Teaching Doctors in Training to Reason With Artificial Intelligence (TEACH-AI)
Teaching Internal Medicine and Family Medicine Residents to Reason With Generative AI: A Multi-Site Randomized Controlled Trial (TEACH-AI)
The purpose of the TEACH-AI study is to assess whether a brief, structured workshop on artificial intelligence can improve the performance of medicine doctors in training (i.e. residents) in their diagnostic and management reasoning.
In this multi-site randomized controlled trial, internal medicine and family medicine residents are assigned either to receive an in-person workshop on safe, effective LLM use before a standardized AI-assisted assessment, or to complete the same assessment before receiving the workshop. Residents will review clinical cases that are fully synthetic, no protected health information is used, using a password protected LLM interface.
연구 개요
상세 설명
Large language models (LLMs) have rapidly entered routine use in medical education and clinical practice. Prior randomized trials have shown that, although LLMs can outperform individual clinicians on some reasoning benchmarks, providing physicians with access to an LLM does not necessarily improve their diagnostic or management performance, and LLMs alone may perform better than physician-plus-LLM teams. These findings suggest that human-AI collaboration is fraught, non-trivial and may require explicit training.
TEACH-AI is a pragmatic, multi-site, two-arm randomized controlled trial embedded within protected residency didactic time. The primary objective is to determine whether a single in-person workshop on the basics of LLMs and best practices of prompting/verification strategies improves residents' performance on an AI-assisted assessment, compared with residents who complete the simulation before receiving the workshop. All participants will ultimately receive the same workshop and the same assessment (either workshop-first vs assessment-first).
The simulation consists of multiple fully synthetic vignettes delivered via a password protected LLM interface. Residents interact freely with the LLM using natural-language prompts and then submit structured final responses regarding aspects such as leading diagnosis, differential, management plan, and/or justification. The platform will record prompts, model outputs, final answers, and timing. Vignette scoring combines correctness of the final diagnosis or management plan. Scoring is conducted by blinded faculty using standardized rubrics and then any discrepancies will be resolved through multiple rounds of discussions.
The trial will enroll up to 200 residents across four ACGME-accredited programs (internal medicine at Beth Israel Deaconess Medical Center, Stanford University, and Cambridge Health Alliance; family medicine at AdventHealth Orlando).
연구 유형
등록 (추정된)
단계
- 해당 없음
연락처 및 위치
연구 연락처
- 이름: Jacob M Koshy, MD, MPH
- 전화번호: 617-754-4677
- 이메일: jkoshy@bidmc.harvard.edu
연구 장소
-
-
California
-
Palo Alto, California, 미국, 94305
- Stanford University
-
연락하다:
- Kevin Keet, MD
- 전화번호: 650-498-4559
- 이메일: kkeet@stanford.edu
-
수석 연구원:
- Kevin R Keet, MD
-
-
Florida
-
Orlando, Florida, 미국, 32804
- AdventHealth
-
연락하다:
- Raj Mehta, MD
- 전화번호: 407-845-8383
- 이메일: raj.mehta.md@adventhealth.com
-
수석 연구원:
- Raj Mehta, MD
-
-
Massachusetts
-
Boston, Massachusetts, 미국, 02215
- Beth Israel Deaconess Medical Center
-
연락하다:
- Jacob M Koshy, MD, MPH
- 전화번호: 617-754-4677
- 이메일: jkoshy@bidmc.harvard.edu
-
수석 연구원:
- Jacob M Koshy, MD, MPH
-
Cambridge, Massachusetts, 미국, 02139
- Cambridge Health Alliance
-
연락하다:
- Priyank Jain, MD
- 전화번호: 617-665-1000
-
수석 연구원:
- Priyank Jain, MD
-
-
참여기준
자격 기준
공부할 수 있는 나이
- 어린이
- 성인
- 고령자
건강한 자원 봉사자를 받아들입니다
설명
Inclusion Criteria:
- Participants must be licensed physicians and have started at least post-graduate year 1 (PGY1) of medical training.
- Training in Internal medicine or family medicine or emergency medicine.
- Able to provide informed consent and complete assessments in English.
Exclusion Criteria:
- Not currently practicing clinically.
