Dementia CaregiverNCT07444866
Machine Learning Enabled Management of Behavioural and Psychological Symptoms of Dementia Intervention for Dementia Caregivers
A study testing Behavioral: Continue, Behavioral: Enhance human coaching and Behavioral: Booster in people with Dementia Caregiver, run by Education University of Hong Kong at 1 site in Hong Kong.
Trial summary
Develop and test a machine learning enabled management of behavioural and psychological symptoms of dementia intervention for dementia caregivers. Read more about this study
- Who is it for?
- Ages 18 years and olderHealthy volunteers can take part
- Conditions the study is for
- Dementia Caregiver
- What is being tested?
- Behavioral: Continue, Behavioral: Enhance human coaching and Behavioral: Booster
- Type of treatment
- Lifestyle or therapy programme
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 550 participants
- Where
- 1 siteHong Kong
- Study dates
- 12 Oct 2026to 31 Dec 2027
- Phase
- Interventional
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- Healthy volunteers accepted
- Adult, Older adult
Who may be able to join
- aged 18 above
- family caregiver of an individual with a confirmed medical diagnosis of any type of dementia who has been residing in the community
- having been providing care for ADLs and IADLs for at least 20 hours per week for at least one year prior to recruitment
- have a smartphone
- have mild to moderate stress (the 14-item Chinese version Perceived Stress Scale).
Who cannot join
- having participated in any structured mind-body intervention, cognitive therapy, or structured psychosocial intervention in the 6 months prior to recruitment
- having acute psychiatric and medical comorbidities that are potentially life-threatening (e.g. suicidal ideation) or that limit the caregivers' participation or adherence (e.g. acute psychosis)
Trial locations and contacts
1 site in 1 country. Contact the study team or a site near you to ask about taking part.
Hong Kong1 site
The Education University of Hong Kong
Hong Kong
Kee Lee Chou, PhD, +85229487473, klchou@eduhk.hk
Vivien Tang, MSc, s1135125@s.eduhk.hk
About this study
Official title: Developing and Testing a Machine Learning Enabled Management of Behavioural and Psychological Symptoms of Dementia Intervention for Dementia Caregivers: A Hybrid Experimental Design Study
Develop and test a machine learning enabled management of behavioural and psychological symptoms of dementia intervention for dementia caregivers.
- Conditions
- Dementia Caregiver
- Being tested
- Active Control, Behavioral: Continue, Behavioral: Enhance human coaching, Behavioral: Booster
- Keywords
- Hybrid factorial - Sequential Multiple Assignment Randomized Trial, Micro Randomized Trial experimental design, machine learning, intervention, dementia caregiver
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Active ControlBehavioural
No APP based coaching, no human coaching, no rerandomization, no MRT
Behavioral: ContinueBehavioural
Continue with existing intervention plan
Behavioral: Enhance human coachingBehavioural
Increase intensity of human coaching
Behavioral: BoosterBehavioural
Add a booster session
| Study group | Role | What they receive |
|---|---|---|
| Active control | Active comparator | Active control Receives: Behavioral: Active Control |
| App & Human Coaching + Continue Intervention | Experimental | First-line of coaching: App + Human Coaching Responder Receives: Behavioral: Behavioral: Continue |
| App & Human Coaching + Increase intensity in human coaching | Experimental | First-line of coaching: App + Human Coaching Non-Responder Receives: Behavioral: Behavioral: Enhance human coaching |
| App & Human Coaching + Booster | Experimental | First-line of coaching: App + Human Coaching Non-Responder Receives: Behavioral: Behavioral: Booster |
| App Coaching + Continue Intervention | Experimental | First-line of coaching: App Coaching Responder Receives: Behavioral: Behavioral: Continue |
| App Coaching + Increase intensity in human coaching | Experimental | First-line of coaching: App Coaching Non-Responder Receives: Behavioral: Behavioral: Enhance human coaching |
| App Coaching + Booster | Experimental | First-line of coaching: App Coaching Non-Responder Receives: Behavioral: Behavioral: Booster |
| Human Coaching + Continue Intervention | Experimental | First-line of coaching: Human Coaching Responder Receives: Behavioral: Behavioral: Continue |
| Human Coaching + Increase intensity in human coaching | Experimental | First-line of coaching: Human Coaching Non-Responder Receives: Behavioral: Behavioral: Enhance human coaching |
| Human Coaching + Booster | Experimental | First-line of coaching: Human Coaching Non-Responder Receives: Behavioral: Behavioral: Booster |
| No Coaching + Continue Intervention | Experimental | First-line of coaching: No Coaching Responder Receives: Behavioral: Behavioral: Continue |
| No Coaching + Increase intensity in human coaching | Experimental | First-line of coaching: No Coaching Non-Responder Receives: Behavioral: Behavioral: Enhance human coaching |
| No Coaching + Booster | Experimental | First-line of coaching: No Coaching Non-Responder Receives: Behavioral: Behavioral: Booster |
What is being measured
The primary outcome is the main question the study is designed to answer.
