LonelinessNCT07822828
A Mechanism Randomised Controlled Trial of a Three-Agent LLM-Augmented mHealth Intervention for Late-Life Loneliness in Older Adults
A study testing Hybrid conversational companion application and Rule-based conversational companion application in people with Loneliness and Social Isolation, run by The University of Hong Kong.
Trial summary
This study examines how a smartphone conversational application affects feelings of loneliness in Cantonese-speaking older adults living in Hong Kong. Seventy-two adults aged 60 or above who report at least moderate loneliness will be randomly assigned to one of two versions of the same application. Read more about this study
- Who is it for?
- Ages 60 years and olderHealthy volunteers can take part
- Conditions the study is for
- Loneliness, Social Isolation, Social Isolation in Older Adults
- What is being tested?
- Hybrid conversational companion application and Rule-based conversational companion application
- Type of treatment
- Lifestyle or therapy programme
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 72 participants
- Where
- No sites listed yet
- Study dates
- 21 Sep 2026to 31 Dec 2026
- 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 60 years and older
- All sexes
- Healthy volunteers accepted
- Adult, Older adult
Who may be able to join
- Aged 60 years or above
- Self-identified Cantonese as primary language of communication
- Community-dwelling in Hong Kong (not in residential care)
- De Jong Gierveld Emotional and Social Loneliness Scale total score of 2 or above at screening, indicating at least moderate loneliness
- Owns a smartphone, or willing to use a study-provided device
- Able to demonstrate understanding of the study using the teach-back method
- Willing to provide written informed consent
Who cannot join
- Acute suicidality, defined as a PHQ-9 item 9 score above 1 with reported active intent
- Currently receiving formal psychiatric treatment
- Severe hearing or visual impairment precluding application use even with accommodation
- Self-reported diagnosis of dementia or significant cognitive impairment
- Unable to demonstrate understanding of the study using the teach-back method
- Prior participation in the feasibility phase of this research programme
Trial locations and contacts
No sites are listed yet. Contact the study team or a site near you to ask about taking part.
About this study
This study examines how a smartphone conversational application affects feelings of loneliness in Cantonese-speaking older adults living in Hong Kong. Seventy-two adults aged 60 or above who report at least moderate loneliness will be randomly assigned to one of two versions of the same application. Both versions look and work the same way, offer the same three conversational companions, and provide the same set of in-app tools. The two versions differ only in how the companions' replies are produced: in one version replies are generated by a large language model, and in the other they are assembled from pre-written templates selected by keyword and conversation state. Participants use the application for four weeks and are then followed for a further four weeks with continued access. The main question is whether any difference between the two versions in emotional loneliness operates through how understood, validated and cared for participants feel during individual conversations. Participants are not told which version they are using, and the researcher who carries out the assessments is also unaware of the assignment.
Read the detailed description
Loneliness in later life is associated with adverse physical and mental health outcomes. Conversational applications based on large language models have been proposed as a scalable form of support, but most published evaluations remain at the pilot feasibility stage, and few have used a comparator that holds interface richness, attention, and novelty constant. Without such a comparator, any observed benefit cannot be attributed to the language model rather than to the surrounding experience.
This trial addresses that gap using an architecturally matched comparator. Both arms deliver the identical mobile application: the same visual interface, navigation, three named conversational companions, tool layer, and in-app assessment prompts. The sole difference is the backend that generates companion response content. In the Hybrid arm, responses are generated by a large language model using each companion's system prompt, conversation history, and user input, and the arm exhibits language-model-distinctive conversational behaviours including anchoring on specific content, cross-session memory, explicit admission of unfamiliarity, mixed-content routing, and generative summarisation. In the Rule-based arm, responses are produced by a template system driven by keyword matching and conversational state, without cross-session memory and without those behaviours; conversational content in this arm is not transmitted to any external service.
