|
注册号: Registration number: |
ChiCTR2600122554 |
|
最近更新日期: Date of Last Refreshed on: |
2026-04-15 10:34:42 |
|
注册时间: Date of Registration: |
2026-04-15 00:00:00 |
|
注册号状态: |
预注册 |
|
Registration Status: |
Prospective registration |
|
注册题目: |
AI赋能医患沟通:基于行为科学的LLMs能力增强技术开发与评估 |
|
Public title: |
AI-Enhanced Doctor-Patient Communication: Development and Evaluation of Behavior Science-Informed LLM Capability Augmentation Technologies |
|
注册题目简写: |
|
|
English Acronym: |
|
|
研究课题的正式科学名称: |
AI赋能医患沟通:基于行为科学的LLMs能力增强技术开发与评估 |
|
Scientific title: |
AI-Enhanced Doctor-Patient Communication: Development and Evaluation of Behavior Science-Informed LLM Capability Augmentation Technologies |
|
研究课题代号(代码): Study subject ID: |
|
|
在二级注册机构或其它机构的注册号: The registration number of the Partner Registry or other register: |
|
申请注册联系人: |
张宇航 |
研究负责人: |
张宇航;吴传安 |
|
Applicant: |
Zhang Yuhang |
Study leader: |
Zhang Yuhang; Wu Chuanan |
|
申请注册联系人电话: Applicant telephone: |
+86 62791154 |
研究负责人电话:
Study leader's |
+86 62791154 |
|
申请注册联系人传真 : Applicant Fax: |
研究负责人传真: Study leader's fax: |
||
|
申请注册联系人电子邮件: Applicant E-mail: |
yuhang-z23@mails.tsinghua.edu.cn |
研究负责人电子邮件: Study leader's E-mail: |
sitongluo@tsinghua.edu.cn |
|
申请单位网址(自愿提供): Applicant website(voluntary supply): |
研究负责人网址(自愿提供): Study leader's website(voluntary supply): |
||
|
申请注册联系人通讯地址: |
北京市海淀区双清路30号 |
研究负责人通讯地址: |
北京市海淀区双清路30号 |
|
Applicant address: |
No.30 Shuangqing Street, Haidian District, Beijing,China |
Study leader's address: |
No.30 Shuangqing Street, Haidian District, Beijing,China |
|
申请注册联系人邮政编码: Applicant postcode: |
研究负责人邮政编码: Study leader's postcode: |
||
|
申请人所在单位: |
清华大学万科公共卫生与健康学院 |
||
|
Applicant's institution: |
Vanke School of Public Health, Tsinghua University |
||
|
研究负责人所在单位: |
清华大学,深圳市龙华区人民医院 |
||
|
Affiliation of the Leader: |
Tsinghua University, Shenzhen Longhua District People's Hospital |
||
|
是否获伦理委员会批准: |
是 |
||
|
Approved by ethic committee: |
Yes |
||
|
伦理委员会批件文号: Approved No. of ethic committee: |
THU-01-2025-1072, 龙华人医伦审(研) [2026]第(027)号 |
伦理委员会批件附件: Approved file of Ethical Committee: |
查看附件View |
|
批准本研究的伦理委员会名称: |
清华大学科技伦理委员会医学委员会,深圳市龙华区人民医院医学伦理委员会 |
||
|
Name of the ethic committee: |
The Medical Committee of the Tsinghua University Scientific and Technological Ethics Committee,Medical Ethics Committee of Shenzhen Longhua District People's Hospital |
||
|
伦理委员会批准日期: Date of approved by ethic committee: |
2025-11-19 00:00:00 | ||
|
伦理委员会联系人: |
朱艳东 |
||
|
Contact Name of the ethic committee: |
Zhu Yandong |
||
|
伦理委员会联系地址: |
北京市海淀区双清路30号 |
||
|
Contact Address of the ethic committee: |
No.30 Shuangqing Street, Haidian District, Beijing,China |
||
|
伦理委员会联系人电话: Contact phone of the ethic committee: |
+86 10 6278 9471 |
伦理委员会联系人邮箱: Contact email of the ethic committee: |
|
|
研究实施负责(组长)单位: |
清华大学, 深圳市龙华区人民医院 |
||||||||||||||||||||||
|
Primary sponsor: |
Tsinghua University, Shenzhen Longhua District People's Hospital |
||||||||||||||||||||||
|
研究实施负责(组长)单位地址: |
北京市海淀区双清路30号 |
||||||||||||||||||||||
|
Primary sponsor's address: |
No.30 Shuangqing Street, Haidian District, Beijing,China |
||||||||||||||||||||||
|
