此页面是自动翻译的，不保证翻译的准确性。请参阅 英文版 对于源文本。

Fudan Tinnitus Doctor for Tinnitus Management

2026年5月4日 更新者：Eye & ENT Hospital of Fudan University

A Multi-agent Large Language Model Conversational AI for Tinnitus Management: The Fudan Tinnitus Doctor Randomized Controlled Trial

The goal of this clinical trial is to evaluate whether a conversational artificial intelligence-based digital intervention can improve symptoms in adults with chronic subjective tinnitus.

The main questions it aims to answer are:

Does the Fudan Tinnitus Doctor (FTD) system reduce tinnitus severity as measured by the Tinnitus Handicap Inventory (THI).

Does the FTD system improve sleep quality, anxiety, depression, and overall patient-reported outcomes.

Researchers will compare the FTD system to a non-conversational digital education program to determine whether the AI-based intervention provides greater clinical benefits.

Participants will:

Use either the FTD conversational AI system or a static digital education program for 30 days.

Complete standardized questionnaires assessing tinnitus severity, sleep, mood, and overall improvement at baseline, Day 14, and Day 30.

Engage with the digital platform for tinnitus self-management.

研究概览

地位

尚未招聘

条件

干预/治疗

详细说明

This study is a prospective, two-arm, parallel-group, open-label randomized controlled trial designed to evaluate the efficacy, usability, and safety of a multi-agent large language model (LLM)-based conversational artificial intelligence system (Fudan Tinnitus Doctor, FTD) for the management of chronic subjective tinnitus.

A total of 256 participants will be randomized in a 1:1 ratio to either the FTD intervention or a non-conversational digital education control. The intervention period is 30 days. The FTD system delivers personalized, real-time tinnitus management using a multi-agent architecture integrating cognitive behavioral therapy (CBT)-based strategies, including psychoeducation, cognitive restructuring, relaxation training, and sleep hygiene guidance. The control group receives a static digital program consisting of educational materials and a fixed-response question-and-answer module.

The primary outcome will be the change in tinnitus severity measured by the Tinnitus Handicap Inventory (THI) from baseline to Day 30. Secondary outcomes will include sleep quality (Pittsburgh Sleep Quality Index, PSQI), anxiety (GAD-2), depression (PHQ-2), and overall perceived improvement (Patient Global Impression of Change, PGIC). Exploratory outcomes will assess usability (System Usability Scale, SUS), satisfaction (Net Promoter Score, NPS), and engagement metrics. All outcomes will be analyzed using mixed-effects models under the intention-to-treat principle.

研究类型

介入性

注册 (估计的)

256

阶段

  • 不适用

联系人和位置

本节提供了进行研究的人员的详细联系信息，以及有关进行该研究的地点的信息。

学习联系方式

学习地点

  • 中国
      • Shanghai、中国、200031
        • Fudan University Eye Ear Nose and Throat Hospital, Otorhinolaryngology Department
        • 接触：

参与标准

研究人员寻找符合特定描述的人，称为资格标准。这些标准的一些例子是一个人的一般健康状况或先前的治疗。

资格标准

适合学习的年龄

  • 成人
  • 年长者

接受健康志愿者

不

描述

Inclusion Criteria:

  1. Diagnosis of subjective tinnitus confirmed by a qualified investigator.
  2. Tinnitus duration ≥ 3 month prior to screening.
  3. THI score of ≥ 18
  4. Aged between 18 and 70 years
  5. The ability to use a smartphone: Both groups will receive therapeutic support and disease management primarily through a mobile application or web-based platform. This requires functional ability to operate the provided software and willingness to engage with the digital intervention protocol.
  6. Perceptibility: Tinnitus is present and recognizable by the participant under ordinary daily conditions (not only in quiet environments).
  7. Compliance and consent: Participant is assessed by the Investigator as able to understand study procedures, voluntarily agrees to participate, is willing to comply with all trial-related requirements, and provides signed informed consent prior to performance of any protocol-specified procedure.

