ChiCTR2600124832 版本V1.0 版本创建时间2026/05/18 15:13:45 中国临床试验注册中心

审核状态：

Project audit state：

通过审核

Successful

注册号：

Registration number：

 ChiCTR2600124832 

最近更新日期：

Date of Last Refreshed on：

 2026-05-18 15:13:35 

注册时间：

Date of Registration：

 2026-05-18 00:00:00 

注册号状态：

预注册

Registration Status：

Prospective registration

注册题目：

用户视角下大语言模型辅助护理决策质量评价指标体系构建

Public title：

Construction of an Evaluation Indicator System for the Quality of Large Language Model-Assisted Nursing Decision-Making from a User Perspective

注册题目简写：

English Acronym：

研究课题的正式科学名称：

用户视角下大语言模型辅助护理决策质量评价指标体系构建

Scientific title：

Construction of an Evaluation Indicator System for the Quality of Large Language Model-Assisted Nursing Decision-Making from a User Perspective

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：

汪彦君 

研究负责人：

付蕾 

Applicant：

Wang Yanjun 

Study leader：

Fu Lei 

申请注册联系人电话：

Applicant telephone：

 +86 17329122018

研究负责人电话：

Study leader's
telephone：

+86 755 8969 8999

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：

 wyj123@henu.edu.cn

研究负责人电子邮件：

Study leader's E-mail：

 leifu@szu.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：

深圳市龙岗区福新路1号

研究负责人通讯地址：

深圳市龙岗区平湖街道福新路1号

Applicant address：

No. 1 Fuxin Road, Longgang District, Shenzhen

Study leader's address：

No.1, Fuxin Road, Longgang District, Shenzhen

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：

深圳大学附属华南医院

Applicant's institution：

Shenzhen University Affiliated South China Hospital

研究负责人所在单位：

深圳大学附属华南医院

Affiliation of the Leader：

South China Hospital of Shenzhen University

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：

 HNLS20260319001-A

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：

深圳大学附属华南医院伦理委员会

Name of the ethic committee：

Ethics Committee of South China Hospital affiliated to Shenzhen University

伦理委员会批准日期：

Date of approved by ethic committee：

 2026-03-30 00:00:00

伦理委员会联系人：

孙海燕

Contact Name of the ethic committee：

Sun Haiyan

伦理委员会联系地址：

深圳市龙岗区平湖街道福新路1号

Contact Address of the ethic committee：

No.1, Fuxin Road, Longgang District, Shenzhen

伦理委员会联系人电话：

Contact phone of the ethic committee：

 +86 755 21583851

伦理委员会联系人邮箱：

Contact email of the ethic committee：

 18302099013@163.com

研究实施负责（组长）单位：

深圳大学附属华南医院

Primary sponsor：

South China Hospital of Shenzhen University

研究实施负责（组长）单位地址：

深圳市龙岗区平湖街道福新路1号

Primary sponsor's address：

No.1, Fuxin Road, Longgang District, Shenzhen

试验主办单位(项目批准或申办者)：

Secondary sponsor：

国家：

中国

省(直辖市)：

广东省

市(区县)：

Country：

China

Province：

Guangdong

City：

单位(医院)：

深圳大学附属华南医院

具体地址：

深圳市龙岗区平湖街道福新路1号

Institution
hospital：

South China Hospital of Shenzhen University

Address：

No.1, Fuxin Road, Longgang District, Shenzhen

经费或物资来源：

自选课题（自筹）

Source(s) of funding：

self-financed

研究疾病：

无  

Target disease：

None

研究疾病代码：

Target disease code：

研究类型：

观察性研究

Study type：

Observational study

研究所处阶段：

 其它 

Study phase：

N/A

研究设计：

横断面 

Study design：

Cross-sectional 

研究目的：

1.基于评价模型、Meta 整合和文献回顾构建出用户视角下大语言模型辅助护理决策质量的评价指标体系。 2.在护士中开展横断面调查，进行量表应用及验证评价指标问卷的信效度，进一步分析评价指标体系的可靠性、有效性和可操作性，为该评价指标体系的应用提供参考工具  

