Pai.ACT: AI-Driven ACT Chatbot for Mental Health Triage and Service Evaluation

NCT06808555 | Not Yet Recruiting DMC

• 1 other identifier: 20250114-002-000
• Study Type: interventional
• Target: 340
• Locations: 0 countries
• Sites: N/A

Brief Summary

Parents of children with special needs in Hong Kong often face limited psychological support, which can negatively impact the child rehabilitation process and the well-being of parent-child relationships. To address this gap, we have developed Pai.ACT, the first deep learning-based mental health advisory system for parents. Pai.ACT features an AI chatbot that integrates the counselling principles of Acceptance and Commitment Therapy (ACT) through natural language processing, providing parents with a human-like voice-to-text experience. Using data from chatbot interactions, the Pai.ACT platform offers assessments regarding the individual's psychological inflexibility status and delivers stratified mental health interventions by:

• Low-risk: Users access self-help ACT digital modules tailored to their specific psychological inflexibility processes.
• Moderate-risk: In addition to the self-help modules, users receive 4-6 sessions of video-conferencing-based ACT interventions (45-60 minutes per session) conducted by our trained counseling team.
• High-risk: Users are directed to specialized mental health services provided by collaborating units. The study includes a regional randomised controlled trial (RCT) in Hong Kong's Sha Tin District, in collaboration with the Shatin District Office. The goal of this regional study is to evaluate the feasibility, acceptability, and potential efficacy of combining AI-driven mental health support across all of Hong Kong. Focus group interviews will also explore parents' perceptions of Pai.ACT and help identify the most effective service model for scaling its use. Pai.ACT provides accessible and comprehensive mental health services to Chinese-speaking parents, helping to alleviate the psychological burden of caregiving. By integrating mental health support with child rehabilitation services and non-governmental organisations, Pai.ACT has the potential to enhance family caregivers' well-being, reduce stigma associated with special needs children, and promote more significant mental health awareness in Chinese-speaking communities.

Conditions

Autism Spectrum Disorder; Attention Deficit Disorder With Hyperactivity (ADHD); Neurodevelopmental Disorder (Diagnosis); Dyslexia

Keywords

Smartphone-delivered Therapy; Deep learning; Acceptance and Commitment Therapy; Parents; Children with Special Needs; Parental Support; Artificial Intelligence in Healthcare; Psychological Interventions; Parenting Stress; Regional Randomized Controlled Trial

Outcome Measures

Primary Outcomes (2)

• Parenting Stress

  Parenting stress will be assessed using the Parental Stress Scale (PSS, 18-item, 5-point scale). The PSS evaluates parental satisfaction and strain regarding parenting roles. A higher score represents a higher level of parental stress. The Chinese PSS version, including its parenting stress, will be assessed using the Parental Stress Scale (PSS), which consists of 18 items and uses a 5-point rating system. The PSS is designed to evaluate how parents perceive their roles in terms of satisfaction and strain. A higher score indicates a greater level of parental stress. The Chinese version of the PSS, along with its subscales, has demonstrated strong validity in terms of both convergent and discriminant measures, as well as good internal consistency, with a Cronbach's alpha ranging from .79 to .88 among Chinese parents.

  Change from baseline to immediate and 6 months post-intervention

• Child's Emotional and Behavioural Symptoms

  The Strengths and Difficulties Questionnaire (SDQ) is designed to evaluate a child's emotional and behavioral symptoms. It employs a 3-point Likert scale to assess the following areas: emotional symptoms, conduct problems, hyperactivity/inattention, peer problems, and prosocial behavior. Each of these subscales consists of five items. The Chinese version of the SDQ has demonstrated adequate test-retest reliability, with an Intraclass Correlation Coefficient ranging from .75 to .86, and has shown good discriminant validity among parents in Hong Kong.

  Change from baseline to immediate and 6 months post-intervention

Secondary Outcomes (4)

• Depressive Symptoms

  Change from baseline to immediate and 6 months post-intervention

• Anxiety Symptoms

  Change from baseline to immediate and 6 months post-intervention

• Psychological Flexibility

  Change from baseline to immediate and 6 months post-intervention

• Perceived usability of the mobile app

  At immediate post-intervention and 6 months post-intervention

Study Arms (2)

Pai.ACT Group

EXPERIMENTAL

Parents allocated to this experimental group will gain complete access to the Pai.ACT mobile app.

Behavioral: Pai.ACT Group

Control Group

OTHER

Parents allocated to the Control Group will receive standard family support through Hong Kong's family and children rehabilitation services, which are administered by government-funded units under the Social Welfare Department. Parents will participate in structured psychoeducation sessions focusing on positive parenting and will have access to peer support groups, while their children will receive individualized training plans tailored for neurodevelopmental conditions, in addition to referrals for speech and occupational therapy.

