ChiCTR2500115466 版本V1.0 版本创建时间2025/12/26 10:55:19 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：

ChiCTR2500115466 

最近更新日期：

Date of Last Refreshed on：

2025-12-26 10:55:01 

注册时间：

Date of Registration：

2025-12-26 00:00:00 

注册号状态：

预注册

Registration Status：

Prospective registration

注册题目：

高阶声学模型构建及在肺结核诊断及随访中的应用价值探索

Public title：

Exploring the Clinical Utility of Advanced Acoustic Models in Tuberculosis Diagnosis and Therapeutic Monitoring

注册题目简写：

English Acronym：

研究课题的正式科学名称：

高阶声学模型构建及在肺结核诊断及随访中的应用价值探索

Scientific title：

Exploring the Clinical Utility of Advanced Acoustic Models in Tuberculosis Diagnosis and Therapeutic Monitoring

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：

王一玮 

研究负责人：

沙巍 

Applicant：

Yiwei Wang 

Study leader：

Sha Wei 

申请注册联系人电话：

Applicant telephone：

+86 18895380868

研究负责人电话：

Study leader's telephone：

+86 21 6511 5006

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：

18895380868@163.com

研究负责人电子邮件：

Study leader's E-mail：

shfksw@126.com

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：

上海市杨浦区政民路507号

研究负责人通讯地址：

上海市杨浦区政民路507号

Applicant address：

Room 507, Zhengmin Road, Yangpu District, Shanghai 200433, China

Study leader's address：

No. 507 Zhengmin Road, Yangpu District, Shanghai

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：

上海市肺科医院

Applicant's institution：

Shanghai Pulmonary Hospital

研究负责人所在单位：

上海市肺科医院

Affiliation of the Leader：

Shanghai Pulmonary Hospital

是否获伦理委员会批准：

是/Yes

Approved by ethic committee：

Yes

伦理委员会批件文号：

Approved No. of ethic committee：

L25-831

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：

上海市肺科医院医学伦理委员会

Name of the ethic committee：

Instituional Review Board, Shanghai Pulmonary Hospital

伦理委员会批准日期：

Date of approved by ethic committee：

2025-11-27 00:00:00

伦理委员会联系人：

桂涛

Contact Name of the ethic committee：

Gui Tao

伦理委员会联系地址：

上海市杨浦区政民路507号

Contact Address of the ethic committee：

No. 507 Zhengmin Road, Yangpu District, Shanghai

伦理委员会联系人电话：

Contact phone of the ethic committee：

+86 21 65115006

伦理委员会联系人邮箱：

Contact email of the ethic committee：

fkyygcp@163.com

研究实施负责（组长）单位：

上海市肺科医院

Primary sponsor：

Shanghai Pulmonary Hospital

研究实施负责（组长）单位地址：

上海市杨浦区政民路507号

Primary sponsor's address：

No. 507 Zhengmin Road, Yangpu District, Shanghai

试验主办单位(项目批准或申办者)：

Secondary sponsor：

国家：

中国

省(直辖市)：

上海市

市(区县)：

Country：

China

Province：

Shanghai

City：

单位(医院)：

上海市肺科医院

具体地址：

上海市杨浦区政民路507号

Institution
hospital：

Shanghai Pulmonary Hospital

Address：

No. 507 Zhengmin Road, Yangpu District, Shanghai

经费或物资来源：

无

Source(s) of funding：

None

Target disease：

Pulmonary Tuberculosis

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：

病例对照研究 

Study design：

Case-Control study 

研究目的：

1.肺结核早筛声学模型构建，以及场景应用验证。 2.肺结核疗效评价声学模型构建，以及远程随访场景应用验证。  

Objectives of Study：

1. Construction of an acoustic model for early screening of pulmonary tuberculosis, and validation of its application in practical scenarios. 2. Construction of an acoustic model for evaluating the efficacy of pulmonary tuberculosis treatment, and validation of its application in remote follow-up scenarios.

