle in, take out the fluid so that she's immediately more comfortable"

From the example report Goals of care in progressive osteosarcoma

The same report gave the clinician a next step for mapping the future: ask the father directly what matters most to him and what worries him most for his daughter.

Goals of care and family meeting cases in the ClinicalSim catalog

A health system can also ask for a case written for its own units and roles, and physicians review every case before release.

ConversationCaseWho the clinician talks to
Goals of careGoals of Care Discussion in Progressive Respiratory FailureThe daughter and decision maker of a 76-year-old man on a ventilator, whose brother sees their father's wishes differently
Goals of careGoals of Care for a Medically Complex Child With Worsening Respiratory FailureA mother who worries the team is giving up on her son
Goals of carePICU Goals of Care Discussion for Severe Neurologic InjuryA mother who asked to meet about her son's prognosis and code status
Family meetingPediatric Polytrauma: Urgent Family Meeting: PEMA father who knows only that his son was in a car accident
Goals of care and family meeting cases in the ClinicalSim catalog

Browse the full catalog

What clinicians and leaders see

  • Each clinician gets a report with strengths, a next step, and a score for each framework step, with the transcript lines behind it.
  • Clinicians can repeat a case in private before sharing a report with a coach or educator.
  • Leaders review participation and patterns across a cohort or unit, under access roles the institution sets before launch.

What ClinicalSim doesn't do

  • Practice is simulated. ClinicalSim doesn't record or monitor real patient or family conversations.
  • Feedback is formative. It isn't for credentialing, privileging, or employment decisions.
  • Scores come from the transcript of what the clinician said. Tone of voice isn't scored.
  • Practice with AI patients extends workshops and standardized patient programs. It doesn't replace them.
  • Practice is audio only and in English for now.

Frequently asked questions

What is the best communication training for difficult goals-of-care conversations?

The answer depends on what your clinicians already have, and this page doesn't claim that one program is best. Three questions help when comparing options: which published structure the training teaches, such as REMAP or the Serious Illness Conversation Guide, how often each clinician says the words out loud, and whether the feedback quotes what the clinician said. Clinicians get the spoken practice and the quoted feedback from ClinicalSim, alongside the workshop that teaches the structure.

Which frameworks are goals of care conversations scored against?

Each case names its framework. Both published goals of care examples are scored against REMAP (Childers et al., Journal of Oncology Practice, 2017), and one also reports NURSE responses to emotion without scoring them. The other is also scored against SPIKES. The Serious Illness Conversation Guide from Ariadne Labs is available too, and a health system can add its own standard, which is reported separately.

Is a goals of care conversation the same as delivering serious news?

No. Delivering serious news means telling a patient or family something they did not know, and those cases are scored against SPIKES. A goals of care conversation asks what matters to the patient and then recommends care that fits, and those cases are scored against REMAP or the Serious Illness Conversation Guide. One family meeting can call for both, so ClinicalSim has a separate use case for serious news practice.

Can clinicians practice a family meeting?

Yes. The catalog includes Pediatric Polytrauma: Urgent Family Meeting and Goals of Care Discussion in Progressive Respiratory Failure, and in each one the clinician talks with a family member of the patient. The AI family member answers in character, and the report quotes the clinician's words under each score.

Does this replace our serious illness communication workshop?

No. Workshops and standardized patient sessions teach the structure and give live coaching. Practice with AI patients adds repetitions between those sessions, so a clinician can rehearse a goals of care conversation again in a browser and bring the report to a coach. Extend your SP program, don't replace it.

Who sees a clinician's results?

The access roles your institution sets before launch decide who sees each report. Clinicians can repeat a case in private before sharing a report with a coach or educator. Practice scores are formative and must not be used for employment, credentialing, or privileging decisions.

Is there evidence that practice improves real goals of care conversations?

This page makes no outcome claim. Studies of ClinicalSim are underway at partner institutions, and their outcomes publish only after the study owners confirm the record in writing. The evidence page explains what supports spoken practice with feedback, and the research page shows what has been presented so far.

References

  1. Secunda K, Wirpsa MJ, Neely KJ, Szmuilowicz E, Wood GJ, Panozzo E, McGrath J, Levenson A, Peterson J, Gordon EJ, Kruser JM. Use and meaning of "goals of care" in the healthcare literature: a systematic review and qualitative discourse analysis. Journal of General Internal Medicine, 35(5), 1559-1566. 2020. doi:10.1007/s11606-019-05446-0
  2. Childers JW, Back AL, Tulsky JA, Arnold RM. REMAP: a framework for goals of care conversations. Journal of Oncology Practice, 13(10), e844-e850. 2017. doi:10.1200/JOP.2016.018796
  3. Ariadne Labs. Serious Illness Conversation Guide. Ariadne Labs, Serious Illness Care Program. 2023.

What this page does not claim

ClinicalSim is not endorsed by, affiliated with, or approved by Ariadne Labs, VitalTalk, the authors of REMAP, or the authors of SPIKES. 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.

The scores describe a simulated conversation. This page makes no claim that practice changes how a clinician leads a goals of care conversation with a real patient or family, or the care that follows.

A question for leadersWhere do your clinicians first ask a family what matters most, out loud?

See a goals of care case run end to end

We'll walk through a case, the framework it is scored against, and the report a clinician sees after each attempt.