Other: Control Group

Interventions

Pai.ACT Group BEHAVIORAL

The Pai.ACT mobile app is an innovative therapeutic tool that utilizes Acceptance and Commitment Therapy (ACT). It integrates a sophisticated AI algorithm to analyze self-reported data and conversation texts when the user interacts with the AI chatbot and identifies what psychological inflexibility processes are required to be the most essential to be addressed for process-matched ACT interventions. Following interactions with the AI chatbot, Pai.ACT provides a stratified mental health support, categorizing into three risk levels: * Low-risk: Users access self-help ACT digital modules tailored to their specific psychological inflexibility processes. * Moderate-risk: In addition to the self-help modules, users receive 4-6 sessions of video-conferencing-based ACT interventions (45-60 minutes per session) conducted by our trained counseling team. * High-risk: Users are directed to specialized mental health services provided by collaborating units.

Pai.ACT Group

Control Group OTHER

Both the Pai.ACT intervention group and the control group will receive standard family support through Hong Kong's family and children rehabilitation services, which are administered by government-funded units under the Social Welfare Department. Parents will participate in structured psychoeducation sessions focusing on positive parenting and will have access to peer support groups. Their children will receive individualized training plans tailored for neurodevelopmental conditions, in addition to referrals for speech and occupational therapy.

Control Group

Eligibility Criteria

• Age: 19 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• The participants of the study are primary caregivers, specifically parents, must be Cantonese-speaking residents of Hong Kong.
• Eligible parents are required to cohabitate with a child aged 2 to 9 years who has either a confirmed or suspected diagnosis of a neurodevelopmental condition, including Autism Spectrum Disorder (ASD), Attention-Deficit/Hyperactivity Disorder (ADHD), or Developmental Delay (DD). These conditions must be recognised by the Child Assessment Service of the Department of Health and meet the diagnostic criteria specified in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5). The diagnosis or suspected diagnosis must be formally documented in the child's case profile maintained at the collaborating non-governmental organisations.

You may not qualify if:

• Parents diagnosed with severe mental illnesses.
• Pregnant parents or those less than six months postpartum.
• Parents with a developmental disability that impairs their ability to understand the program's content.
• Parents with cognitive, language, communication, visual, or hearing impairments that could hinder their comprehension of the intervention content.
• Parents actively participating in other psychosocial, psychoeducational, or parenting interventions.

Sponsors & Collaborators

• Chinese University of Hong Kong: lead
• Social Welfare Department, Hong Kong: collaborator

MeSH Terms

Conditions

Autism Spectrum Disorder; Attention Deficit Disorder with Hyperactivity; Neurodevelopmental Disorders; Disease; Dyslexia

Interventions

Control Groups

Condition Hierarchy (Ancestors)

Child Development Disorders, Pervasive; Mental Disorders; Attention Deficit and Disruptive Behavior Disorders; Pathologic Processes; Pathological Conditions, Signs and Symptoms; Language Disorders; Communication Disorders; Neurobehavioral Manifestations; Neurologic Manifestations; Nervous System Diseases; Specific Learning Disorder; Learning Disabilities; Signs and Symptoms

Intervention Hierarchy (Ancestors)

Epidemiologic Research Design; Epidemiologic Methods; Investigative Techniques; Research Design; Methods

Central Study Contacts

Yuen Yu CHONG, PhD

CONTACT

(852) 3943 0665; conniechong@cuhk.edu.hk

Pui Tik YAU, MPsyMed

CONTACT

(852) 3943 9915; jamyau@cuhk.edu.hk

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: DOUBLE
• Who Masked: INVESTIGATOR, OUTCOMES ASSESSOR
• Masking Details: Participants will be randomly assigned to either the Pai.ACT Group or Control Group in a 1:1 ratio using a permuted block size of 6, stratified by child's age (preschool, school age). Randomization will utilize sequentially numbered, opaque, sealed envelopes with number cards (1=intervention, 2=control), prepared by clerical staff uninvolved in the study. An independent statistician will generate and conceal randomization details from the research team. Following informed consent and baseline assessments, a blinded research assistant will open the envelopes. Both groups will access their respective interventions through a secure e-link, using unique login credentials tied to their mobile device's ID, accompanied by weekly reminders. The Pai.ACT application includes content-locking features to prevent sharing of its audio and video materials.
• Purpose: TREATMENT
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Assistant Professor

Study Record Dates

• First Submitted: January 30, 2025
• First Posted: February 5, 2025
• Study Start: February 10, 2025
• Primary Completion: February 28, 2026
• Study Completion (Estimated): February 28, 2027
• Last Updated: February 12, 2025

Record last verified: 2025-02

Data Sharing

• IPD Sharing: Will not share