Stress
10-item Perceived Stress Scale; each item will be rated from 0=Never to 4=Very often. Total scores range from 0 to 40.
Measured: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Secondary outcomes (12)
Depression
Patient Health Questionnaire-9; Each item will be rated from 0=Not at all to 3=nearly everyday. Total scores range from 0 to 27
Measured: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Sleep Quality
Pittsburgh Sleep Quality Index; each item will be rated from 0=No difficulty to 3=Severe difficulty. Total scores range from 0 to 21. Higher scores indicating poorer sleep quality
Measured: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Anxiety
Generalised Anxiety Disorder; each item will be rated from 0=not at all to 3=nearly every day. Total score range from 0 to 21.
Measured: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Physical Health
Lawton Instrumental Activities of Daily Living; each item will be rated 0=dependent to 1=independent. Total scores range from 0 to 8.
Measured: Baseline (T0), 32 weeks after baseline assessment (T4)
Physical Health
Activities of Daily Living; each item will be rate from 0=dependent to 5/10=independent. Total scores range from 0 to 100.
Measured: Baseline (T0), 32 weeks after baseline assessment (T4)
Physical Symptoms
Wahler Physical Symptoms Inventory; each item will be rated from 0=almost never agree to 5=agree almost every day. Total score range from 0 to 210.
Measured: Baseline (T0), 32 weeks after baseline assessment (T4)
Chronic Illness
Participants will indicate any presence of chronic illness (e.g., diabetes, asthma, high blood pressure).
Measured: Baseline (T0), 32 weeks after baseline assessment (T4)
Caregiver Burden
12-item Zarit Burden Interview Scale ; each item will be rated from 0=Never to 4=Nearly always. Total scores range from 0 to 48.
Measured: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Psychological Well-Being
18-item Ryff Psychological Well-Being scale, each item range from 1-strongly agree to 7-strongly disagree. Total score range from 18-126.
Measured: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Physical and Mental Health
5-level EQ-5D version (EQ-5D-5L) will be utilized; the EQ-5D descriptive system and the EQ visual analogue scale (EQ VAS).
The descriptive system comprises five dimensions: mobility, self-care, usual activities, pain/discomfort and anxiety/depression. Each dimension has 5 levels: no problems, slight problems, moderate problems, severe problems and extreme problems. The patient is asked to indicate his/her health state by ticking the box next to the most appropriate statement in each of the five dimensions. This decision results in a 1-digit number that expresses the level selected for that dimension. The digits for the five dimensions can be combined into a 5-digit number that describes the patient's health state.
The EQ VAS records the patient's self-rated health on a vertical visual analogue scale where the endpoints are labelled 'The best health you can imagine' and 'The worst health you can imagine'. The VAS can be used as a quantitative measure of health outcome that reflects
Measured: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Neuropsychiatric
Neuropsychiatric Inventory Questionnaire; classified each of the 12 domain into presence of symptom, frequency, severity, and caregiver distress.
Measured: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Memory and Behaviour Problems
Revised Memory and Behavior Problems Checklist; a 24-item checklist from 0=never occurred/not at all to 4=daily/extremely. Higher score indicate more frequent behavioral problems/caregiver distress
Measured: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted3 Mar 2026
- Study start12 Oct 2026 (estimated)
- Primary completion31 Dec 2027 (estimated)
- Study completion31 Dec 2027 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (1)Papers the sponsor has linked to this study.