Exclusion Criteria:

  1. Acute-phase tinnitus (duration < 3 month or tinnitus secondary to acute otologic events).
  2. Pulsatile or objective tinnitus.
  3. Unstable symptoms: Fluctuating tinnitus loudness at screening or baseline.
  4. Psychiatric contraindication: History or current presence of severe psychiatric disorders (e.g., major depressive disorder with recent suicidality, schizophrenia) that, in the opinion of the Investigator, may interfere with study participation or data validity.
  5. Testing limitations: Inability to adequately complete tinnitus testing procedures or comply with study assessments.
  6. Prior therapy exposure: Previous history of sound therapy specifically for tinnitus management.
  7. Concurrent treatments: Ongoing psychotherapy for conditions such as anxiety or depression, or any other psychological treatment that may interfere with the study endpoints.
  8. Concurrent trial participation: Active participation in another interventional research study that, in the opinion of the Investigator, could affect tinnitus symptoms or interact with study procedures.
  9. Investigator judgment: Any condition (medical, surgical, psychiatric, or social) or factor which, in the Investigator's judgment, renders the subject unsuitable for participation, places the patient at higher risk, or may interfere with compliance or scientific validity of the trial.

学习计划

本节提供研究计划的详细信息，包括研究的设计方式和研究的衡量标准。

研究是如何设计的？

设计细节

  • 主要用途：治疗
  • 分配：随机化
  • 介入模型：并行分配
  • 屏蔽：单身的

武器和干预

参与者组/臂
干预/治疗
实验性的：FTD Conversational AI Intervention
Participants in this arm will use the Fudan Tinnitus Doctor (FTD) system, a multi-agent large language model-based conversational AI platform that delivers personalized tinnitus management strategies based on cognitive behavioral therapy principles.
设备：Fudan Tinnitus Doctor (FTD) System
The FTD system is a multi-agent conversational artificial intelligence platform that delivers personalized tinnitus management through a secure web-based interface. It supports multimodal interaction (text and voice) and integrates a large language model, retrieval-augmented generation, and multi-agent collaboration to provide cognitive behavioral therapy-based interventions, including psychoeducation, cognitive restructuring, relaxation techniques, and sleep hygiene guidance.
有源比较器：Digital Education Control
Participants in this arm will receive access to a non-conversational digital program consisting of static educational materials and a fixed-response question-and-answer module related to tinnitus, sleep, and mental health.
设备：Non-conversational Digital Education Program
Participants in this arm will receive access to a non-conversational digital tinnitus self-management program delivered through the same secure web-based interface as the intervention group. The program provides static educational materials and a fixed-response question-and-answer module related to tinnitus, sleep, and mental health.

研究衡量的是什么？

主要结果指标

结果测量
措施说明
大体时间
耳鸣残疾量表 (THI)
大体时间：基线、第14天和第30天
THI问卷在研究中广泛使用，包含功能性、情感性和灾难性三个分量表。 该问卷共包含25个问题，答案采用"是"（4分）、"有时"（2分）和"否"（0分）的评分标准。 总分通过累加所有问题的得分计算得出，并根据耳鸣严重程度分为无残疾（0-16分）、轻度残疾（18-36分）、中度残疾（38-56分）和重度残疾（58-100分）。
基线、第14天和第30天

