Efficacy and Safety of LLM-Based CBT for Tinnitus

Not Applicable

Recruiting

• Conditions: Tinnitus

• Registration Number: NCT07097909
• Lead Sponsor: Eye & ENT Hospital of Fudan University

Brief Summary

Given the limited evidence on digital cognitive behavioral therapy (CBT) for chronic subjective tinnitus, especially those powered by large language models (LLMs), this single-arm, 4-week open-label trial aims to evaluate the preliminary efficacy and safety of an LLM-based intelligent CBT intervention. Participants with moderate to severe tinnitus will use a customized mobile application delivering daily CBT modules, including cognitive restructuring and relaxation training. Outcomes include tinnitus severity, sleep quality, mood symptoms, and user adherence.

Detailed Description

Not available

Study Timeline

• Study First Submitted: 2025-07-30
• Study First Submitted QC: 2025-07-30
• Status Verified: 2025-08
• Study Start: 2025-08-01
• Study First Posted: 2025-08-01
• Last Update Submitted: 2025-08-06
• Last Update Posted: 2025-08-12
• Primary Completion: 2027-08-01
• Study Completion: 2027-08-01

Recruitment & Eligibility

• Status: RECRUITING
• Sex: All
• Target Recruitment: 93

Inclusion Criteria

• Chronic subjective tinnitus lasting for ≥3 months;
• Tinnitus Handicap Inventory (THI) score ≥18;
• Age between 18 and 70 years, regardless of gender;
• Ability to use a smartphone;
• Willingness to provide written informed consent.

Exclusion Criteria

• Pulsatile tinnitus or objective tinnitus;
• Organic ear diseases;
• Severe psychiatric disorders (e.g., schizophrenia);
• Recent participation in other CBT interventions or drug trials for tinnitus;
• Determined by the investigators to be unsuitable for participation in this study.

Study & Design

• Study Type: INTERVENTIONAL
• Study Design: SINGLE_GROUP

Primary Outcome Measures

Name	Time	Method
Tinnitus Handicap Inventory (THI)	2, 4 weeks from baseline	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).

Secondary Outcome Measures

Name	Time	Method
Visual Analogue Scale (VAS)	2, 4 weeks from baseline	Subjective perception of tinnitus loudness will be assessed using the VAS. Participants will be asked to rate the loudness of the tinnitus on a scale ranging from 0 (no tinnitus) to 10 (tinnitus could not be louder).
Hospital Anxiety and Distress Scale (HADS)	2, 4 weeks from baseline	HADS is a 14-item self-report questionnaire with two 7-item subscales to assess symptoms of anxiety (HADS-A) and depression (HADS-D)\[31\]. Each item is scored from 0-3, with each subscale ranging from 0-21. A threshold value of 8 or greater for the HADS-A or HADS-D indicates clinically significant symptoms of anxiety or depression.
Athens Insomnia Scale (AIS)	2, 4 weeks from baseline	The AIS comprises eight items that commonly measure difficulties in falling asleep or maintaining sleep to quantify the presence of insomnia. The higher the AIS score, the lower the sleep quality and mental status. The AIS identifies three types of sleep disorders: no insomnia (score below 4), suspicious (4-6), and insomnia (score between 7-24).

Trial Locations

Locations (1)

Fudan University Eye Ear Nose and Throat Hospital, Otorhinolaryngology Department; 🇨🇳 Shanghai, Shanghai, China