- Other trials for Dementia CaregiverStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Prevention
- Allocation
- Randomised
- Intervention model
- Factorial
- Model description
- Hybrid factorial - Sequential Multiple Assignment Randomized Trial (SMART), Micro Randomized Trial (MRT) experimental design with a 2x2+1 factorial design (with five arms) randomized clinical trial, 2 stage SMART and three MRTs
- Masking
- Double blind
- Who is masked
- Participant, Outcomes assessor
- Enrolment
- 550 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Education University of Hong Kong
- Sponsor type
- University, hospital or other
- Collaborators
- The Hong Kong Polytechnic University, Lingnan University, Columbia University, Penn State University, The University of Hong Kong, Deakin University
- Responsible party
- Principal investigator, Chou Kee Lee, Education University of Hong Kong
- Investigators
- Kee Lee Chou, PhD, Principal investigator, The Education University of Hong Kong
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07444866
- Sponsor's protocol ID
- 2023-2024-0387
- Other IDs
- 22231921
- Status last verified
- Sep 2026
- First submitted
- 25 Feb 2026
- Last updated
- 5 Oct 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No
Publications
Cheung DSK, Kor PPK, Chu AMY, Xie H, Qian M, Chu LW, Zarit S, Chou KL. Machine learning-enabled behavioural and psychological symptoms of dementia management intervention for dementia caregivers: protocol for a hybrid factorial SMART-MRT trial. BMC Geriatr. 2026 Jul 13. doi: 10.1186/s12877-026-07894-w. Online ahead of print.
PubMed 42443790
Study at a glance
From the registry record, last updated by the sponsor on 5 Oct 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Developing and Testing a Machine Learning Enabled Management of Behavioural and Psychological Symptoms of Dementia Intervention for Dementia Caregivers: A Hybrid Experimental Design Study
- ClinicalTrials.gov ID
- NCT07444866
- Acronym / sponsor ID
- 2023-2024-0387
- Conditions
- Dementia Caregiver
- Keywords
- Hybrid factorial - Sequential Multiple Assignment Randomized Trial, Micro Randomized Trial experimental design, machine learning, intervention, dementia caregiver
- Study type
- Interventional
- Recruitment status
- Not yet recruiting
- Enrolment
- 550 participants (estimated)
- Lead sponsor
- Education University of Hong KongUniversity, hospital or other
- Collaborators
- The Hong Kong Polytechnic University, Lingnan University, Columbia University, Penn State University, The University of Hong Kong, Deakin University
- Study start
- 12 Oct 2026 (estimated)
- Primary completion
- 31 Dec 2027 (estimated)
- Study completion
- 31 Dec 2027 (estimated)
- First posted
- 3 Mar 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
Develop and test a machine learning enabled management of behavioural and psychological symptoms of dementia intervention for dementia caregivers.
Study design
- Primary purpose
- Prevention
- Allocation
- Randomised
- Intervention model
- Factorial
- Masking
- Double blind (participant, outcomes assessor)
- Number of arms
- 13
- Model description
- Hybrid factorial - Sequential Multiple Assignment Randomized Trial (SMART), Micro Randomized Trial (MRT) experimental design with a 2x2+1 factorial design (with five arms) randomized clinical trial, 2 stage SMART and three MRTs
| Arm | Type | Receives |
|---|---|---|
| Active control | Active comparator | Behavioral: Active ControlActive control |
| App & Human Coaching + Continue Intervention | Experimental | Behavioral: Behavioral: ContinueFirst-line of coaching: App + Human Coaching Responder |
| App & Human Coaching + Increase intensity in human coaching | Experimental | Behavioral: Behavioral: Enhance human coachingFirst-line of coaching: App + Human Coaching Non-Responder |
| App & Human Coaching + Booster | Experimental | Behavioral: Behavioral: BoosterFirst-line of coaching: App + Human Coaching Non-Responder |
| App Coaching + Continue Intervention | Experimental | Behavioral: Behavioral: ContinueFirst-line of coaching: App Coaching Responder |
| App Coaching + Increase intensity in human coaching | Experimental | Behavioral: Behavioral: Enhance human coachingFirst-line of coaching: App Coaching Non-Responder |
| App Coaching + Booster | Experimental | Behavioral: Behavioral: BoosterFirst-line of coaching: App Coaching Non-Responder |
| Human Coaching + Continue Intervention | Experimental | Behavioral: Behavioral: ContinueFirst-line of coaching: Human Coaching Responder |
| Human Coaching + Increase intensity in human coaching | Experimental | Behavioral: Behavioral: Enhance human coachingFirst-line of coaching: Human Coaching Non-Responder |
| Human Coaching + Booster | Experimental | Behavioral: Behavioral: BoosterFirst-line of coaching: Human Coaching Non-Responder |
| No Coaching + Continue Intervention | Experimental | Behavioral: Behavioral: ContinueFirst-line of coaching: No Coaching Responder |
| No Coaching + Increase intensity in human coaching | Experimental | Behavioral: Behavioral: Enhance human coachingFirst-line of coaching: No Coaching Non-Responder |
| No Coaching + Booster | Experimental | Behavioral: Behavioral: BoosterFirst-line of coaching: No Coaching Non-Responder |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (5 listed)
- aged 18 above
- family caregiver of an individual with a confirmed medical diagnosis of any type of dementia who has been residing in the community
- having been providing care for ADLs and IADLs for at least 20 hours per week for at least one year prior to recruitment
- have a smartphone
- have mild to moderate stress (the 14-item Chinese version Perceived Stress Scale).
