Prospective Randomized Controlled Trial to Evaluate Locally Implemented Large Language Models (LLMs) for Simplifying Patient Communication in Hematology and Oncology
试验速览
- 阶段
- 不适用
- 状态
- 招募中
- 发起方
- 入组人数
- 150
- 试验地点
- 1
- 主要终点
- Patient Comprehension Score
研究概览
简要总结
This study tests whether patients with blood cancer or other cancers better understand their medical information when it is rewritten in plain language by an artificial intelligence (AI) system.
When patients are discharged from the hospital, they receive a medical letter summarizing their diagnosis, treatment, and next steps. These letters are often written in technical language that is difficult for patients to understand. In this study, an AI language model running on the hospital's own secure servers rewrites parts of this letter into simpler language. A physician checks the simplified version before the patient receives it.
Patients are randomly assigned to one of two groups. One group receives both the standard medical letter and the AI-simplified version. The other group receives the standard letter only. A separate group of patients who do not speak German well will receive a simplified and translated version.
After reading their letter, all participants fill out a short questionnaire about how well they understood the information. The study takes place at TUM University Hospital (Klinikum rechts der Isar) in Munich, Germany.
详细描述
Background:
Studies show that up to 40-80% of medical information conveyed during physician consultations is not correctly recalled or understood by patients. This problem is particularly relevant in hematology and oncology, where treatment regimens, prognoses, and side-effect profiles are complex. Large language models (LLMs) have demonstrated the ability to convert medical texts into plain language with high accuracy. However, prospective randomized controlled trials evaluating the clinical benefit of LLM-simplified patient synopses in routine care are lacking.
Study Design:
Prospective, single-center, randomized controlled trial with parallel group design. Randomization is 2:1 (intervention : control) using permuted blocks of variable size (4-6). An additional non-randomized translation arm enrolls patients with insufficient German language proficiency.
Intervention:
研究设计
- 研究类型
- Interventional
- 分配方式
- Randomized
- 干预模型
- Parallel
- 主要目的
- Health Services Research
- 盲法
- Single (Participant)
盲法说明
Blinding of participants and care providers is not possible, as the intervention group receives a visibly additional simplified synopsis. Questionnaire data are analyzed blinded to group assignment.
入排标准
- 年龄范围
- 18 Years 至 —（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •Age 18 years or older
- •Inpatient of the Department of Medicine III (Hematology/Oncology) at TUM University Hospital (Klinikum rechts der Isar), Munich, Germany
- •Receipt of a discharge letter including the sections Current Status, Medical History, Epicrisis, and Further Management as part of routine clinical care
- •Capacity to provide informed consent
- •Written informed consent following the consent procedure
排除标准
- •Cognitive impairment precluding independent assessment of comprehension (e.g., dementia, severe encephalopathy)
- •Participation in another study with potential influence on the study endpoints
- •Lack of capacity to provide informed consent
- •Refusal to participate in the study
研究组 & 干预措施
Control: Standard Synopsis
Participants receive the standard discharge letter synopsis only, as provided in routine clinical care.
Intervention: LLM-Simplified Synopsis
Participants receive the standard discharge letter synopsis plus an
LLM-generated plain-language version of the following sections:
Current Status, Medical History, Epicrisis, and Further Management. The simplified version is reviewed and approved by a study physician before being given to the patient.
干预措施: LLM-Generated Plain-Language Patient Synopsis (Other)
结局指标
主要结局
Patient Comprehension Score
时间窗: At the time of hospital discharge (Day 0), assessed immediately after reading the synopsis (approximately 15-30 minutes after receipt)
Comprehension of the patient synopsis measured using a 5-item scale based on the Patient Education Materials Assessment Tool (PEMAT; scores range from 1 to 10, with higher scores indicating better comprehension), assessing overall comprehension and comprehension of diagnosis, treatment, next steps, and medical terminology. The score is calculated as the mean of all five items (range 0-10; higher scores indicate better comprehension).
次要结局
- Patient Satisfaction with Information Received(Day 0, assessed immediately after reading the synopsis)
- Subjective Uncertainty Reduction(Day 0, before and after reading the synopsis)
- Patient Preference for Synopsis Format(Day 0, assessed immediately after reading the synopsis)
- Physician Review Time(Day 0, recorded at time of physician review)
- Physician Correction Rate(Day 0, recorded at time of physician review)