Clinical Language Evaluation With AI for Residents (CLEAR2) - A Pilot Randomized Controlled Trial
试验速览
- 阶段
- 不适用
- 状态
- 尚未招募
- 发起方
- 入组人数
- 64
- 试验地点
- 1
- 主要终点
- Readability discernment as assessed by a survey
研究概览
简要总结
The purpose of this study is to refine and test existing enterprise-grade large language model (LLM) based on generative artificial intelligence (AI), to assess the feasibility and acceptability of LLM-based feedback, to assess the ability of LLM-based feedback to improve residents' communications,to explore the ability of standardized patients to assess residents' communication and to explore the ability of residents to self-assess their communication complexity
研究设计
- 研究类型
- Interventional
- 分配方式
- Randomized
- 干预模型
- Parallel
- 主要目的
- Other
- 盲法
- None
入排标准
- 年龄范围
- 18 Years 至 50 Years（Adult）
- 性别
- All
- 接受健康志愿者
- 是
入选标准
- •McGovern Medical School (MMS) general surgery residents
- •postgraduate year (PGY) 1-5
排除标准
- 未提供
研究组 & 干预措施
Educational LLM-based feedback tool
干预措施: educational LLM-based feedback tool (Behavioral)
Control
结局指标
主要结局
Readability discernment as assessed by a survey
时间窗: end of intervention ( 1 hour after baseline)
This will be scored by the by Cohen's Kappa values from 1-5. Higher Cohen's kappa scores mean better outcome
Perceived readability of resident-standardized patient (SP) interactions as assessed by a survey: schooling level
时间窗: end of intervention ( 1 hour after baseline)
This will be categorically reported in the following categories: Elementary middle high college graduate
Quality discernment as assessed by a survey
时间窗: end of intervention ( 1 hour after baseline)
This will be scored by the by Cohen's Kappa values from 1-5. Higher Cohen's kappa scores mean better outcome
Correctness of recommendations as assessed by a survey
时间窗: end of intervention ( 1 hour after baseline)
This will be reported on a 5 point Likert scale form 1 very incorrect to 5 very correct
Applicability of recommendations as assessed by a survey
时间窗: end of intervention ( 1 hour after baseline)
This will be reported on a 5 point Likert scale form 1 very inapplicable to 5 very applicable
confidence in communication ability
时间窗: end of intervention ( 1 hour after baseline)
This is scored from 1( very unconfident) to 5 (very confident)
usefulness of the LLM
时间窗: end of intervention ( 1 hour after baseline)
This is scored from 1( very useless) to 5 (very useful)
acceptability of future use
时间窗: end of intervention ( 1 hour after baseline)
This is scored from 1( very unlikely) to 5 (very likely)
次要结局
- Survey feedback on the LLM interface(end of intervention ( 1 hour after baseline))
- readability grade level of resident-SP transcripts as assessed by the Flesch-Kincaid Grade Level (FKGL) readability tool(end of intervention ( 1 hour after baseline))
- Quality based on Ensuring Quality Information for Patients (EQIP) score of resident-SP transcripts(end of intervention ( 1 hour after baseline))
- Perceived readability of SP-resident interactions as assessed by a standardized survey(end of intervention ( 1 hour after baseline))
- confidence in communication ability(end of intervention ( 1 hour after baseline))
研究者
Krislynn Michelle Mueck
Assistant Professor
The University of Texas Health Science Center, Houston