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.菌阳肺结核组：患者均来自上海市肺科医院结核科确诊的菌阳肺结核，符合WHO《结核病诊断与治疗指南（2024年版）》[11]，病原学证据至少满足以下一项：呼吸道样本（痰/灌洗液）培养阳性（分枝杆菌培养确认）或GeneXpert MTB/RIF检测阳性同时影像学支持胸部CT肺结核典型表现。纳入标准：（1）符合WHO《结核病诊断与治疗指南（2024年版）》中活动性肺结核的诊断标准；（2）病原学证据明确，呼吸道样本（痰/灌洗液）分枝杆菌培养阳性或GeneXpert MTB/RIF检测阳性）；（3）首次接受标准抗结核治疗方案，治疗起始时间不超过1个月；（4）年龄在18至80岁之间，男女不限；（5）无合并其他活动性肺部疾病（如慢性阻塞性肺疾病、肺癌等）或严重系统性疾病（如晚期肝病、恶性肿瘤等）；
2.健康对照组：无肺部疾病史的健康成人，年龄、性别与菌阳肺结核组匹配。纳入标准：（1）PPD试验硬结直径<5mm 或结核感染免疫学检测阴性；（2）呼吸道样本（痰/灌洗液）Xpert MTB/RIF检测及培养均阴性；（3）胸部CT未见活动性肺结核典型影像学征象；（4）无咳嗽、咳痰等呼吸道症状或慢性肺病病史。
3.其他呼吸系统疾病组：为控制肺部非特异性声学特征对人工智能模型训练与验证的干扰，同时保证研究对象的代表性与可比性，社区获得性肺炎（CAP）或医院获得性肺炎（HAP）是呼吸系统疾病中常见的气道疾病；慢性阻塞性肺疾病（chronic obstructive pulmonary disease，COPD ）与支气管哮喘（Asthma）是呼吸系统疾病中最常见的慢性气道疾病[12]，都具有长期慢性咳嗽、咳痰和气流受限等表现，能够有效控制研究中的混杂变量，确保纳入患者在疾病特征上的同质性，符合前瞻性队列研究的规范化设计要求。故本研究将“其他呼吸系统疾病组”限定为三类典型疾病：慢性阻塞性肺疾病、支气管哮喘与肺炎。纳入标准：（1） COPD患者组：1）年龄在18至80岁之间，男女不限；2）《全球慢性阻塞性肺疾病倡议（GOLD）2023指南》[13]，确诊为COPD，需满足以下条件：肺功能检查显示FEV1/FVC < 0.7（用力呼气容积/用力肺活量比值小于0.7）；存在慢性咳嗽、咳痰或呼吸困难等典型症状；有吸烟史或其他明确危险因素暴露史。（2）支气管哮喘患者组：1）年龄在18至80岁之间，男女不限；2）根据《全球哮喘防治倡议（GINA）2023指南》[14]，确诊为支气管哮喘，且目前处于稳定期，需满足以下条件：有支气管哮喘确诊史，伴随气道高反应性或可逆性气流受限证据；症状控制良好，无急性发作史（近4周内无哮喘急性加重）；无夜间觉醒、无日常活动受限。（3）肺炎患者组：1）年龄在18至80岁之间，男女不限；2）符合《中国成人社区获得性肺炎诊断和治疗指南（2023版）》标准。

