ChiCTR2600124131 版本V1.0 版本创建时间2026/05/07 17:29:47 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:

ChiCTR2600124131 

最近更新日期:

Date of Last Refreshed on:

2026-05-07 17:29:24 

注册时间:

Date of Registration:

2026-05-07 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

临床实践中基于智能手机的多模态 AI 疼痛评估系统与视觉模拟评分法的前瞻性验证研究

Public title:

Prospective Validation of a Smartphone-based Multimodal AI Pain Assessment System versus the Visual Analogue Scale in Clinical Practice

注册题目简写:

English Acronym:

研究课题的正式科学名称:

临床实践中基于智能手机的多模态AI疼痛评估系统与视觉模拟评分法的前瞻性验证研究

Scientific title:

Prospective Validation of a Smartphone-based Multimodal Artificial Intelligence Pain Assessment System versus the Visual Analogue Scale in Clinical Practice: A Single-Center Diagnostic Accuracy Study

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:

柯鹏辉 

研究负责人:

柯鹏辉 

Applicant:

Ke Penghui 

Study leader:

Ke Penghui 

申请注册联系人电话:

Applicant telephone:

+86 186 5591 1729

研究负责人电话:

Study leader's
telephone:

+86 186 5591 1729

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:

864040149@qq.com

研究负责人电子邮件:

Study leader's E-mail:

864040149@qq.com

申请单位网址(自愿提供):

Applicant website(voluntary supply):

安徽医科大学第一附属医院

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:

合肥市蜀山区绩溪路218号

研究负责人通讯地址:

合肥市蜀山区绩溪路218号

Applicant address:

No.218 Jixi Road, Hefei, 230022, China

Study leader's address:

No.218 Jixi Road, Hefei, 230022, China

申请注册联系人邮政编码:

Applicant postcode:

230022

研究负责人邮政编码:

Study leader's postcode:

230022

申请人所在单位:

安徽医科大学第一附属医院 疼痛科

Applicant's institution:

Department of Pain Medicine, The First Affiliated Hospital of Anhui Medical University

研究负责人所在单位:

安徽医科大学第一附属医院 疼痛科

Affiliation of the Leader:

Department of Pain Medicine, The First Affiliated Hospital of Anhui Medical University

是否获伦理委员会批准:

Approved by ethic committee:

Yes

伦理委员会批件文号:

Approved No. of ethic committee:

KY2026-04-10

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:

安徽医科大学第一附属医院伦理委员会

Name of the ethic committee:

Ethics Committee of the First Affiliated Hospital of Anhui Medical University

伦理委员会批准日期:

Date of approved by ethic committee:

2026-04-10 00:00:00

伦理委员会联系人:

陈毅豪

Contact Name of the ethic committee:

Chen Yihao

伦理委员会联系地址:

中国安徽省合肥市高新区皖水路121号

Contact Address of the ethic committee:

No. 121 Wanshui Road, High-tech Zone, Hefei City, Anhui Province, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 551 6292 3004

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:

安徽医科大学第一附属医院

Primary sponsor:

The First Affiliated Hospital of Anhui Medical University

研究实施负责(组长)单位地址:

合肥市蜀山区绩溪路218号

Primary sponsor's address:

No.218 Jixi Road, Hefei, 230022, China

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

安徽

市(区县):

合肥

Country:

china

Province:

Anhui

City:

单位(医院):

安徽医科大学第一附属医院

具体地址:

中国安徽省合肥市蜀山区绩溪路218号

Institution
hospital:

First Affiliated Hospital of Anhui Medical University

Address:

218 Jixi Road, Shushan District, Hefei City, Anhui, China

经费或物资来源:

无资助(研究者自发,本单位内部条件支持)

Source(s) of funding:

No external funding. Investigator-initiated study supported by internal resources of the institution.

