Efficacy and Safety of LLM-Based CBT for Tinnitus
A Multi-agent Large Language Model Conversational AI for Tinnitus Management: The Fudan Tinnitus Doctor Randomised Controlled Trial
1 other identifier
interventional
172
1 country
1
Brief Summary
Given the limited evidence on digital cognitive behavioral therapy (CBT) for chronic subjective tinnitus, particularly interventions supported by large language models (LLMs), this two-arm, 30-day randomized controlled trial will aim to evaluate the efficacy, safety, and usability of an LLM-based conversational CBT intervention compared with a digital education control. Participants with chronic subjective tinnitus will be randomly assigned to either the intervention group, which will receive daily AI-supported CBT sessions through the Fudan Tinnitus Doctor (FTD) system, or the control group, which will receive static tinnitus education materials matched for duration and platform interface. The FTD system will be powered by a multi-agent large language model and will deliver personalized CBT-style dialogues, including psychoeducation, cognitive restructuring, relaxation, and mindfulness guidance. Outcomes will include tinnitus severity, sleep quality, mood symptoms, global improvement, and user adherence and experience.
Trial Health
Trial Health Score
Automated assessment based on enrollment pace, timeline, and geographic reach
participants targeted
Target at P75+ for not_applicable
Started Aug 2025
Shorter than P25 for not_applicable
1 active site
Health score is calculated from publicly available data and should be used for screening purposes only.
Trial Relationships
Click on a node to explore related trials.
Study Timeline
Key milestones and dates
First Submitted
Initial submission to the registry
July 30, 2025
CompletedFirst Posted
Study publicly available on registry
August 1, 2025
CompletedStudy Start
First participant enrolled
August 2, 2025
CompletedPrimary Completion
Last participant's last visit for primary outcome
September 19, 2025
CompletedStudy Completion
Last participant's last visit for all outcomes
September 19, 2025
CompletedNovember 20, 2025
October 1, 2025
2 months
July 30, 2025
November 17, 2025
Conditions
Outcome Measures
Primary Outcomes (1)
Tinnitus Handicap Inventory (THI)
The THI questionnaire, widely used in research, including functional, emotional, and catastrophic subscales. It consists of 25 questions, and answers are rated on a "yes" (4 points), "sometimes" (2 points), and "no" (0 points) scale. The total score is calculated by adding up the scores for all questions and classifying the severity of tinnitus as no handicap (0-16), mild handicap (18-36), moderate handicap (38-56), and severe handicap (58-100).
Baseline, Day 14, and Day 30
Secondary Outcomes (4)
Pittsburgh Sleep Quality Index (PSQI)
Baseline, Day 14, and Day 30
Generalized Anxiety Disorder Scale (GAD-2)
Baseline, Day 14, and Day 30
Patient Health Questionnaire-2 (PHQ-2)
Baseline, Day 14, and Day 30
Patient Global Impression of Change (PGIC)
Day 14, and Day 30
Other Outcomes (3)
System Usability Scale (SUS)
Day 30
Net Promoter Score (NPS)
Day 30
User Engagement Metrics
Continuous during 30-day intervention period
Study Arms (2)
LLM-based Conversational CBT (FTD)
EXPERIMENTALParticipants in this group will receive a 30-day self-directed intervention delivered through the Fudan Tinnitus Doctor (FTD) system, a multi-agent large language model-based conversational AI platform designed to provide tinnitus-focused cognitive behavioural therapy.
Digital Education Control Group
ACTIVE COMPARATORParticipants in this group will receive static, evidence-based tinnitus education materials presented through the same digital platform, matched in format and duration to the intervention group but without interactive AI components.
Interventions
The FTD system will deliver personalized CBT-style dialogues including tinnitus psychoeducation, cognitive restructuring, relaxation training, sleep hygiene, and mindfulness guidance. The system will operate through a secure hospital web platform, accessible via personal devices, and will incorporate retrieval-augmented generation and safety moderation to ensure evidence-based and safe interaction.
Educational modules will include information on tinnitus mechanisms, common coping strategies, and general lifestyle recommendations. The materials will be accessed via the same secure platform as the intervention group to control for exposure time and digital interface effects.
Eligibility Criteria
You may qualify if:
- Diagnosis of subjective tinnitus confirmed by a qualified investigator.
- Tinnitus duration ≥ 3 month prior to screening.
- THI score of ≥ 18
- Aged between 18 and 70 years
- 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.
- Perceptibility: Tinnitus is present and recognizable by the participant under ordinary daily conditions (not only in quiet environments).
- 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.
You may not qualify if:
- Acute-phase tinnitus (duration \< 3 month or tinnitus secondary to acute otologic events).
- Pulsatile or objective tinnitus.
- Unstable symptoms: Fluctuating tinnitus loudness at screening or baseline.
- 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.
- Testing limitations: Inability to adequately complete tinnitus testing procedures or comply with study assessments.
- Prior therapy exposure: Previous history of sound therapy specifically for tinnitus management.
- Concurrent treatments: Ongoing psychotherapy for conditions such as anxiety or depression, or any other psychological treatment that may interfere with the study endpoints.
- 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.
- 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.
Contact the study team to confirm eligibility.
Sponsors & Collaborators
Study Sites (1)
Fudan University Eye Ear Nose and Throat Hospital, Otorhinolaryngology Department
Shanghai, Shanghai Municipality, 200031, China
MeSH Terms
Conditions
Condition Hierarchy (Ancestors)
Study Officials
- PRINCIPAL INVESTIGATOR
Shan Sun, Ph.D
Eye and ENT Hospital of Fudan University
Study Design
- Study Type
- interventional
- Phase
- not applicable
- Allocation
- RANDOMIZED
- Masking
- SINGLE
- Who Masked
- OUTCOMES ASSESSOR
- Purpose
- TREATMENT
- Intervention Model
- PARALLEL
- Sponsor Type
- OTHER
- Responsible Party
- SPONSOR
Study Record Dates
First Submitted
July 30, 2025
First Posted
August 1, 2025
Study Start
August 2, 2025
Primary Completion
September 19, 2025
Study Completion
September 19, 2025
Last Updated
November 20, 2025
Record last verified: 2025-10
Data Sharing
- IPD Sharing
- Will not share
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.