Seventy-two community-dwelling Cantonese-speaking adults aged 60 or above who score at least 2 on the De Jong Gierveld Emotional and Social Loneliness Scale are allocated 1:1, stratified by baseline emotional loneliness using permuted blocks within stratum, with allocation concealment. A designated staff member performs randomisation and onboarding and does not collect outcome data. The Principal Investigator conducts all in-person assessments while unaware of allocation. Participants are not informed which version they use and are debriefed at study completion.
The intervention period is four weeks, followed by four weeks of follow-up with continued application access and continuous usage logging. The primary analysis is a longitudinal 1-1-1 multilevel mediation model with arm as the between-person predictor, session-level perceived responsiveness as the within-person mediator, and emotional loneliness as the outcome; the indirect effect is tested using Monte Carlo confidence intervals. The study is powered for the indirect effect rather than for confirmatory testing of the between-arm main effect, which is reported as an effect estimate with a 95% confidence interval. A falsifiable specification of the proposed mechanism is that an arm advantage appears on emotional loneliness but not on social loneliness.
A three-layer safety architecture operates in both arms: a Cantonese-calibrated distress detector that surfaces Hong Kong crisis resources in real time and alerts the research team; a daily 100% audit of Thought Exercise events against pre-specified scope criteria; and weekly Principal Investigator review of all flags and audits. Pre-specified pause criteria are an intervention-related serious adverse event, boundary-crossed events exceeding 10%, or distress detector recall below 0.90 on a real Cantonese corpus.
- Being tested
- Hybrid conversational companion application, Rule-based conversational companion application
- Keywords
- loneliness, older adults, large language model, conversational agent, chatbot, mHealth, mechanism trial
- Medical subject headings
- Social Isolation
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Hybrid conversational companion applicationBehavioural
Mobile application providing three named Cantonese-language conversational companions plus four in-app tools (Action Loop, Thought Exercise, Education, Progress). Companion replies are generated turn-by-turn by a large language model (DeepSeek-V3, accessed via Firebase Cloud Functions), conditioned on the companion's system prompt, retrieved conversation history, and current user input. This arm can therefore produce five conversational behaviours the comparator cannot: anchoring on specific content the participant has just said, memory carried across separate sessions, explicit admission of unfamiliarity, routing of single messages containing mixed emotional and informational content, and generative summarisation. Occurrences are tagged in system logs and analysed as a cumulative within-arm exposure variable. Conversational text is transmitted to the model provider for response generation; participants are advised at consent not to include identifying information. Recommended use is a
Rule-based conversational companion applicationBehavioural
Mobile application identical to the experimental arm in interface, navigation, companion names and personae, tool layer (Action Loop, Thought Exercise, Education, Progress), notification schedule, and all in-app assessment prompts. The sole difference is the response-generation backend: companion replies are assembled from pre-written templates selected by keyword matching and conversational state, with no language model involved. The system retains no memory across sessions, cannot anchor on unanticipated content, cannot admit unfamiliarity outside scripted cases, and cannot generate novel summaries. Conversational content is not transmitted to any external service. This is an attention- and interface-matched active comparator rather than a waitlist or usual-care control: participants receive equivalent contact time, interface richness, tool access, and prompting schedule. Recommended use, expected daily duration, and logging are identical to the experimental arm.
| Study group | Role | What they receive |
|---|---|---|
| Hybrid arm (LLM-driven) | Experimental | Participants receive the mobile application with companion responses generated by a large language model backend, using each companion's system prompt, conversation history, and user input. Language-model-distinctive conversational behaviours (content anchoring, cross-session memory, admission of unfamiliarity, mixed-content routing, generative summarisation) are operationally present. Recommended use is at least three sessions per week over four weeks; actual use is at the participant's discretion and is logged. Receives: Behavioral: Hybrid conversational companion application |
| Rule-based arm (template-driven) | Active comparator | Participants receive an application identical in interface, navigation, companion personae, tool layer, and in-app assessment prompts, with companion responses produced by a template system driven by keyword matching and conversational state. Cross-session memory and the language-model-distinctive behaviours are absent. Conversational content is not transmitted externally. Recommended use and logging are identical to the Hybrid arm. Receives: Behavioral: Rule-based conversational companion application |
What is being measured
The primary outcome is the main question the study is designed to answer.
