ChiCTR2600121535 版本V1.0 版本创建时间2026/03/31 17:58:06 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:

ChiCTR2600121535 

最近更新日期:

Date of Last Refreshed on:

2026-03-31 17:57:44 

注册时间:

Date of Registration:

2026-03-31 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

基于多模态语音生物标志物的AI甲状腺疾病的无创筛查系统开发与临床验证研究

Public title:

Research Plan for the Development and Clinical Validation of an AI-Based Non-Invasive Screening System for Thyroid Diseases Using Multimodal Speech Biomarkers

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于多模态语音生物标志物的AI甲状腺疾病的无创筛查系统开发与临床验证研究

Scientific title:

Research Plan for the Development and Clinical Validation of an AI-Based Non-Invasive Screening System for Thyroid Diseases Using Multimodal Speech Biomarkers

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:

吴杨 

研究负责人:

吴杨 

Applicant:

Wu Yang 

Study leader:

Wu Yang 

申请注册联系人电话:

Applicant telephone:

+86 13922843721

研究负责人电话:

Study leader's
telephone:

+86 755 89698999

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:

szwy1022@163.com

研究负责人电子邮件:

Study leader's E-mail:

szwy1022@163.con

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:

广东省深圳市龙岗区平湖街道福新路1号深圳大学附属华南医院

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, Pinghu Street, Longgang District, Shenzhen City, Guangdong Province. Shenzhen Uni

Study leader's address:

No.1, Fuxin Road, Longgang District, Shenzhen, P. R. China, 518116

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:

Approved by ethic committee:

Yes

伦理委员会批件文号:

Approved No. of ethic committee:

HNLS20260126001-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:

2026-02-05 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, P. R. China, 518116

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, P. R. China, 518116

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, P. R. China, 518116

经费或物资来源:

自选课题(自筹)

Source(s) of funding:

Self-raised funds

研究疾病:

甲状腺疾病  

Target disease:

Thyroid Diseases

研究疾病代码:

Target disease code:

研究类型:

诊断试验

Study type:

Diagnostic test

研究所处阶段:

其它 

Study phase:

N/A

研究设计:

诊断试验诊断准确性 

Study design:

Diagnostic test for accuracy 

研究目的:

构建并验证全球首个面向甲状腺疾病的AI语音筛查系统,实现≥80%敏感性与≥80%特异性,推动临床转化落地。  

Objectives of Study:

Build and validate the world's first AI voice screening system for thyroid diseases, achieving a sensitivity of ≥80% and a specificity of ≥80%, and promoting the clinical application and implementation.

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20-70周岁,性别不限;
2.理解研究内容并自愿签署知情同意书,能配合完成语音采集与临床评估;
3.拟接受甲状腺功能检测(血清TSH、FT4、FT3)的门诊或住院患者,或体检中心健康筛查人群;
4.诊断标准:入组时具备3个月内的甲状腺功能检测报告(作为金标准参照): 临床甲状腺功能减退:TSH > 5.91 mIU/L且FT4低于正常参考值下限; 临床甲状腺功能亢进:TSH < 0.56 mIU/L且FT4高于正常参考值上限; 正常或亚临床组:TSH 0.56-5.91 mIU/L且FT3、FT4在正常范围内;
5.经培训后掌握录音笔操作;
6.母语为汉语普通话,能清晰朗读98字标准化文本《四季的声音》。

Inclusion criteria

1. Age range: 20 - 70 years old, gender not restricted; 2. Understand the research content and voluntarily sign the informed consent form, and be able to cooperate in completing voice collection and clinical assessment; 3. Patients who are scheduled to undergo thyroid function tests (serum TSH, FT4, FT3) in outpatient or inpatient settings, or those in the health screening group of the physical examination center; 4. Diagnostic criteria: At the time of enrollment, possess a thyroid function test report within 3 months (as the gold standard reference): Clinical hypothyroidism: TSH > 5.91 mIU/L and FT4 below the lower limit of the normal reference range; Clinical hyperthyroidism: TSH < 0.56 mIU/L and FT4 above the upper limit of the normal reference range; Normal or subclinical group: TSH 0.56 - 5.91 mIU/L and FT3, FT4 within the normal range; 5. After training, master the operation of the voice recorder; 6. Native language: Mandarin Chinese, able to clearly read the 98-character standardized text "The Sounds of the Four Seasons".

排除标准:

1.既往有喉部手术史、声带息肉/结节、喉返神经损伤等器质性嗓音疾病;
2.研究期间有急性上呼吸道感染、咽喉炎等影响发音的急性疾病;
3.喉部外伤/结构异常,包括1)声带麻痹:颈部外伤、手术损伤(甲状腺手术常见并发症)、气管插管损伤等导致喉返神经受损,声带无法正常运动;2)喉狭窄:外伤、手术后遗症导致喉部组织瘢痕增生,气道变窄,伴随嘶哑、呼吸困难。
4.长期服用可能影响嗓音的药物(如吸入性糖皮质激素、抗胆碱能药物);
5.患有严重心肺功能不全、呼吸衰竭等无法完成持续朗读的躯体疾病;
6.精神疾病或认知功能障碍无法配合指令者;
7.孕期或哺乳期妇女(甲状腺激素生理性波动干扰基线);
8.职业嗓音使用者(如教师、歌手、播音员),其嗓音特征基线变异度大;
9.录音环境不符合质控标准(背景噪声>30dB或无法达到安静环境要求)。