Key exclusion criteria (2 listed)
- having participated in any structured mind-body intervention, cognitive therapy, or structured psychosocial intervention in the 6 months prior to recruitment
- having acute psychiatric and medical comorbidities that are potentially life-threatening (e.g. suicidal ideation) or that limit the caregivers' participation or adherence (e.g. acute psychosis)
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Active ControlNo APP based coaching, no human coaching, no rerandomization, no MRT | Behavioural | Active control |
| Behavioral: ContinueContinue with existing intervention plan | Behavioural | App & Human Coaching + Continue Intervention, App Coaching + Continue Intervention, Human Coaching + Continue Intervention, No Coaching + Continue Intervention |
| Behavioral: Enhance human coachingIncrease intensity of human coaching | Behavioural | App & Human Coaching + Increase intensity in human coaching, App Coaching + Increase intensity in human coaching, Human Coaching + Increase intensity in human coaching, No Coaching + Increase intensity in human coaching |
| Behavioral: BoosterAdd a booster session | Behavioural | App & Human Coaching + Booster, App Coaching + Booster, Human Coaching + Booster, No Coaching + Booster |
Primary outcome
Stress
Time frame: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
10-item Perceived Stress Scale; each item will be rated from 0=Never to 4=Very often. Total scores range from 0 to 40.
12 secondary outcomes
Depression
Time frame: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Sleep Quality
Time frame: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Anxiety
Time frame: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Physical Health
Time frame: Baseline (T0), 32 weeks after baseline assessment (T4)
Physical Health
Time frame: Baseline (T0), 32 weeks after baseline assessment (T4)
Physical Symptoms
Time frame: Baseline (T0), 32 weeks after baseline assessment (T4)
Chronic Illness
Time frame: Baseline (T0), 32 weeks after baseline assessment (T4)
Caregiver Burden
Time frame: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Psychological Well-Being
Time frame: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Physical and Mental Health
Time frame: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Neuropsychiatric
Time frame: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Memory and Behaviour Problems
Time frame: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 5 Oct 2026.
- Derived from this study: PubMed 42443790Cheung DSK, Kor PPK, Chu AMY, Xie H, Qian M, Chu LW, Zarit S, Chou KL. Machine learning-enabled behavioural and psychological symptoms of dementia management intervention for dementia caregivers: protocol for a hybrid factorial SMART-MRT trial. BMC Geriatr. 2026 Jul 13. doi: 10.1186/s12877-026-07894-w. Online ahead of print.
- Individual participant dataSharing planned: No
Related trials for Dementia Caregiver
Not yet recruiting
Acupressure as Long-term Intervention to Slow the Progression of Early/Mild Alzheimer's Disease
Alzheimer's Disease
Active, not recruiting
NYUCI-ES: Psychosocial Intervention to Improve Health Outcomes for Chinese and Korean ADRD Caregivers
Dementia Caregivers, Diabetes
Active, not recruiting
Health enSuite Caregivers: an App-based Treatment for Distressed Caregivers of Persons With Moderate Dementia
Caregiver Burnout
Not yet recruiting
Music Listening for Chronic Pain in Adults With Early-Stage Dementia
Chronic Pain, Alzheimer Disease
Not yet recruiting
A Mobile Informatics Solution to Assist Caregivers in Care Coordination and Monitoring Social Engagement
Memory Disorders, Mild Cognitive Impairment
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part.
Kee Lee Chou, PhD principal investigator
The Education University of Hong Kong
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing Behavioral: Continue, Behavioral: Enhance human coaching and Behavioral: Booster in people with Dementia Caregiver, run by Education University of Hong Kong at 1 site in Hong Kong.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 5 inclusion and 2 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: opening soon, as of the sponsor's last update on 5 Oct 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in Hong Kong. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Each site lists its own contact: choose the nearest one under Trial locations. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Stress (time frame: Baseline (T0), 6 weeks after baseline assessment (T1), 10 weeks after baseline assessment (T2), 20 weeks after baseline assessment (T3), 32 weeks after baseline assessment (T4)). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT07444866, which also lists 1 linked publication.
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 5 Oct 2026.