Objectives of Study：

1.Based on an evaluation model, Meta-synthesis, and literature review, an evaluation indicator system for the quality of large language model-assisted nursing decision-making from a user perspective was constructed. 2.A cross-sectional survey was conducted among nurses to apply and validate the reliability and validity of the evaluation indicator questionnaire, and further analyze the reliability, validity, and operability of the evaluation indicator system, thereby providing a reference tool for the application of this evaluation indicator system.

药物成份或治疗方案详述：

 

Description for medicine or protocol of treatment in detail：

 

纳入标准：

1.半结构化质性访谈：（1）目前已实际使用大语言模型开展护理决策内容生成相关工作的护士（2）具备良好的普通话语言沟通能力，能清晰表达自身观点 (3)自愿参与本研究，配合访谈及相关记录工作。
2.德尔菲专家函询：（1）函询拥有大语言模型辅助护理决策的相关实践经历（2) 学历达到本科及以上水平 (3) 专业技术职称为中级及以上(4)临床护理与护理科研工作总时长≥10年 (5) 了解本研究研究内容，自愿参与函询工作并配合指标评分、意见反馈；
3.横断面研究调查：（1）日常临床护理决策工作中，实际使用大语言模型作为辅助工具（2)持续使用该大语言模型辅助系统的时长≥1个月(3)为所在医疗机构/科室的正式在编护士 (4) 知晓本研究目的，知情同意并自愿参与问卷调查；

Inclusion criteria

1.Semi-structured interview: (1) Nurses who have actually used large language models to generate nursing decision-making content; (2) Possess good Mandarin communication skills and can clearly express their own views; (3) Voluntarily participate in this study and cooperate with interviews and related documentation work.
2.Delphi experts: (1) Have practical experience in using large language models to assist nursing decision-making; (2) Hold at least a bachelor's degree; (3) Have a mid-level or higher professional title; (4) Have at least 10 years of combined experience in clinical nursing and nursing research; (5) Understand the study, participate voluntarily, and cooperate with scoring and feedback.
3. Cross-sectional study: (1) Actually use large language models as an auxiliary tool in daily clinical nursing decision-making; (2) Have continuously used the LLM-assisted system for ≥1 month; (3) Be a regular/tenured nurse in the medical institution/department; (4) Understand the purpose of this study, give informed consent, and voluntarily participate in the questionnaire survey.

排除标准：

1.半结构化质性访谈：（1）完全未使用过大语言模型生成护理相关材料（如护理计划、健康教育内容等）的护士； （2）拒绝接受访谈录音、文字记录的护士。
2.德尔菲专家函询 （1）不符合任一入选标准（如无相关实践经历、学历低于本科、职称为初级及以下、工作总时长＜10年）的专家。 （2）未在规定时间内完成函询问卷、评分明显敷衍或主动退出/撤回知情同意的专家。
3.横断面研究调查：（1）目前已停止使用大语言模型辅助护理决策系统的护士（2）非科室正式护士，包括实习护士、见习护士、进修护士、规培护士、科室临时借调护士等（3）虽参与问卷作答，但经数据审核判定为无效作答的对象（如作答时间不足6分钟、IP地址与填写信息不符、所有题目打分完全相同、相同IP多次作答等，此类为问卷数据筛选阶段的排除情形）；