次要结果测量

结果测量
措施说明
大体时间
患者健康问卷-2 (PHQ-2)
大体时间：基线、第14天和第30天
PHQ-2将评估过去两周内的抑郁症状。 两项条目均按0（“完全没有”）到3（“几乎每天”）进行评分。 总分范围为0至6分，分数越高表明抑郁症状越严重。 得分≥3分提示具有临床意义的抑郁症。
基线、第14天和第30天
患者整体印象变化量表 (PGIC)
大体时间：第14天和第30天
PGIC将评估参与者自开始干预以来对整体改善的主观感受。 该量表采用7级李克特评分法，从1分（“显著改善”）到7分（“显著恶化”），分数越低代表感知改善程度越高。
第14天和第30天
Generalized Anxiety Disorder Scale (GAD-2)
大体时间：Baseline, Day 14, and Day 30]
The GAD-2 will assess anxiety symptoms over the past two weeks. Each of the two items is rated from 0 ("not at all") to 3 ("nearly every day"). The total score ranges from 0 to 6, with higher scores indicating greater anxiety. A score ≥3 suggests clinically significant anxiety.
Baseline, Day 14, and Day 30]
Pittsburgh Sleep Quality Index (PSQI)
大体时间：Baseline, Day 14, and Day 30
The PSQI will be used to evaluate subjective sleep quality over the past month. It comprises 19 items yielding seven component scores (subjective sleep quality, latency, duration, efficiency, disturbances, use of sleep medication, and daytime dysfunction). The global PSQI score ranges from 0 to 21, with higher scores indicating worse sleep quality.
Baseline, Day 14, and Day 30

其他结果措施

结果测量
措施说明
大体时间
净推荐值 (NPS)
大体时间：第30天
净推荐值（NPS）将用于评估参与者在第30天向他人推荐复旦耳鸣医生系统的可能性。 参与者将在0（完全不可能）到10（极有可能）的评分尺度上评估其推荐可能性。
第30天
System Usability Scale (SUS)
大体时间：Day 30
The System Usability Scale (SUS) will be used to evaluate participants' perceived usability and satisfaction with the Fudan Tinnitus Doctor (FTD) conversational AI system at Day 30. The SUS is a 10-item questionnaire rated on a 5- point scale. The total score will be calculated as (sum of adjusted item scores × 2.5), ranging from 0 to 100, with higher scores indicating greater usability.
Day 30
User Engagement Metrics
大体时间：Continuous during 30-day intervention period

User engagement will be assessed using three predefined system-recorded metrics:

(1)Login Frequency: Number of logins. (2)Active Session Duration: Total time (minutes) spent actively interacting with the system, excluding inactive periods and time spent completing study assessments. (3)Conversation Turns: Number of complete interaction cycles, defined as one user input followed by one system response.

Higher values indicate greater engagement.
Continuous during 30-day intervention period

合作者和调查者

在这里您可以找到参与这项研究的人员和组织。

赞助

Eye & ENT Hospital of Fudan University

调查人员

  • 首席研究员：Shan Sun、Eye and ENT Hospital of Fudan University

研究记录日期

这些日期跟踪向 ClinicalTrials.gov 提交研究记录和摘要结果的进度。研究记录和报告的结果由国家医学图书馆 (NLM) 审查，以确保它们在发布到公共网站之前符合特定的质量控制标准。

研究主要日期

学习开始 (估计的)

2026年5月1日

初级完成 (估计的)

2027年5月30日

研究完成 (估计的)

2027年5月30日

研究注册日期

首次提交

2026年4月23日

首先提交符合 QC 标准的

2026年4月23日

首次发布 (实际的)

2026年4月30日

研究记录更新

最后更新发布 (实际的)

2026年5月7日

上次提交的符合 QC 标准的更新

2026年5月4日

最后验证

2026年4月1日

更多信息

与本研究相关的术语

其他相关的 MeSH 术语

其他研究编号

  • 2025072

计划个人参与者数据 (IPD)

计划共享个人参与者数据 (IPD)？

不

IPD 计划说明

Deidentified individual participant data (IPD) collected for this trial, including outcome measures and baseline characteristics, will be made available upon reasonable request to qualified researchers. Data sharing will require prior approval from the Institutional Review Board of the Eye & ENT Hospital of Fudan University. The DeepSeek-R1 671B model used to support the intervention is open-source and publicly accessible at https://github.com/deepseek-ai/DeepSeek-R1.

药物和器械信息、研究文件

研究美国 FDA 监管的药品

不

研究美国 FDA 监管的设备产品

不

此信息直接从 clinicaltrials.gov 网站检索，没有任何更改。如果您有任何更改、删除或更新研究详细信息的请求，请联系 register@clinicaltrials.gov. clinicaltrials.gov 上实施更改，我们的网站上也会自动更新.

订阅