Inclusion criteria

1.Patients in this group were individuals with culture-positive pulmonary tuberculosis diagnosed by the Tuberculosis Department of Shanghai Pulmonary Hospital. All diagnoses met the criteria outlined in the WHO Consolidated Guidelines on Tuberculosis: Module 3: Diagnosis: Rapid diagnostics for tuberculosis detection, 2024 update [11]. The bacteriological evidence required at least one of the following: a positive culture for Mycobacterium tuberculosis from a respiratory specimen (sputum/bronchoalveolar lavage fluid, BALF) or a positive GeneXpert MTB/RIF assay result, accompanied by supportive imaging findings typical of pulmonary tuberculosis on chest CT. Inclusion Criteria: (1) Met the diagnostic criteria for active pulmonary tuberculosis specified in the WHO Consolidated Guidelines on Tuberculosis: Module 3: Diagnosis, 2024 update; (2) Had definitive bacteriological evidence, i.e., a positive culture for Mycobacterium tuberculosis from a respiratory specimen (sputum/BALF) or a positive GeneXpert MTB/RIF assay result; (3) Were treatment-na?ve, having just initiated a standard anti-tuberculosis treatment regimen, with treatment duration not exceeding one month; (4) Were aged between 18 and 80 years, regardless of gender; (5) Had no comorbid active pulmonary diseases (e.g., chronic obstructive pulmonary disease, lung cancer, etc.) or severe systemic diseases (e.g., advanced liver disease, malignancy, etc.).
2.Healthy Control Group: The healthy control group consisted of adults with no history of pulmonary disease, matched in age and sex with the culture-positive pulmonary tuberculosis group. Inclusion Criteria: (1) PPD skin test induration diameter <5 mm or negative immunological test for tuberculosis infection; (2) Negative results for both Xpert MTB/RIF assay and culture from respiratory specimens (sputum/bronchoalveolar lavage fluid); (3) No typical imaging signs of active pulmonary tuberculosis on chest CT; (4) Absence of respiratory symptoms (e.g., cough, expectoration) or history of chronic pulmonary diseases.
3.Other Respiratory Diseases Group: To control for interference from non-specific pulmonary acoustic features during artificial intelligence model training and validation, while ensuring the representativeness and comparability of study subjects, community-acquired pneumonia (CAP) or hospital-acquired pneumonia (HAP) were selected as common acute airway diseases in respiratory disorders. Chronic obstructive pulmonary disease (COPD) and bronchial asthma (Asthma) are the most prevalent chronic airway diseases in respiratory system conditions [12]. Both are characterized by long-term chronic cough, expectoration, and airflow limitation, thereby effectively controlling confounding variables in the study and ensuring homogeneity in disease characteristics among included patients. This approach aligns with the standardized design requirements of a prospective cohort study. Consequently, the "Other Respiratory Diseases Group" in this study was limited to three typical disease categories: chronic obstructive pulmonary disease, bronchial asthma, and pneumonia. Inclusion Criteria: (1) COPD Patient Subgroup: Aged between 18 and 80 years, regardless of gender; Diagnosed with COPD according to the Global Initiative for Chronic Obstructive Lung Disease (GOLD) 2023 Report [13], meeting the following conditions: pulmonary function tests showing FEV?/FVC < 0.7 (ratio of forced expiratory volume in one second to forced vital capacity less than 0.7); presence of typical symptoms such as chronic cough, expectoration, or dyspnea; and a history of smoking or other well-defined risk factor exposure. (2) Bronchial Asthma Patient Subgroup: Aged between 18 and 80 years, regardless of gender; Diagnosed with bronchial asthma according to the Global Initiative for Asthma (GINA) 2023 Strategy Report [14], currently in a stable phase, meeting the following conditions: a confirmed history of bronchial asthma with evidence of airway hyperresponsiveness or reversible airflow limitation; well-controlled symptoms with no history of recent acute exacerbations (no asthma exacerbation within the past 4 weeks); absence of nocturnal awakenings or limitations in daily activities. (3) Pneumonia Patient Subgroup: Aged between 18 and 80 years, regardless of gender; Meeting the diagnostic criteria outlined in the *Chinese Guidelines for the Diagnosis and Management of Community-Acquired Pneumonia in Adults;

排除标准：

1.年龄＜18岁或＞80岁； 2.存在严重语音或呼吸功能障碍（如喉癌、声带损伤等）； 3.患有重度认知功能障碍、精神疾病等不能配合者； 4.拒绝签署知情同意书或中途退出研究、无法完成随访； 5.合并非结核分枝杆菌感染或其他肺部感染性疾病； 6.声学数据采集过程中存在无法控制的强噪声干扰，影响数据有效性。