- Resident directly involved in the design of the study, development of the workshop, or creation/piloting of the assessment vignettes.
- Resident who declines or withdraws consent.
공부 계획
연구는 어떻게 설계됩니까?
디자인 세부사항
- 주 목적: 특수 증상
- 할당: 무작위
- 중재 모델: 병렬 할당
- 마스킹: 하나의
무기와 개입
참가자 그룹 / 팔 |
개입 / 치료 |
|---|---|
|
간섭 없음: Assessment-First
Participants assigned to this group will be tasked with completing the assessment using a password protected LLM interface first in advance of the workshop.
The workshop will be delivered during a scheduled mandatory didactic time slot.
|
|
|
실험적: Workshop-first
Participants assigned to this group will be tasked with completing the assessment using a password protected LLM interface after they participate in a scheduled mandatory didactic time slot.
|
Participants will attend a workshop during their didactic time that will review various aspects of large language models including fundamentals and best practices of interacting and interpreting their outputs.
|
연구는 무엇을 측정합니까?
주요 결과 측정
결과 측정 |
측정값 설명 |
기간 |
|---|---|---|
|
Total Score on Expert-Development Rubrics
기간: Within 24 hours of assessment completion.
|
The primary outcome will be the number of correct responses for all cases using select questions from expert-developed scoring rubrics.
The rubrics were developed using a Delphi consensus process by expert physicians as established by Goh et al (Nature Medicine, 2025; DOI: 10.1038/s41591-024-03456-y). The primary outcome will be analyzed at the case level, comparing performance between the randomized study groups, with a higher number of correct responses indicating a better outcome.
|
Within 24 hours of assessment completion.
|
2차 결과 측정
결과 측정 |
측정값 설명 |
기간 |
|---|---|---|
|
Time Spent on Management
기간: Within 24 hours of assessment completion.
|
Comparison of time spent per case between the two study groups.
|
Within 24 hours of assessment completion.
|
|
Prompt Count
기간: Within 24 hours of assessment completion.
|
Comparison of the number of resident-initiated prompts to the LLM per case between the two study groups.
|
Within 24 hours of assessment completion.
|
|
Management Reasoning Using Expert-Derived Rubrics
기간: Within 24 hours of assessment completion.
|
Comparison of management reasoning accuracy based on the number of correct responses per case between the two groups on expert-developed scoring rubrics.
The rubrics were developed using a Delphi consensus process by expert physicians as established by Goh et al (Nature Medicine, 2025; DOI: 10.1038/s41591-024-03456-y). The primary outcome will be analyzed at the case level, comparing performance between the randomized study groups with more correct responses indicating a better outcome.
|
Within 24 hours of assessment completion.
|
|
Diagnostic Reasoning
기간: Within 24 hours of assessment completion.
|
Comparison of diagnostic reasoning accuracy based on the number of correct responses per case between the two groups.
|
Within 24 hours of assessment completion.
|
공동 작업자 및 조사자
연구 기록 날짜
연구 주요 날짜
연구 시작 (추정된)
기본 완료 (추정된)
연구 완료 (추정된)
연구 등록 날짜
최초 제출
QC 기준을 충족하는 최초 제출
처음 게시됨 (실제)
연구 기록 업데이트
마지막 업데이트 게시됨 (실제)
QC 기준을 충족하는 마지막 업데이트 제출
마지막으로 확인됨
추가 정보
이 연구와 관련된 용어
기타 연구 ID 번호
- 2026P000369
- 63901784-350738 (기타 보조금/기금 번호: Macy Foundation)
개별 참가자 데이터(IPD) 계획
개별 참가자 데이터(IPD)를 공유할 계획입니까?
약물 및 장치 정보, 연구 문서
미국 FDA 규제 의약품 연구
미국 FDA 규제 기기 제품 연구
이 정보는 변경 없이 clinicaltrials.gov 웹사이트에서 직접 가져온 것입니다. 귀하의 연구 세부 정보를 변경, 제거 또는 업데이트하도록 요청하는 경우 register@clinicaltrials.gov. 문의하십시오. 변경 사항이 clinicaltrials.gov에 구현되는 즉시 저희 웹사이트에도 자동으로 업데이트됩니다. .