Pai.ACT - An Artificial Intelligence Driven Chatbot Assisted ACT (Full Scale RCT)
Artificial Intelligence-driven, Chatbot-assisted Acceptance and Commitment Therapy (Pai.ACT) for Parents of Young Children With Neurodevelopmental Disorders: A Randomised Controlled Trial
1 other identifier
interventional
210
0 countries
N/A
Brief Summary
Interventions for parents of children with NDD face two pivotal challenges. Firstly, many overlook the consequential influence of parenting stress, symptoms of parental anxiety and depression on the well-being of parent-child dyads. Though some address parenting stress, they fall short of considering comprehensive health outcomes. Secondly, current evidence has supported ACT as an empirically validated, transdiagnostic psychotherapeutic intervention for parents with dual benefits for the parent-child dyads, but the treatment delivery (e.g., group-based and guided online approaches) is primarily in-person, demanding the presence of expert personnel in every session, limiting its scalability and accessibility. Unlike other psychotherapies like CBT and mindfulness, conventional ACT sessions often adopt a 'one-size-fits-all' strategy, using standardised and pre-packed exercises lacking the personalisation necessary to address individual variations in psychological inflexibility. Leveraging our available innovation, Pai.ACT, an AI-driven chatbot adopting the Focused ACT approach, seeks to offer personalised and scalable mental health solutions for Chinese-speaking parents of NDD children. With our encouraging preliminary data supporting our pre-trained NLP model's accuracy and Pai.ACT's feasibility, the investigators propose to examine Pai.ACT in a full-scale clinical trial. The study will examine the following research questions:
- 1.Is Pai.ACT more effective than positive parenting advice for reducing parenting stress (primary outcome for parents) of parents and the emotional and behavioural symptoms of their young children with NDD (primary outcome for children) over the 12-month post-intervention follow-up?
- 2.Is Pai.ACT more effective than positive parenting advice for reducing symptoms of depression and anxiety, improving parental psychological flexibility and parenting behaviour over the 12-month post-intervention follow-up?
- 3.Is Pai.ACT more effective than positive parenting advice for reducing the use of healthcare and rehabilitation services in children with NDD over the 12-month post-intervention follow-up?
- 4.What are the perceived benefits, satisfaction, strengths, and limitations of Pai.ACT from the parents' perspectives?
Trial Health
Trial Health Score
Automated assessment based on enrollment pace, timeline, and geographic reach
participants targeted
Target at P75+ for not_applicable
Started Feb 2025
Longer than P75 for not_applicable
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
January 12, 2025
CompletedFirst Posted
Study publicly available on registry
January 16, 2025
CompletedStudy Start
First participant enrolled
February 13, 2025
CompletedPrimary Completion
Last participant's last visit for primary outcome
December 31, 2027
ExpectedStudy Completion
Last participant's last visit for all outcomes
December 31, 2028
January 23, 2025
January 1, 2025
2.9 years
January 12, 2025
January 21, 2025
Conditions
Keywords
Outcome Measures
Primary Outcomes (2)
Parenting Stress
Parenting stress will be evaluated utilising the Parenting Stress Index-Short Form (PSI-SF), comprising 36 items on a 5-point Likert scale. The PSI-SF assesses stress across three dimensions: parental distress, dysfunctional parent-child interaction, and challenging child behaviour, with a higher total score reflecting greater stress. The Chinese version of the PSI-SF has demonstrated robust convergent and discriminant validity, as well as internal consistency (α = .79-.88) in a Chinese parental cohort.
Change from baseline to immediate, 3-month, 6-month and 12-month post-intervention
Child Emotional and Behavioural Symptoms
Child emotional and behavioural symptoms will be evaluated using the Strengths and Difficulties Questionnaire (SDQ), which consists of 25 items on a 3-point Likert scale. The SDQ, a parent-reported measure, assesses five domains: emotional symptoms, conduct issues, hyperactivity/inattention, peer-related problems, and prosocial behaviour, with a higher total score reflecting more symptoms. The Chinese version of the SDQ has shown satisfactory test-retest reliability (ICC = .75-.86) and discriminant validity among Hong Kong parents.