Exclusion criteria：

1. Age <18 years or >80 years; 2. Presence of severe speech or respiratory dysfunction (e.g., laryngeal cancer, vocal cord injury, etc.); 3.Diagnosis of severe cognitive impairment, psychiatric disorders, or any condition preventing cooperation; 4. Refusal to sign the informed consent form, withdrawal from the study midway, or inability to complete follow-up; 5.Coinfection with nontuberculous mycobacterial infection or other pulmonary infectious diseases; 6.Uncontrollable strong noise interference during acoustic data collection that compromises data validity.

研究实施时间：

Study execute time：

从 From 2025-09-01 00:00:00至 To 2027-03-31 00:00:00  

征募观察对象时间：

Recruiting time：

从From 2025-12-29 00:00:00 至 To 2026-03-31 00:00:00  

干预措施：

Interventions：

组别：

健康对照组

样本量：

133

Group：

Healthy Control Group

Sample size：

干预措施：

无

干预措施代码：

Intervention：

N/A

Intervention code：

组别：

其他呼吸系统疾病组

样本量：

133

Group：

Other Respiratory Diseases Group

Sample size：

干预措施：

无

干预措施代码：

Intervention：

N/A

Intervention code：

组别：

疑似肺结核患者组

样本量：

103

Group：

Suspected Pulmonary Tuberculosis Group

Sample size：

干预措施：

无

干预措施代码：

Intervention：

N/A

Intervention code：

组别：

初治菌阳肺结核组

样本量：

100

Group：

Treatment-na?ve Culture-positive Pulmonary Tuberculosis Group

Sample size：

干预措施：

无

干预措施代码：

Intervention：

N/A

Intervention code：

组别：

菌阳肺结核组

样本量：

133

Group：

Culture-positive Pulmonary Tuberculosis Group

Sample size：

干预措施：

无

干预措施代码：

Intervention：

N/A

Intervention code：

研究实施地点：

Countries of recruitment and research settings：

国家：

 中国

省(直辖市)：

 上海市 

市(区县)：

  

Country：

China 

Province：

Shanghai 

City：

 

单位(医院)：

上海市肺科医院 

单位级别：

三级甲等 

Institution
hospital：

Shanghai Pulmonary Hospital

Level of the institution：

Tertiary A

测量指标：

Outcomes：

指标中文名：

影像学指标

指标类型：

主要指标

Outcome：

Imaging findings

Type：

Primary indicator

测量时间点：

治疗前（第0周）、治疗2周、第2月、第6月（疗程末）

测量方法：

胸部CT影像学指标：为系统评估未治疗菌阳肺结核治疗随访中的胸部CT病灶变化与形态变化（记录病灶范围、空洞大小），结合世界卫生组织（WHO）、美国胸科学会（ATS）及国内肺结核诊断与治疗专家共识，制定标准化评估体系

Measure time point of outcome：

Before treatment (Week 0), at 2 weeks of treatment, at Month 2, and at Month 6 (end of treatment).

Measure method：

Chest CT Imaging Metrics: To systematically evaluate changes in lesion characteristics and morphology on chest CT scans during follow-up of previously untreated, culture-positive pulmonary tuberculosis patients—specifically documenting parameters such as lesion extent and cavity size—a standardized assessment system was developed. This system was established by integrating recommendations from the World Health Organization (WHO) the American Thoracic Society (ATS), and relevant Chinese expert c

指标中文名：

声学数据

指标类型：

主要指标

Outcome：

Acoustic data

Type：

Primary indicator

测量时间点：

治疗前、治疗开始后连续14天（第1-14天）、第2月

测量方法：

通过专业设备采集受试者的连续5声主动咳嗽声音：咳嗽音：频率、音强、时长、音调；使用智能设备作为产品运行终端，结合外接麦克风实现高保真信号采集受试者的咳嗽声学信号（包括时域特征、频域特征）并进行特征提取。

