Development of a Machine Learning-Based Prognosis Prediction Model for Tinnitus Patients Using a Large Sample Size: A Retrospective Observational Clinical Study
|
注册号: Registration number: |
ChiCTR2600126731 |
|
最近更新日期: Date of Last Refreshed on: |
2026-06-15 10:57:44 |
|
注册时间: Date of Registration: |
2026-06-15 00:00:00 |
|
注册号状态: |
预注册 |
|
Registration Status: |
Prospective registration |
|
注册题目: |
基于机器学习的大样本耳鸣患者预后预测模型构建:一项回顾性观察性临床研究 |
|
Public title: |
Development of a Machine Learning-Based Prognosis Prediction Model for Tinnitus Patients Using a Large Sample Size: A Retrospective Observational Clinical Study |
|
注册题目简写: |
|
|
English Acronym: |
|
|
研究课题的正式科学名称: |
基于机器学习的大样本耳鸣患者预后预测模型构建:一项回顾性观察性临床研究 |
|
Scientific title: |
Development of a Machine Learning-Based Prognosis Prediction Model for Tinnitus Patients Using a Large Sample Size: A Retrospective Observational Clinical 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: |
季迪 |
研究负责人: |
季迪 |
|
Applicant: |
Di Ji |
Study leader: |
Di Ji |
|
申请注册联系人电话: Applicant telephone: |
+86 23 6877 4527 |
研究负责人电话: Study leader's telephone: |
+86 23 6877 4527 |
|
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: |
1065849595@qq.com |
研究负责人电子邮件: Study leader's E-mail: |
1065849595@qq.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: |
重庆市沙坪坝区新桥正街183号 |
研究负责人通讯地址: |
重庆市沙坪坝区新桥正街183号 |
|
Applicant address: |
183 Xinqiao Main Street, Shapingba District, Chongqing |
Study leader's address: |
183 Xinqiao Main Street, Shapingba District, Chongqing |
|
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: |
中国人民解放军陆军军医大学第二附属医院耳鼻咽喉科 |
||
|
Applicant's institution: |
Otolaryngology Department, the Second Affiliated Hospital of Army Medical University |
||
|
研究负责人所在单位: |
中国人民解放军陆军军医大学第二附属医院耳鼻咽喉科 |
||
|
Affiliation of the Leader: |
Otolaryngology Department, the Second Affiliated Hospital of Army Medical University |
||
|
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: |
2026-研第 131-01 |
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: |
中国人民解放军陆军军医大学第二附属医院医学伦理委员会 |
||
|
Name of the ethic committee: |
Medical Ethics Committee of the Second Affiliated Hospital of Army Medical University, PLA |
||
|
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: |
宋彩萍 |
||
|
Contact Name of the ethic committee: |
Caiping Song |
||
|
伦理委员会联系地址: |
中国人民解放军陆军军医大学第二附属医院医学伦理委员会办公室 |
||
|
Contact Address of the ethic committee: |
Medical Ethics Committee Office of the Second Affiliated Hospital of Army Medical University |
||
|
伦理委员会联系人电话: Contact phone of the ethic committee: |
+86 23 6875 5422 |
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: |
中国人民解放军陆军军医大学第二附属医院 |
||||||||||||||||||||||
|
Primary sponsor: |
Second Affiliated Hospital of Army Medical University |
||||||||||||||||||||||
|
研究实施负责(组长)单位地址: |
重庆市沙坪坝区新桥正街83号 |
||||||||||||||||||||||
|
Primary sponsor's address: |
183 Xinqiao Zheng Street, Shapingba District, Chongqing |
||||||||||||||||||||||
|
试验主办单位(项目批准或申办者): Secondary sponsor: |
|
||||||||||||||||||||||
|
经费或物资来源: |
重庆市科卫联合课题面上项目:虚拟现实场景下多元复合声治疗听力损失型慢性耳鸣患者的疗效分析及预测模型构建2026MSXM080 |
||||||||||||||||||||||
|
Source(s) of funding: |
Chongqing Municipal Science and Health Joint Research Programme: Analysis of the Efficacy of Multimodal Sound Therapy in Virtual Reality Settings for Patients with Chronic Tinnitus Associated with Hearing Loss, and the Development of a Predictive Model 2026MSXM080 |
||||||||||||||||||||||
|
Target disease: |
Tinnitus |
||||||||||||||||||||||
|