Session-level perceived responsiveness (primary mediator)
Brief perceived-responsiveness measure administered in-app immediately after each companion conversation. Single-item sliders scored 1-7 covering Understanding, Validation, Caring and Insensitivity. Higher scores indicate greater perceived responsiveness. This is the within-person mediator in the pre-specified primary mediation model, not an efficacy endpoint.
Measured: After each conversation session, Weeks 1 through 4
Change in emotional loneliness (De Jong Gierveld emotional subscale)
De Jong Gierveld Emotional and Social Loneliness Scale, 3-item emotional subscale. Score range 0-3; higher scores indicate greater emotional loneliness. Change from baseline to Week 4. This is the outcome variable in the pre-specified primary mediation model. The trial is powered for the indirect effect via session-level perceived responsiveness and is not powered for confirmatory testing of the between-arm difference, which is reported as an effect estimate with a 95% confidence interval.
Measured: Baseline (Week 0) and Week 4
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted16 Sep 2026
- Study start21 Sep 2026 (estimated)
- Primary completion31 Dec 2026 (estimated)
- Study completion31 Dec 2026 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for LonelinessStudies of the same condition, open and under way.
- More trials run by The University of Hong KongThe sponsor's other registered studies.
- 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
- Basic science
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Model description
- Two-arm parallel-group mechanism trial with an architecturally matched active comparator.
- Masking
- Double blind
- Who is masked
- Participant, Outcomes assessor
- Enrolment
- 72 participants (estimated)
Sponsor and investigators
- Lead sponsor
- The University of Hong Kong
- Sponsor type
- University, hospital or other
- Responsible party
- Sponsor
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07822828
- Sponsor's protocol ID
- EA260523
- Status last verified
- Sep 2026
- First submitted
- 10 Sep 2026
- Last updated
- 16 Sep 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
Study at a glance
From the registry record, last updated by the sponsor on 16 Sep 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- A Mechanism Randomised Controlled Trial of a Three-Agent LLM-Augmented mHealth Intervention for Late-Life Loneliness in Older Adults
- ClinicalTrials.gov ID
- NCT07822828
- Acronym / sponsor ID
- EA260523
- Keywords
- loneliness, older adults, large language model, conversational agent, chatbot, mHealth, mechanism trial
- Study type
- Interventional
- Recruitment status
- Not yet recruiting
- Enrolment
- 72 participants (estimated)
- Lead sponsor
- The University of Hong KongUniversity, hospital or other
- Study start
- 21 Sep 2026 (estimated)
- Primary completion
- 31 Dec 2026 (estimated)
- Study completion
- 31 Dec 2026 (estimated)
- First posted
- 16 Sep 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.
This study examines how a smartphone conversational application affects feelings of loneliness in Cantonese-speaking older adults living in Hong Kong. Seventy-two adults aged 60 or above who report at least moderate loneliness will be randomly assigned to one of two versions of the same application. Both versions look and work the same way, offer the same three conversational companions, and provide the same set of in-app tools. The two versions differ only in how the companions' replies are produced: in one version replies are generated by a large language model, and in the other they are assembled from pre-written templates selected by keyword and conversation state. Participants use the application for four weeks and are then followed for a further four weeks with continued access. The main question is whether any difference between the two versions in emotional loneliness operates through how understood, validated and cared for participants feel during individual conversations. Participants are not told which version they are using, and the researcher who carries out the assessments is also unaware of the assignment.
Detailed description
Loneliness in later life is associated with adverse physical and mental health outcomes. Conversational applications based on large language models have been proposed as a scalable form of support, but most published evaluations remain at the pilot feasibility stage, and few have used a comparator that holds interface richness, attention, and novelty constant. Without such a comparator, any observed benefit cannot be attributed to the language model rather than to the surrounding experience.