Measure time point of outcome：

Prior to treatment initiation, on each of the first 14 consecutive days following treatment commence

Measure method：

The cough acoustic data were collected using specialized equipment, which recorded a sequence of five consecutive voluntary coughs from each subject. The recorded cough sounds were analyzed for fundamental parameters including frequency, intensity, duration, and pitch. In practice, smart devices served as the operational platform, integrated with an external high-fidelity microphone to achieve high-quality signal acquisition. This setup captured the subjects' cough acoustic signals, and subseque

指标中文名：

呼吸道样本（痰/灌洗液）病原学指标

指标类型：

主要指标

Outcome：

Bacteriological tests on respiratory specimens (sputum/bronchoalveolar lavage fluid)

Type：

Primary indicator

测量时间点：

治疗前（第0周）、治疗2周、第2月、第6月（疗程末）

测量方法：

采用标准抗酸染色涂片和结核分枝杆菌培养评估：记录阴转时间、菌量变化趋势

Measure time point of outcome：

Before treatment (Week 0), at 2 weeks of treatment, at Month 2, and at Month 6 (end of treatment).

Measure method：

Standard acid-fast staining smears and Mycobacterium tuberculosis culture were employed for assessment, documenting the time to negativity and the dynamic trend of bacterial load.

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 18 岁 years
最大 Max age 80 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

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）：

不共享研究数据

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

The research data will not be shared

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：

1. 数据采集方式： 声学数据： 采用“智能终端”的轻量化方案进行高保真信号采集，例如使用指向性麦克风和一次性防风噪海绵罩。 临床数据： 记录包括年龄、性别、呼吸道样本（痰/灌洗液）Xpert MTB/RIF 检测及培养结果、以及胸部 CT 影像学征象等。 2. 数据安全与隐私保护（三重隐私防护）： 去标识化： 使用研究 ID 替代姓名，声学文件进行匿名化处理。 数据隔离： 原始音频与临床数据分离存储于医院加密服务器及区块链可信数据空间，研究人员只接触脱敏后的特征矩阵。 声纹风险控制： 提取 MFCC（梅尔频率倒谱系数）特征后，立即销毁原始音频，确保永不尝试还原个人身份。 传输安全： 数据传输采用 TLS 1.3 加密和医院 VPN。 3. 数据存储和留存： 保存期限： 电子数据将进行离线磁带备份，保存 5 年（研究终止后） 权限管理： 对数据访问实行角色分级权限（研究者/统计师/监查员），并且访问需要双因素认证。

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

1. Data Collection Methods: Acoustic Data: A "smart terminal" lightweight solution was employed for high-fidelity signal acquisition, utilizing directional microphones and disposable wind-noise reduction foam covers. Clinical Data: Recorded parameters included age, gender, results of Xpert MTB/RIF assays and cultures from respiratory specimens (sputum/bronchoalveolar lavage fluid), as well as chest CT imaging findings. 2. Data Security and Privacy Protection (Triple-Layer Privacy Safeguards): De-identification: Study IDs replaced personal names, and acoustic files were anonymized. Data Isolation: Original audio recordings and clinical data were stored separately on encrypted hospital servers and within a blockchain-based trusted data space. Researchers only accessed de-identified feature matrices. Voiceprint Risk Mitigation: Upon extraction of MFCC (Mel-frequency cepstral coefficients) features, the original audio files were immediately destroyed to ensure no possibility of personal identity reconstruction. Transmission Security: Data transmission was protected using TLS 1.3 encryption and the hospital's VPN. 3. Data Storage and Retention: Retention Period: Electronic data were backed up offline on magnetic tapes and retained for 5 years following study termination. Access Control: Role-based access control (Researcher/Statistician/Monitor) was implemented for data access, requiring two-factor authentication.

数据与安全监察委员会：

Data and Safety Monitoring Committee：

无/No

注册人：

Name of Registration：

  2025-12-26 10:55:01