CClinicalTrials.gg
Not yet recruitingNCT07699042Updated Jul 16, 2026

Efficacy of Digital CBT-I Utilizing Embodied Artificial Intelligence Agent in Virtual Reality

An interventional study of App-based dCBT-I with AI chatbot and VR-enhanced dCBT-I with embodied AI agent in Insomnia, sponsored by Chinese University of Hong Kong. Not yet recruiting at 1 site in Hong Kong. Open to participants aged 18 Years to 65 Years. Per ClinicalTrials.gov, last updated 2026-07-16.

Sponsored by Chinese University of Hong Kong · Not applicable, Interventional, and Supportive care

Phase
Not applicable
Study type
Interventional
Enrollment
168
Allocation
Randomized
Ages
18 Years to 65 Years
Sex
All
01

Study summary

The goal of this clinical trial is to evaluate whether a virtually embodied artificial intelligence (AI) agent delivered via VR-enhanced digital cognitive behavioral therapy for insomnia (dCBT-I) can improve insomnia outcomes and treatment adherence in adults with insomnia.

The main questions it aims to answer are:

- Does VR-enhanced dCBT-I with an embodied AI agent lead to greater improvements in insomnia symptoms compared to app-based dCBT-I with an AI chatbot at post-intervention and 3-month follow-up?

Researchers will compare VR-enhanced dCBT-I with an embodied AI agent to app-based dCBT-I with an AI chatbot to see if the VR-enhanced intervention results in significantly improved clinical outcomes and adherence.

Participants will:

  • Be randomly assigned to either the VR-enhanced AI agent intervention group or the app-based AI chatbot control group
  • Complete a digital cognitive behavioral therapy for insomnia (dCBT-I) program with either a virtually embodied AI agent (VR-based) or a chatbot-based application
  • Undergo assessments at baseline, post-intervention, and 3-month follow-up
02

Conditions studied

03

In context

Sleep Initiation and Maintenance Disorders

1,856 studies on the registry are indexed under Sleep Initiation and Maintenance Disorders; 594 are open to participants now.

This study's planned enrollment of 168 is above the median of 73 across 1,631 interventional studies indexed under Sleep Initiation and Maintenance Disorders.

Browse Sleep Initiation and Maintenance Disorders studies →

Lead sponsor

Chinese University of Hong Kong is the lead sponsor of 1,419 studies on the registry; 487 are open to participants now.

Counted across the registry records on this site, refreshed daily.

04

Who can participate

Ages eligible
18 Years to 65 Years
Sexes eligible
All
Accepts healthy volunteers
No

Inclusion criteria

  • Adults of Chinese ethnicity, aged between 18 and 65 years.
  • Presence of insomnia, as indicated by a score of 10 or higher on the ISI.
  • Meeting the DSM-IV-TR diagnostic criteria for insomnia disorder. The 1-month duration criterion in DSM-IV-TR rather than the 3-month criterion in DSM-V is adopted to broaden the clinical relevance of the study findings.
  • Willing to provide online informed consent to participate in the study.
  • Willing to comply with the requirements outlined in the study protocol.
  • Possession of a smartphone and consistent internet access for smartphone use.
  • Acceptance of the terms of service and privacy policies of the mobile apps used for intervention delivery.

Exclusion criteria

Exclusion Criteria:

  • A current or history of any sleep disorders other than insomnia disorder, such as narcolepsy, obstructive sleep apnea, and restless legs syndrome.
  • A current or history of mental retardation or neuropsychiatric disorders other than depression or anxiety or stress disorders (as they are considered treatment outcomes), including bipolar disorder, schizophrenia, and substance use disorder.
  • Presence of serious suicidality, demonstrated by ideation with a plan or a previous suicide attempt.
  • Currently receiving long-term pharmacological treatment, including sleep-promoting agents.
  • Currently undergoing structured psychotherapy.
  • A current or history of significant visual, auditory, or balance impairment.
  • A current or history of epilepsy
  • Subject who is preparing for pregnancy or pregnant
  • A current or history of any voice, speech, language disorders and learning difficulties.
  • A current or history of severe health conditions (e.g., stroke, heart attack)
  • Engaged in shiftwork or trans-meridian travel within the past 3 months or during the study.
05

Study design

Phase
Not applicable
Primary purpose
Supportive care
Allocation
Randomized
Intervention model
Parallel assignment
Masking
Single (Outcomes assessor)
Enrollment
168 participants (estimated)

Study arms

  • Experimental
    App-based dCBT-I with AI chatbot

    Participants will receive digital cognitive behavioral therapy for insomnia through a mobile application featuring a text-based artificial intelligence chatbot, which capable of two-way interactive communication. The chatbot will provide psychoeducation, behavioral strategies, cognitive techniques, and relaxation sessions throughout the intervention period.

    Behavioral: App-based dCBT-I with AI chatbot

  • Active comparator
    VR-enhanced dCBT-I with embodied AI agent

    Participants will receive digital cognitive behavioral therapy for insomnia in a virtual reality environment. The intervention will be delivered by a virtually embodied artificial intelligence agent capable of two-way interactive communication. The embodied AI agent will provide the same therapeutic content as the app-based intervention, including psychoeducation, behavioral strategies, cognitive techniques, and relaxation sessions, while leveraging immersive virtual reality features to enhance user engagement and therapeutic interaction.

    Behavioral: VR-enhanced dCBT-I with embodied AI agent

Interventions

  • BehavioralApp-based dCBT-I with AI chatbot

    Digital cognitive behavioral therapy for insomnia with two-way interactive, intelligent, and text-based conversational agents

  • BehavioralVR-enhanced dCBT-I with embodied AI agent

    Digital cognitive behavioral therapy for insomnia delivered in virtual reality with a two-way interactive, virtually embodied, and intelligent AI agent.