This trial addresses that gap using an architecturally matched comparator. Both arms deliver the identical mobile application: the same visual interface, navigation, three named conversational companions, tool layer, and in-app assessment prompts. The sole difference is the backend that generates companion response content. In the Hybrid arm, responses are generated by a large language model using each companion's system prompt, conversation history, and user input, and the arm exhibits language-model-distinctive conversational behaviours including anchoring on specific content, cross-session memory, explicit admission of unfamiliarity, mixed-content routing, and generative summarisation. In the Rule-based arm, responses are produced by a template system driven by keyword matching and conversational state, without cross-session memory and without those behaviours; conversational content in this arm is not transmitted to any external service.
Seventy-two community-dwelling Cantonese-speaking adults aged 60 or above who score at least 2 on the De Jong Gierveld Emotional and Social Loneliness Scale are allocated 1:1, stratified by baseline emotional loneliness using permuted blocks within stratum, with allocation concealment. A designated staff member performs randomisation and onboarding and does not collect outcome data. The Principal Investigator conducts all in-person assessments while unaware of allocation. Participants are not informed which version they use and are debriefed at study completion.
The intervention period is four weeks, followed by four weeks of follow-up with continued application access and continuous usage logging. The primary analysis is a longitudinal 1-1-1 multilevel mediation model with arm as the between-person predictor, session-level perceived responsiveness as the within-person mediator, and emotional loneliness as the outcome; the indirect effect is tested using Monte Carlo confidence intervals. The study is powered for the indirect effect rather than for confirmatory testing of the between-arm main effect, which is reported as an effect estimate with a 95% confidence interval. A falsifiable specification of the proposed mechanism is that an arm advantage appears on emotional loneliness but not on social loneliness.
A three-layer safety architecture operates in both arms: a Cantonese-calibrated distress detector that surfaces Hong Kong crisis resources in real time and alerts the research team; a daily 100% audit of Thought Exercise events against pre-specified scope criteria; and weekly Principal Investigator review of all flags and audits. Pre-specified pause criteria are an intervention-related serious adverse event, boundary-crossed events exceeding 10%, or distress detector recall below 0.90 on a real Cantonese corpus.
Study design
- Primary purpose
- Basic science
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- Double blind (participant, outcomes assessor)
- Number of arms
- 2
- Model description
- Two-arm parallel-group mechanism trial with an architecturally matched active comparator.
| Arm | Type | Receives |
|---|---|---|
| Hybrid arm (LLM-driven) | Experimental | Behavioral: Hybrid conversational companion applicationParticipants receive the mobile application with companion responses generated by a large language model backend, using each companion's system prompt, conversation history, and user input. Language-model-distinctive conversational behaviours (content anchoring, cross-session memory, admission of unfamiliarity, mixed-content routing, generative summarisation) are operationally present. Recommended use is at least three sessions per week over four weeks; actual use is at the participant's discretion and is logged. |
| Rule-based arm (template-driven) | Active comparator | Behavioral: Rule-based conversational companion applicationParticipants receive an application identical in interface, navigation, companion personae, tool layer, and in-app assessment prompts, with companion responses produced by a template system driven by keyword matching and conversational state. Cross-session memory and the language-model-distinctive behaviours are absent. Conversational content is not transmitted externally. Recommended use and logging are identical to the Hybrid arm. |
Who may qualify
- Ages
- 60 years and older
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (7 listed)
- Aged 60 years or above
- Self-identified Cantonese as primary language of communication
- Community-dwelling in Hong Kong (not in residential care)
- De Jong Gierveld Emotional and Social Loneliness Scale total score of 2 or above at screening, indicating at least moderate loneliness
- Owns a smartphone, or willing to use a study-provided device
Key exclusion criteria (6 listed)
- Acute suicidality, defined as a PHQ-9 item 9 score above 1 with reported active intent
- Currently receiving formal psychiatric treatment
- Severe hearing or visual impairment precluding application use even with accommodation
- Self-reported diagnosis of dementia or significant cognitive impairment
- Unable to demonstrate understanding of the study using the teach-back method