试验主办单位(项目批准或申办者): Secondary sponsor: |
|
||||||||||||||||||||||
|
经费或物资来源: |
2025科技新星计划;新发突发与重大传染病防控国家科技重大专项 |
||||||||||||||||||||||
|
Source(s) of funding: |
2025 Beijing Nova Program;Preventionand Control of Emerging and Major Infectious Diseases-National Science and Technology Major Project |
||||||||||||||||||||||
|
研究疾病: |
高血压,2型糖尿病 |
||||||||||||||||||||||
|
Target disease: |
Hypertension, type 2 diabetes, chronic obstructive pulmonary disease (COPD), and other common chronic non-communicable diseases (NCDs) in the community. |
||||||||||||||||||||||
|
研究疾病代码: |
|
||||||||||||||||||||||
|
Target disease code: |
|
||||||||||||||||||||||
|
研究类型: |
干预性研究 |
||||||||||||||||||||||
|
Study type: |
Interventional study |
||||||||||||||||||||||
|
研究所处阶段: |
其它 | ||||||||||||||||||||||
|
Study phase: |
N/A |
||||||||||||||||||||||
|
研究设计: |
整群随机分组 |
||||||||||||||||||||||
|
Study design: |
Cluster randomization |
||||||||||||||||||||||
|
研究目的: |
本研究旨在评估基于LLM的人工智能辅助沟通系统是否能够提升基层医疗场景中的医患沟通质量,并进一步分析其对患者自我管理能力、健康行为及临床结局的影响。 |
||||||||||||||||||||||
|
Objectives of Study: |
This study aims to evaluate whether an LLM-based AI-assisted communication system can improve the quality of doctor-patient communication in primary care settings, and to further analyze its impact on patients' self-management capabilities, health behaviors, and clinical outcomes. |
||||||||||||||||||||||
|
药物成份或治疗方案详述: |
|
||||||||||||||||||||||
|
Description for medicine or protocol of treatment in detail: |
|
||||||||||||||||||||||
|
纳入标准: |
|||||||||||||||||||||||
|
Inclusion criteria |
|||||||||||||||||||||||
|
排除标准: |
1.医生:(1)诊疗内容不涉及慢性非传染性疾病管理;(2)有严重身体疾病或沟通障碍;(3)不愿意参与研究或拒绝签署知情同意书。 2.患者:(1)处于高血压危象、糖尿病酮症酸中毒等急性并发症期,或患有其他严重躯体疾病需紧急住院治疗者;(2)正在参加其他相关的临床试验或健康管理干预项目;(3)近6个月没有来社区健康服务中心的就诊信息;(4)患有重度认知障碍或其他影响沟通的精神障碍,无法独立或在辅助下完成有效对话及问卷填写 |
||||||||||||||||||||||
|
Exclusion criteria: |
1.Physicians:(1) Clinical practice does not involve the management of non-communicable diseases;(2) Have serious physical illnesses or communication impairments;(3) Are unwilling to participate in the study or refuse to sign the informed consent form. 2.Patients:(1) Currently in the acute complication phase of conditions such as hypertensive crisis or diabetic ketoacidosis, or suffering from other severe physical illnesses requiring urgent hospitalization;(2) Currently participating in other related clinical trials or health management intervention programs;(3) No record of visits to the Community Health Center (CHC) in the past 6 months.(4) Suffering from severe cognitive impairment or other psychiatric disorders affecting communication, rendering them unable to complete effective dialogues and questionnaires, either independently or with assistance. |
||||||||||||||||||||||
|
研究实施时间: Study execute time: |
从 From 2026-04-27 00:00:00至 To 2026-06-30 00:00:00 |
征募观察对象时间: Recruiting time: |
从 From 2026-05-01 00:00:00 至 To 2026-05-10 00:00:00 |
|
干预措施: Interventions: |
|
|
研究实施地点: Countries of recruitment and research settings: |
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||
|
测量指标: Outcomes: |
|
|
采集人体标本:
Collecting sample(s)
|
|
|
征募研究对象情况: Recruiting status: |
尚未开始 Not yet recruiting |