06

What researchers measure

Primary outcomes

  1. Insomnia Severity Index

    the severity of insomnia symptoms

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  2. Insomnia Module in the Diagnostic Interview for Sleep Disorder (DISP)

    the severity of insomnia symptoms

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

Secondary outcomes

  1. Sleep onset latency (SOL)

    7-day sleep diary

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  2. Wake after sleep onset (WASO)

    7-day sleep diary

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  3. Sleep efficiency (SE)

    7-day sleep diary

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  4. Total sleep time (TST)

    7-day sleep diary

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  5. The Pre-Sleep Arousal Scale

    cognitive and somatic manifestations of arousal near bedtime Total score ranges from 8 to 40. Higher scores suggest increased cognitive and somatic arousal before sleep.

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  6. Ford Insomnia Response to Stress Test

    personal vulnerability to stress-related insomnia Total score ranges from 9 to 36. Higher scores suggest a greater likelihood of stress-induced insomnia.

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  7. Reduced Morningness and Eveningness Questionnaire

    Chronotype preference. Total score ranges from 4 to 25. Higher scores suggest a morning chronotype, while lower scores indicate an evening chronotype.

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  8. The Dysfunctional Beliefs and Attitudes about Sleep Scale

    Faulty sleep-related beliefs and cognitions, which are cognitive aspects typically involved in the maintenance of insomnia. Total score range of 0 to 160, with higher scores indicating stronger dysfunctional beliefs about sleep.

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  9. Depression, Anxiety and Stress Scale - 21 Items

    The DASS-21 contains 21 items in three subscales, which assess symptoms of depression, anxiety, and stress

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  10. Patient Health Questionnaire-9

    The severity of depressive symptoms. Total score range of 0 to 27, where higher scores signify higher levels of depressive symptoms.

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  11. General Anxiety Disorder-7

    The severity of anxiety symptoms. Total score range of 0 to 21, with higher scores reflecting higher levels of anxiety symptoms

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  12. The Sleep Hygiene Index

    The practice of sleep hygiene behaviors. Total score ranges from 0 to 52. Higher scores reflect poorer sleep hygiene practices.

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  13. The Multidimensional Fatigue Inventory

    Five dimensions of fatigue (general fatigue, physical fatigues, mental fatigue, decreased motivation, and decreased activities). Total score ranges from 20 to 100. Higher scores indicate greater fatigue levels.

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  14. Sleep Self-Efficiency Scale

    A 9-item scale evaluating abilities such as falling asleep quickly, returning to sleep after waking, and preventing a poor night's sleep from disrupting daily activities.

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  15. Revised Attitudes Toward Internet Questionnaire

    evaluates users' psychological, behavioral, and emotional responses to being online.

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  16. Credibility and expectancy questionnaire

    measure a participant's treatment credibility and outcome expectancy in therapy.

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  17. Motivation to Change Sleep Behaviors questionnaire

    Assess the level of motivation to change sleep behaviors.

    Time frame: a) baseline; b) post-intervention (1-month after baseline); c) 3-month after intervention (4-month after baseline)

  18. Acceptability E-scale questionnaire

    evaluate patients' impressions of computerized or e-health programs.

    Time frame: post-intervention (1-month after baseline)

  19. The Embodied Conversational Agents Trust Questionnaire

    measure a user's trust in a virtual agent or avatar. It evaluates trust across two dimensions: perceived credibility and perceived benevolence.

    Time frame: post-intervention (1-month after baseline)

  20. Adherence questionnaire

    Assess the frequency of engagement in, and adherence to, the behavioral strategies and sleep-related recommendations taught during the program.

    Time frame: post-intervention (1-month after baseline)

  21. User survey

    Measure perceived system usability, safety, interactivity, personalization, and overall user experience.

    Time frame: post-intervention (1-month after baseline)

07

Study locations

1 site
  • 7/F, Sleep Assessment Unit, Shatin Hospital, 33 A Kung Kok Street, Ma On Shan, New Territories
    Hong Kong, Hong Kong
08

References and documents

Individual participant data

Plan to share: No — Individual participant data collected during this study will not be made publicly available because participant consent does not include permission for data sharing outside the study team and because of considerations related to participant privacy and confidentiality.

No publications or documents are linked to this record.

09

Updates

Tracking since Sep 25, 2026
No changes since tracking began. The registry record was last updated on Jul 16, 2026, before this site started recording changes on Sep 25, 2026. Its history is on ClinicalTrials.gov ↗
10

Registry details

Key details

Study ID
NCT07699042
Lead sponsor
Chinese University of Hong Kong
Responsible party
Tim M. H. Li (Assistant Professor, Chinese University of Hong Kong) — Principal investigator
First posted
Jul 13, 2026
Start date
Oct 23, 2026 (estimated)
Primary completion
Sep 30, 2028 (estimated)
Completion
Apr 22, 2029 (estimated)
Last update
Jul 16, 2026

Study contacts

Dr. Tim MH Li
Contact
manholi@cuhk.edu.hk
+852 61150322
Ms. Phoebe K.Y. Chan
Contact
mastersleep@cuhk.edu.hk
+852 53202853

Oversight

Data monitoring committee
Yes
FDA-regulated drug
No
FDA-regulated device
No
View the source record on ClinicalTrials.gov ↗

Not currently enrolling

This study is not yet recruiting, as verified in Jun 2026. You cannot join it, but the record below documents what was studied.

Follow this study

Get an email when the registry record changes — status, dates, results — or when someone posts here.

Sign in to follow

Discussion

Questions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.

Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.

Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.

Start the discussion