研究疾病:

疼痛(临床疼痛评估)  

Target disease:

Pain (clinical pain assessment)

研究疾病代码:

R52

Target disease code:

R52

研究类型:

观察性研究

Study type:

Observational study

研究所处阶段:

诊断试验新技术临床试验 

Study phase:

Diagnostic New Technique Clincal Study

研究设计:

连续入组 

Study design:

Sequential 

研究目的:

主要目的:以九宫格重分类分析为主要终点,验证基于智能手机的多模态AI疼痛评估系统,在VAS评分与多维临床证据出现矛盾的病例中,能否正确识别矛盾并给出与复合参考标准(CRS)一致的判断。具体证明AI在两个关键临床场景中的纠正能力:(1)隐性剧痛识别——VAS低报但AI与CRS均判定为中/重度疼痛的病例;(2)主观放大识别——VAS高报但AI与CRS均判定为无痛/轻度疼痛的病例。 次要目的:(1)比较AI与VAS的评估覆盖率,验证AI在老年、认知障碍等特殊人群中的可评估优势;(2)比较不同操作者使用AI与指导VAS的操作者间一致性(ICC);(3)比较AI与VAS的单次评估耗时;(4)识别对疼痛评分贡献最大的核心模态特征。 探索性目的:(1)Bland-Altman一致性描述;(2)VAS与AI评分分布特征对比;(3)SRM动态响应度分析。  

Objectives of Study:

Primary objective: Using nine-grid reclassification analysis as the primary endpoint, to validate whether a smartphone-based multimodal AI pain assessment system can correctly identify and resolve discrepancies between VAS scores and multidimensional clinical evidence, and provide judgments consistent with a composite reference standard (CRS). Specifically, to demonstrate the AI system's corrective capacity in two key clinical scenarios: (1) occult severe pain (low VAS but AI and CRS both indicate moderate/severe pain); (2) subjective amplification (high VAS but AI and CRS both indicate no/mild pain). Secondary objectives: (1) compare assessability coverage of AI vs. VAS, particularly in special populations (elderly, cognitive impairment); (2) compare inter-operator reliability (ICC) of AI vs. operator-guided VAS; (3) compare single-assessment duration; (4) identify the most contributive modality features. Exploratory objectives: (1) Bland-Altman agreement; (2) distribution comparison of VAS and AI scores; (3) standardized response mean (SRM) for dynamic responsiveness.

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. 年龄≥18岁; 2. 因各种原因需要进行疼痛评估的临床患者(含门诊及住院); 3. 本人或法定代理人签署知情同意书。

Inclusion criteria

1. Age >= 18 years; 2. Clinical patients (outpatient or inpatient) requiring pain assessment for any reason; 3. Signed informed consent by the participant or legal representative.

排除标准:

1. 面部严重损伤或手术后面部被完全遮挡,无法进行面部表情采集者; 2. 处于深度镇静或昏迷状态(RASS评分≤-4)者; 3. 拒绝参与研究或撤回知情同意者; 4. 研究者判断存在其他不宜入组情况者。

Exclusion criteria:

1. Severe facial injury or complete facial occlusion postoperatively, precluding facial expression capture; 2. Deep sedation or coma (RASS <= -4); 3. Refusal to participate or withdrawal of informed consent; 4. Other conditions deemed unsuitable for enrollment by the investigator.

研究实施时间:

Study execute time:

From 2026-06-01 00:00:00 To 2026-09-30 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-06-01 00:00:00 To 2026-09-30 00:00:00

干预措施:

Interventions:

组别:

主队列

样本量:

240

Group:

Main cohort

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

组别:

子队列A(操作者间一致性)

样本量:

60

Group:

Sub-cohort A (inter-operator reliability)

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

组别:

子队列B(动态响应度)

样本量:

60

Group:

Sub-cohort B (dynamic responsiveness)

Sample size:

干预措施:

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):

安徽 

市(区县):

合肥 

Country:

China

Province:

Anhui

City:

Hefei

单位(医院):

安徽医科大学第一附属医院 

单位级别:

三甲 

Institution
hospital:

The First Affiliated Hospital of Anhui Medical University

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

九宫格重分类分析(AI vs. VAS相对于CRS的净重分类改善)

指标类型:

主要指标

Outcome:

Nine-grid reclassification analysis (net reclassification improvement of AI vs. VAS against CRS)

Type:

Primary indicator

测量时间点:

入组当日同步评估(T0)

测量方法:

构建3×3九宫格(VAS:0-30/31-69/70-100mm;AI同分档),以CRS四分类为颜色编码,计算临床净重分类改善(Clinical NRI),采用配对McNemar检验

Measure time point of outcome:

At enrollment, concurrent assessment (T0)

Measure method:

3×3 reclassification grid (VAS: 0-30/31-69/70-100 mm; AI identical bands) coded by CRS four-category rating; Clinical NRI calculated; paired McNemar test

指标中文名:

AI评估成功率与VAS评估成功率的对比

指标类型:

次要指标

Outcome:

Assessability coverage: success rate of AI vs. VAS assessment

Type:

Secondary indicator

测量时间点:

入组当日同步评估(T0)

测量方法:

配对卡方检验(McNemar)

Measure time point of outcome:

At enrollment, concurrent assessment (T0)

Measure method:

指标中文名:

操作者间一致性(ICC):AI vs. VAS

指标类型:

次要指标

Outcome:

Inter-operator reliability (ICC) of AI vs. VAS

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

单次评估耗时对比(AI vs. VAS)

指标类型:

次要指标

Outcome:

Single-assessment duration of AI vs. VAS

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

Bland-Altman一致性分析(AI vs. CRS, VAS vs. CRS)

指标类型:

附加指标

Outcome:

Bland-Altman agreement (AI vs. CRS, VAS vs. CRS)

Type:

Additional indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

SRM动态响应度

指标类型:

附加指标

Outcome:

Standardized Response Mean (SRM)

Type:

Additional 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:

组织:

Sample Name:

none

Tissue:

人体标本去向

使用后销毁  

说明

Fate of sample:

Destruction after use  

Note:

征募研究对象情况:

Recruiting status:

正在进行

Recruiting

年龄范围:

Participant age:

最小 Min age 18 years
最大 Max age 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):

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:

公开/Public

盲法:

Blinding:

试验完成后的统计结果(上传文件):

Calculated Results after
the Study Completed(upload file):

是否共享原始数据:

IPD sharing

是Yes

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):

研究结束并发表主要成果后,经伦理委员会批准,去标识化的结构化数据(不含原始音视频)可应合理请求向研究人员共享;原始音视频因包含面部及声纹等生物识别信息,不予共享。联系方式:通讯作者单位邮箱。

The way of sharing IPD”(include metadata and protocol, If use web-based public database, please provide the url):

After publication of primary results and with approval from the Ethics Committee, de-identified structured data (excluding raw audio/video) may be shared with qualified researchers upon reasonable request. Raw audio/video data containing biometric information (facial images, voiceprints) will not be shared. Contact: corresponding author's institutional email.

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:

数据采集由两部分组成:(1)病例报告表(CRF):研究护士采用纸质CRF记录受试者基本信息、生理参数、VAS评分、评估时间、失败原因等;CRS专家评分表密封提交后由专人拆封录入。(2)电子采集系统:AI扫描的视频/音频/评分结果自动加密保存至本院AES-256加密本地服务器,不上传云端。所有数据以受试者编码(PAIN-AI-XXX)标识,去除身份信息。数据录入采用双人核查,锁定前全面核查,修改保留操作日志可溯源。保存期限不少于5年。

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

Data collection consists of: (1) Case Record Form (CRF): research nurses record baseline characteristics, physiological parameters, VAS scores, assessment duration, and failure reasons on paper CRFs; sealed expert rating sheets are opened and entered by a dedicated data manager. (2) Electronic capture: video, audio, and AI scores are automatically encrypted and stored on an on-site AES-256-encrypted server (no cloud upload). All data are identified by a subject code (PAIN-AI-XXX) with personal identifiers removed. Double-entry verification is applied, and full data review is performed before database lock. Modifications are logged and fully traceable. Retention period: at least 5 years.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2026-05-07 17:29:24