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 |
|---|---|---|
| Hybrid conversational companion applicationMobile application providing three named Cantonese-language conversational companions plus four in-app tools (Action Loop, Thought Exercise, Education, Progress). Companion replies are generated turn-by-turn by a large language model (DeepSeek-V3, accessed via Firebase Cloud Functions), conditioned on the companion's system prompt, retrieved conversation history, and current user input. This arm can therefore produce five conversational behaviours the comparator cannot: anchoring on specific content the participant has just said, memory carried across separate sessions, explicit admission of unfamiliarity, routing of single messages containing mixed emotional and informational content, and generative summarisation. Occurrences are tagged in system logs and analysed as a cumulative within-arm exposure variable. Conversational text is transmitted to the model provider for response generation; participants are advised at consent not to include identifying information. Recommended use is a | Behavioural | Hybrid arm (LLM-driven) |
| Rule-based conversational companion applicationMobile application identical to the experimental arm in interface, navigation, companion names and personae, tool layer (Action Loop, Thought Exercise, Education, Progress), notification schedule, and all in-app assessment prompts. The sole difference is the response-generation backend: companion replies are assembled from pre-written templates selected by keyword matching and conversational state, with no language model involved. The system retains no memory across sessions, cannot anchor on unanticipated content, cannot admit unfamiliarity outside scripted cases, and cannot generate novel summaries. Conversational content is not transmitted to any external service. This is an attention- and interface-matched active comparator rather than a waitlist or usual-care control: participants receive equivalent contact time, interface richness, tool access, and prompting schedule. Recommended use, expected daily duration, and logging are identical to the experimental arm. | Behavioural | Rule-based arm (template-driven) |
Primary outcome
Session-level perceived responsiveness (primary mediator)
Time frame: After each conversation session, Weeks 1 through 4
Brief perceived-responsiveness measure administered in-app immediately after each companion conversation. Single-item sliders scored 1-7 covering Understanding, Validation, Caring and Insensitivity. Higher scores indicate greater perceived responsiveness. This is the within-person mediator in the pre-specified primary mediation model, not an efficacy endpoint.
Change in emotional loneliness (De Jong Gierveld emotional subscale)
Time frame: Baseline (Week 0) and Week 4
De Jong Gierveld Emotional and Social Loneliness Scale, 3-item emotional subscale. Score range 0-3; higher scores indicate greater emotional loneliness. Change from baseline to Week 4. This is the outcome variable in the pre-specified primary mediation model. The trial is powered for the indirect effect via session-level perceived responsiveness and is not powered for confirmatory testing of the between-arm difference, which is reported as an effect estimate with a 95% confidence interval.
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 16 Sep 2026.
Related trials for Loneliness
RecruitingObservational study
Student Precarity and Psychiatry
Depressive Disorder, Major, Generalized Anxiety Disorder
Not yet recruiting
Hangeoreum: A Self-Paced Web-Based Program for Loneliness and Connectedness Among Korean Immigrants Aged 50 and Older
Loneliness, Korean
Not yet recruiting
Interpersonal Relational Role Analysis Group Therapy for Nursing Students at Risk of Internet Addiction
Internet Addiction
Active, not recruiting
PREWELL Digital Well-being Promotion Intervention With the BitHabit App
General Mental Health and Well-Being, Mental Disorders
Recruiting
Intergenerational Interaction Program for Nursing Home Residents and Nursing Students
Ageism, Loneliness
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.
Questions about this trial
What is this clinical trial studying?
A study testing Hybrid conversational companion application and Rule-based conversational companion application in people with Loneliness and Social Isolation, run by The University of 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 7 inclusion and 6 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 16 Sep 2026. Status can change between updates, so confirm with the study contact before making plans.
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?
Contact Junyu Zhao (852-60919592, zhaojyxs@connect.hku.hk), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Session-level perceived responsiveness (primary mediator) (time frame: After each conversation session, Weeks 1 through 4). The study lists 2 primary outcomes in all. It is what the study was designed to measure, not a finding.
Where can I read the original study information?
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 16 Sep 2026.