Exclusion criteria：

1. Semi-structured qualitative interview: (1) Nurses who have never used a large language model to generate nursing-related materials (such as nursing plans, health education content, etc.); (2) Nurses who refuse to have the interview audio-recorded or documented in writing.
2. Delphi expert consultation: (1) Experts who do not meet any of the inclusion criteria (e.g., no relevant practical experience, education below bachelor’s degree, junior or lower professional title, total work experience <10 years). (2) Experts who fail to complete the consultation questionnaire within the specified time, show clearly perfunctory scoring, or voluntarily withdraw/withdraw informed consent.Nurses who have stopped using the large language model-assisted nursing decision-making system; Nurses who are not formal members of the department, including intern nurses, trainee nurses, visiting nurses, standardized training nurses, temporarily transferred nurses, etc.; Participants who, despite completing the questionnaire, are determined to have provided invalid responses upon data review (e.g., completion time of less than 6 minutes, inconsistency between IP address and reported information, identical scores across all items, multiple submissions from the same IP address, etc.). These cases will be excluded during the questionnaire data screening phase.
3. Cross-sectional study survey: (1) Nurses who have stopped using the large language model-assisted nursing decision-making system; (2) Non-regular ward nurses, including intern nurses, trainee nurses, visiting nurses, standardized training nurses, temporarily seconded nurses, etc.; (3) Individuals who completed the questionnaire but were judged to have provided invalid responses during data review (e.g., response time less than 6 minutes, IP address inconsistent with provided information, identical scores for all items, multiple responses from the same IP address, etc.) — these are exclusion criteria during the questionnaire data screening stage.

研究实施时间：

Study execute time：

从 From 2026-01-01 00:00:00至 To 2027-03-01 00:00:00  

征募观察对象时间：

Recruiting time：

从 From 2026-06-01 00:00:00 至 To 2026-12-30 00:00:00

干预措施：

Interventions：

组别：

开展半结构质性访谈

样本量：

 15

Group：

Conduct semi-structured qualitative interviews

Sample size：

干预措施：

无

干预措施代码：

Intervention：

None

Intervention code：

组别：

横断面研究

样本量：

 200

Group：

Cross-sectional study

Sample size：

干预措施：

无

干预措施代码：

Intervention：

None

Intervention code：

组别：

德尔菲专家函询

样本量：

 15

Group：

Delphi expert consultation

Sample size：

干预措施：

无

干预措施代码：

Intervention：

None

Intervention code：

研究实施地点：

Countries of recruitment and research settings：

国家：

 中国

省(直辖市)：

 广东省 

市(区县)：

  

Country：

China

Province：

Guangdong

City：

单位(医院)：

 深圳大学附属华南医院 

单位级别：

 三级 

Institution
hospital：

South China Hospital of Shenzhen University

Level of the institution：

Tertiary

测量指标：

Outcomes：

指标中文名：

编码一致性系数

指标类型：

主要指标

Outcome：

Coding consistency coefficient

Type：

Primary indicator

测量时间点：

测量方法：

Measure time point of outcome：

Measure method：

指标中文名：

德尔菲专家函询的统计分析指标包括：问卷回收率、专家建议提出率、专家权威系数（Cr）、肯德尔协调系数（Kendall‘s W）、指标重要性赋值均数、变异系数（CV）、满分率。

指标类型：

主要指标

Outcome：

Delphi statistical indicators: recovery rate, suggestion rate, authority coefficient (Cr), Kendall’s W, mean importance, CV (coefficient of variation), and full-score rate.

Type：

Primary indicator

测量时间点：

测量方法：

Measure time point of outcome：

Measure method：

指标中文名：

有效回收率

指标类型：

主要指标

Outcome：

Effective response rate

Type：

Primary indicator

测量时间点：

测量方法：

Measure time point of outcome：

Measure method：

指标中文名：

Cronbach‘s α系数

指标类型：

主要指标

Outcome：

Cronbach's α

Type：

Primary indicator

测量时间点：

测量方法：

Measure time point of outcome：

Measure method：

指标中文名：

分半信度

指标类型：

主要指标

Outcome：

split-half reliability

Type：

Primary indicator

测量时间点：

测量方法：

Measure time point of outcome：

Measure method：

指标中文名：

内容效度指数（S-CVI、I-CVI）

指标类型：

主要指标

Outcome：

content validity index (S-CVI, I-CVI)