年龄范围: Participant age: |
|
||||||
|
性别: |
男女均可 |
Gender: |
Both |
||||||
|
随机方法(请说明由何人用什么方法产生随机序列): |
采用计算机生成的随机序列进行分组。由不直接参与参与者招募和干预实施的研究人员,使用Python(版本3.13)的 random 库生成 21 位全科医生的随机分配序列。考虑到各中心样本量的平衡,采用分层随机化方法,以“社区健康服务中心”作为分层因素,确保每个中心内部的医生被均衡地分配至三个组别,排除社康管理水平和日常门诊量差异等因素对结果的影响。 |
||||||||
|
Randomization Procedure (please state who generates the random number sequence and by what method): |
Participants were allocated using a computer-generated random sequence. The random allocation sequence for the 21 general practitioners was generated by a researcher not directly involved in participant recruitment or intervention implementation, utilizing the random library in Python (Version 3.13). To ensure balance across sample sizes at different sites, stratified randomization was employed with the "Community Health Center" serving as the stratification factor. This approach ensured that physicians within each center were evenly distributed across the three groups, thereby minimizing the potential impact of confounding factors such as variations in management standards and daily outpatient volume among the centers. |
||||||||
|
是否公开试验完成后的统计结果: Calculated Results after the Study Completed public access: |
不公开/Private |
|
盲法: |
本研究针对不同角色实施了不同程度的盲法: (1)医生端(部分盲法):两个AI辅助组的医生对具体分组保持部分盲态,即医生知晓其正在使用AI辅助沟通系统,但不知晓其具体属于哪一AI策略版本。为减少因技术偏好引起的偏倚,两组医生所使用的硬件设备(工作电脑)、界面交互形式、系统响应方式及提示呈现格式均保持一致,仅在后台算法策略层面存在差异。常规诊疗组无法实施医生盲法。 (2)患者端(单盲):入组患者对其医生所接受的具体分组情况不知情,仅知晓参与一项关于医患沟通的研究,但不知晓具体干预分配。患者在诊疗过程中可能基于体验形成主观判断,但研究团队不向其披露分组信息。 |
|
Blinding: |
1. Physician Side (Partial Blinding) Physicians in the two AI-assisted groups maintained a partial blind status regarding their specific group allocation. Specifically, while they were aware that they were using an AI-assisted communication system, they were unaware of which specific AI strategy version they were assigned to. To minimize bias arising from technology preference, the hardware (work computers), interface interaction, system response methods, and prompt presentation formats were kept identical across both groups; differences existed solely at the level of backend algorithmic strategies. Blinding was not implemented for physicians in the routine care group. 2. Patient Side (Single Blinding) Enrolled patients were blinded to the specific group allocation of their physicians. They were informed that they were participating in a study regarding doctor-patient communication but were not aware of the specific intervention assignment. Although patients might form subjective judgments based on their experience during the consultation, the research team did not disclose any group allocation information to them. |
|
是否共享原始数据: IPD sharing |
否No |
|
共享原始数据的方式(说明:请填入公开原始数据日期和方式,如采用网络平台,需填该网络平台名称和网址): |
无 |
|
The way of sharing IPD”(include metadata and protocol, If use web-based public database, please provide the url): |
None |
|
数据采集和管理(说明:数据采集和管理由两部分组成,一为病例记录表(Case Record Form, CRF),二为电子采集和管理系统(Electronic Data Capture, EDC),如ResMan即为一种基于互联网的EDC: |
CRF;EDC |
|
Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture: |
CRF;EDC |
|
数据与安全监察委员会: Data and Safety Monitoring Committee: |
无/No |