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. 主要目的: (1)开发并验证一个基于机器学习的预测模型,用于预测广泛性耳鸣患者 在 3 个月随访期内,其耳鸣严重程度(以 VAS 评分下降程度衡量)的预后结局。 (2)比较逻辑回归(LR)、随机森林(RF)、极端梯度提升(XGBoost)和 支持向量机(SVM)四种算法在耳鸣预后预测任务中的性能,确定最优模型。 2. 次要目的: (1)探索不同治疗方式(如偏头痛治疗、声治疗、鼓室注射等)与患者基线特 征之间的交互作用对预后的影响。 (2)分析心理共病(焦虑、抑郁、睡眠障碍)与耳鸣预后之间的关联。 2.3 预期结果: (1)获得一个具有高区分度(预期验证集 AUC > 0.85)和良好校准度的耳鸣 预后预测模型。 (2)明确最优机器学习算法(预期为集成学习算法如 RF 或 XGBoost)。 (3)明确关键预测因子排名,可能包括治疗方式、基线 VAS/THI 评分、听力损 失程度、HADS/PSQI 评分、病程等。 |
||||||||||||||||||||||
|
Objectives of Study: |
1. Primary Objectives: (1) To develop and validate a machine learning-based predictive model for forecasting the prognostic outcomes of patients with generalised tinnitus regarding the severity of their tinnitus (measured by the degree of decline in VAS scores) over a 3-month follow-up period. (2) To compare the performance of four Support Vector Machine (SVM) algorithms—Logistic Regression (LR), Random Forest (RF), XGBoost, and Support Vector Machines (SVM) in the task of tinnitus prognosis prediction, and to identify the optimal model. 2. Secondary Objectives: (1) To explore the impact of interactions between different treatment modalities (e.g. migraine treatment, sound therapy, tympanic membrane injection, etc.) and patient baseline characteristics on prognosis. (2) Analyse the association between psychological comorbidities (anxiety, depression, sleep disorders) and tinnitus prognosis. 2.3 Expected Outcomes: (1) Obtain a tinnitus prognosis prediction model with high discriminatory power (expected validation set AUC > 0.85) and good calibration. (2) Identify the optimal machine learning algorithm (expected to be an ensemble learning algorithm such as RF or XGBoost). (3)Determine the ranking of key predictive factors, which may include treatment modality, baseline VAS/THI scores, degree of hearing loss, HADS/PSQI scores, and duration of illness. |
||||||||||||||||||||||
|
药物成份或治疗方案详述: |
|
||||||||||||||||||||||
|
Description for medicine or protocol of treatment in detail: |
|
||||||||||||||||||||||
|
纳入标准: |
1.90 岁>= 年龄>= 18 岁。 2.主诉为耳鸣(病程不限,耳鸣性质不限)。 |
||||||||||||||||||||||
|
Inclusion criteria |
1.90 years >= age >= 18 years. 2. The chief complaint was tinnitus (regardless of the course of disease or the nature of tinnitus). |
||||||||||||||||||||||
|
排除标准: |
1.由活动性外耳/中耳疾病(如急性中耳炎)、梅尼埃病急性期、听神经瘤、颅脑外伤等明确结构性病变引起的耳鸣。 2.患有严重的精神疾病(如精神分裂症、双相情感障碍)或认知障碍。 3.有颅脑外伤或耳科手术史或计划实施影响听力的手术等。 4.妊娠或哺乳期妇女。 5.随访数据缺失、不完整。 |
||||||||||||||||||||||
|
Exclusion criteria: |
1. Tinnitus caused by active external or middle ear diseases (such as acute otitis media), acute stage of Meniere's disease, acoustic neuroma, and cranial brain trauma, etc., which are clearly caused by structural lesions. 2. Patients with severe mental disorders (such as schizophrenia, bipolar disorder) or cognitive impairments. 3. Those with a history of cranial brain trauma or ear surgery or those planning to undergo surgeries that affect hearing. 4. Pregnant or lactating women. 5. Missing or incomplete follow-up data. |
||||||||||||||||||||||
|
研究实施时间: Study execute time: |
从 From 2026-06-20 00:00:00至 To 2027-06-20 00:00:00 |
征募观察对象时间: Recruiting time: |
从From 2026-06-20 00:00:00 至 To 2027-06-20 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): |
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): |
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: |
EDC |
|
Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture: |
EDC |
|
数据与安全监察委员会: Data and Safety Monitoring Committee: |
暂未确定/Not yet |