Type：

Primary indicator

测量时间点：

测量方法：

Measure time point of outcome：

Measure method：

采集人体标本：

Collecting sample(s)
from participants：

标本中文名：

无

组织：

Sample Name：

NA

Tissue：

人体标本去向

 其它  

说明

Fate of sample：

0thers  

Note：

征募研究对象情况：

Recruiting status：

尚未开始

Not yet recruiting

年龄范围：

Participant age：
最小 Min age 岁 years
最大 Max age 岁 years

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）：

无

Randomization Procedure (please state who generates the random number sequence and by what method)：

None

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：

无

Blinding：

None

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：

数据采集：本研究通过三类途径采集数据：质性研究阶段，采用半结构化访谈对约15名使用大语言模型辅助护理决策的护士进行面对面或线上录音访谈，借助NVivo软件进行资料记录与整理，以信息饱和原则确定样本量；德尔菲专家函询阶段，通过电子邮件结合微信方式向15至50名护理、人工智能及信息管理领域的专家发放Likert 5级评分问卷，每轮设置2周回收期限并辅以电话提醒，共进行两轮函询；横断面调查阶段，通过问卷星平台向符合入选标准（使用时长≥1个月）的护士发放结构化自评问卷，设置断点续答、逻辑效验题及作答时间记录功能，按量表条目数的5至10倍并预留20%失访量估算样本量 数据管理：所有数据实行分类匿名编码处理，访谈录音及转录文本、德尔菲函询数据、横断面问卷数据均存储于加密移动硬盘及课题组加密云盘进行双备份；采用双人独立录入与交叉核对机制确保数据准确性，建立数据溯源记录本登记所有数据变更操作；问卷星后台设置IP限制、每题必答及逻辑校验以控制数据质量，剔除标准包括作答时间不足6分钟、IP地址与填写信息不符、打分完全一致或逻辑效验矛盾等无效问卷；数据访问权限仅限研究团队核心成员，研究结束后按伦理要求保存3年，数据使用仅限于本研究，不得用于其他商业或研究用途。

Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture：

Data Collection: This study collects data through three approaches. In the qualitative research phase, semi-structured interviews are conducted with approximately 15 nurses who use large language models to assist nursing decision-making, either face-to-face or online with audio recording. Data are recorded and organized using NVivo software, and the sample size is determined based on the principle of information saturation. In the Delphi expert consultation phase, a Likert 5-point scale questionnaire is distributed to 15–50 experts in nursing, artificial intelligence, and information management via email combined with WeChat. A two-week response period is set for each round, supplemented by telephone reminders, and a total of two rounds of consultations are conducted. In the cross-sectional survey phase, a structured self-report questionnaire is distributed via the WJX platform to nurses who meet the inclusion criteria (using the system for ≥1 month, formally employed nurses). Functions such as resume-breakpoint answering, logical validity checks, and response time recording are enabled, and the sample size is estimated based on 5–10 times the number of scale items with an additional 20% reserved for attrition.Data Management: All data are processed with categorical anonymous coding. Interview audio recordings and transcripts, Delphi consultation data, and cross-sectional survey data are stored in duplicate on an encrypted portable hard drive and the research team's encrypted cloud drive. A dual-person independent entry and cross-checking mechanism is used to ensure data accuracy, and a data traceability log is established to record all data modification operations. In the WJX platform backend, IP restrictions, mandatory answering of each question, and logical validation are enabled to control data quality. Exclusion criteria include invalid questionnaires with response time less than 6 minutes, IP address inconsistent with the provided information, identical ratings across all items, or logical contradictions in validity checks. Data access is restricted to core members of the research team. After the study is completed, data will be preserved for 3 years as required by ethical standards, and data use is limited to this study and shall not be used for other commercial or research purposes

数据与安全监察委员会：

Data and Safety Monitoring Committee：

有/Yes

注册人：

Name of Registration：

  2026-05-18 15:13:35