Change from baseline to immediate, 3-month, 6-month and 12-month post-intervention
Secondary Outcomes (4)
Symptoms of Depression and Anxiety
Change from baseline to immediate, 3-month, 6-month and 12-month post-intervention
Parental Psychological Flexibility
Change from baseline to immediate, 3-month, 6-month and 12-month post-intervention
Parenting Behaviour
Change from baseline to immediate, 3-month, 6-month and 12-month post-intervention
The use of health care and rehabilitation services
Change from baseline to immediate, 3-month, 6-month and 12-month post-intervention
Study Arms (2)
Pai.ACT Group
EXPERIMENTALParents allocated to this experimental group will gain complete access to the Pai.ACT mobile app, featuring a 6-week, AI chatbot-assisted Focused ACT intervention for Cantonese-speaking parents of children with NDD, plus one 30-45-minute, individual-based videoconferencing booster session via the Pai.ACT app, mirroring the final session of Focused ACT.
Control Group
OTHERParents in the Control group will receive 6-week mobile-based e-reading modules (30-45 mins of completion/module) about positive parenting advice as recommended by the Child Assessment Services under the Department of Health, plus one 30-45 minute videoconferencing session led by another experienced counsellor for content revision. No access to AI chatbot/ACT modules will be granted.
Interventions
The Pai.ACT mobile app is an innovative therapeutic tool that utilizes Acceptance and Commitment Therapy (ACT). It integrates a sophisticated 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. These interventions, including self-help modules and experiential exercises, are enhanced with dynamic animations and audio metaphors (see NCT06086951). The contents of Pai.ACT is underpinned by: (i) the core principles of Focused ACT, (ii) our validated Focused ACT protocol used in our ongoing Focused ACT trial (see NCT05803252), and (iii) our validated ACT protocols, established since 2019, that address psychological challenges specific to the Chinese parenting context (e.g., affiliate stigma, internalisation of external criticism, self-blame) through a 4-to-6 week of ACT.
Positive parenting advice is recommended by the Child Assessment Services under the Department of Health, and videoconferencing session(s) led by another experienced counsellor for content revision. No access to AI chatbot/ACT modules will be granted.
Eligibility Criteria
You may qualify if:
- Primary caregivers who are Cantonese-speaking Hong Kong residents.
- Parents aged ≥21 years.
- Primary caregivers who adopt the responsibility of taking care of the child.
- Living together with the child and having smartphone devices for daily access to the internet.
- Parent's children should be with following criteria:
- i) Aged 2-6 years. ii) Received a primary and clinical diagnosis/suspected diagnosis of NDD as indicated in the clinical records according to the DSM-5 criteria. (e.g., ASD, ADHD, developmental delay) iii) Registered for Social Welfare Department subvented Onsite Pre-school Rehabilitation Services.
You may not qualify if:
- Parents diagnosed with severe mental illnesses.
- Parents with learning, cognitive, language, communication impairments or other debilitating conditions. (e.g., hearing or vision impairment) that could impede full participation in the study)
- Parents currently participating in /under the evaluation of other psychosocial, psychoeducation or parenting programmes.
Contact the study team to confirm eligibility.
Sponsors & Collaborators
- Chinese University of Hong Konglead
- Social Welfare Department, Hong Kongcollaborator
- Hong Kong Christian Servicecollaborator
MeSH Terms
Conditions
Condition Hierarchy (Ancestors)
Central Study Contacts
Study Design
- Study Type
- interventional
- Phase
- not applicable
- Allocation
- RANDOMIZED
- Masking
- DOUBLE
- Who Masked
- INVESTIGATOR, OUTCOMES ASSESSOR
- Masking Details
- Consented articipants will be randomly assigned to either the Pai.ACT Group or Control Group in a 1:1 ratio, using the permuted block size of 6 stratified by child's age (2-3, 4-6) through sequentially numbered, opaque and sealed envelopes with number cards (1=intervention, 2=control). A separate set of random numbers, concealed from the research team and RAs, will be generated by a statistician. Clerical staff uninvolved in the project will administer the randomisation. RA-1, blinded to subject selection, will open the envelopes only after informed consent and baseline assessments are completed. Parents in both study groups will receive a secure e-link for their assigned intervention, accessible via unique login credentials that can tie to their mobile device's ID, as well as a once-weekly reminder to prompt participation. Pai.ACT features content-locking to prevent screen-recording or sharing of audio and video contents to other parents. RA-2, also blinded to group assignment.
- Purpose
- TREATMENT
- Intervention Model
- PARALLEL
- Sponsor Type
- OTHER
- Responsible Party
- PRINCIPAL INVESTIGATOR
- PI Title
- Assistant Professor
Study Record Dates
First Submitted
January 12, 2025
First Posted
January 16, 2025
Study Start
February 13, 2025
Primary Completion (Estimated)
December 31, 2027
Study Completion (Estimated)
December 31, 2028
Last Updated
January 23, 2025
Record last verified: 2025-01