Exclusion criteria:

1. Previous history of throat surgery, vocal cord polyps/nodules, or injury to the recurrent laryngeal nerve, etc., indicating organic voice disorders; 2. During the study period, there were acute diseases affecting voice such as acute upper respiratory tract infections and pharyngitis; 3. Throat trauma/structural abnormalities, including 1) vocal cord paralysis: neck trauma, surgical injury (a common complication of thyroid surgery), injury from tracheal intubation, etc., resulting in damage to the recurrent laryngeal nerve and inability of the vocal cords to move normally; 2) laryngeal stenosis: trauma, postoperative sequelae causing scar hyperplasia of laryngeal tissues, narrowing of the airway, accompanied by hoarseness and breathing difficulties. 4. Long-term use of drugs that may affect voice (such as inhaled glucocorticoids, anticholinergic drugs); 5. Suffering from severe cardiopulmonary insufficiency, respiratory failure, etc., unable to complete continuous reading; 6. Individuals with mental disorders or cognitive dysfunction unable to follow instructions; 7. Pregnant or lactating women (physiological fluctuations of thyroid hormones interfere with the baseline); 8. Professional voice users (such as teachers, singers, announcers), with significant variability in the baseline characteristics of their voice; 9. Recording environment not meeting quality control standards (background noise > 30 dB or unable to meet the requirements of a quiet environment).

研究实施时间:

Study execute time:

From 2026-02-26 00:00:00 To 2028-01-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-02-27 00:00:00 To 2028-01-01 00:00:00

诊断试验:

Diagnostic Tests:

金标准或参考标准(即可准确诊断某疾病的单项方法或多项联合方法,在本研究中用于诊断是否有该病的临床参考标准):

金标准检测(TSH、FT4)由本院实验室独立出具报告

Gold Standard or Reference Standard (The clinical reference standards required to establish the presence or absence of the target condition in the tested population in present study):

The gold standard tests (TSH, FT4) are independently reported by the laboratory of our hospital.

指标试验(即本研究的待评估诊断试验,无论为方法、生物标志物或设备,均请列出名称):

通过分析用户语音特征,结合临床信息,AI自动筛查甲状腺功能异常并预测TSH水平。

Index test:

By analyzing the user's voice characteristics and integrating clinical information, the AI automatically screens for thyroid dysfunction and predicts the TSH level.

目标人群(可以是某种疾病患者或正常人群,详细描述其疾病特征,注意应纳入符合分布特点的全序列病例,具有良好的代表性)

临床甲状腺功能减退 临床甲状腺功能亢进 正常或亚临床组

例数:

Sample size:

320

Target condition (The target condition is a particular disease or disease stage that the index test will be intended to identify. Please specify the characteristics in detail; the population should has a complete spectrum and good representative):

Clinical hypothyroidism Clinical hyperthyroidism Normal or subclinical group

容易混淆的疾病人群(即与目标疾病不易区分的一种或多种不同疾病,应避免采用正常人群对照的病例-对照设计):

例数:

Sample size:

0

Population with condition difficult to distinguish from the target condition, the normal population in a case-control study design should be avoid:

None

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:

三级医院 

Institution
hospital:

South China Hospital of Shenzhen University

Level of the institution:

Tertiary

测量指标:

Outcomes:

指标中文名:

敏感性

指标类型:

主要指标

Outcome:

sensitivity

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

特异性

指标类型:

主要指标

Outcome:

specificity

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:

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 20 years
最大 Max age 70 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:

不公开/Private

盲法:

Blinding:

None

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):

研究公开发表后半年,邮件联系研究负责人合理获取。

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

Six months after the publication of the research, contact the research leader via email to obtain reasonable information.

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:

语音数据 ? 获取方法:经受试者明确授权后采集,朗读文本不含隐私信息; ? 保存方式:原始WAV文件加密后存储于私有云服务器(阿里云或腾讯云医疗专区),备份至本地NAS; ? 保存年限:原始数据保存5年(满足AI模型迭代与监管追溯要求),特征提取后的脱敏数据可长期保存用于算法优化; ? 隐私保护:语音文件永不保留可识别身份的直接标识符(如姓名、身份证号),仅通过匿名编号关联; ? 接触权限:语音工程师与算法研究员仅能访问脱敏后数据,需签署保密协议;原始数据访问需PI与伦理委员会双审批; ? 销毁流程:保存期限届满后,通过数据擦除软件(符合DoD 5220.22-M标准)彻底删除,出具销毁证明交伦理备案。

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

Voice data?Acquisition method: Collected with the explicit consent of the subjects. The read text does not contain any private information.?Saving method: The original WAV files are encrypted and stored in private cloud servers (Alibaba Cloud or Tencent Cloud Medical Zone), and backups are made to local NAS.?Saving period: The original data is saved for 5 years (to meet the requirements for AI model iteration and regulatory traceability), and the de-identified data after feature extraction can be saved for a long time for algorithm optimization.?Privacy protection: Voice files never retain direct identifiers that can identify the identity (such as name, ID number), and are only associated through anonymous numbers.?Access rights: Voice engineers and algorithm researchers can only access the de-identified data. They need to sign a confidentiality agreement; access to the original data requires dual approval from the PI and the ethics committee.?Destruction process: After the expiration of the storage period, the data is completely deleted through data erasure software (in compliance with DoD 5220.22-M standards), and a destruction certificate is issued and filed with the ethics committee.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2026-03-31 17:57:44