A Mechanism Randomised Controlled Trial of a Three-Agent LLM-Augmented mHealth Intervention for Late-Life Loneliness in Older Adults

NCT07822828 | Not Yet Recruiting

• 1 other identifier: EA260523
• Study Type: interventional
• Target: 72
• Locations: 0 countries
• Sites: N/A

Brief 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. 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.

Conditions

Loneliness; Social Isolation in Older Adults; Social Isolation

Keywords

loneliness; older adults; large language model; conversational agent; chatbot; mHealth; mechanism trial

Outcome Measures

Primary Outcomes (2)

• 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.

  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.

  Baseline (Week 0) and Week 4

Study Arms (2)

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.

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.

Behavioral: Rule-based conversational companion application

Interventions

Hybrid conversational companion application BEHAVIORAL

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

Hybrid arm (LLM-driven)

Rule-based conversational companion application BEHAVIORAL

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.

Rule-based arm (template-driven)

Eligibility Criteria

• Age: 60 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• 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

You may not qualify if:

• 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

Sponsors & Collaborators

• The University of Hong Kong: lead

MeSH Terms

Conditions

Social Isolation

Condition Hierarchy (Ancestors)

Social Behavior; Behavior

Central Study Contacts

Junyu Zhao

CONTACT

852-60919592; zhaojyxs@connect.hku.hk

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: DOUBLE
• Who Masked: PARTICIPANT, OUTCOMES ASSESSOR
• Masking Details: Participants are not informed which version of the application they receive; both arms are presented identically as a conversational support application under evaluation. The Principal Investigator, who administers all in-person outcome assessments, is not informed of allocation. The staff member who performs randomisation and onboarding is necessarily unmasked but collects no outcome data. The analyst is masked while preparing the efficacy analysis dataset and unmasked for mechanism analyses, in which arm assignment is the predictor of interest. Assessor masking may be partially compromised during qualitative interviews when participants describe application behaviour; this is monitored and reported.
• Purpose: BASIC SCIENCE
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: Two-arm parallel-group mechanism trial with an architecturally matched active comparator.

Study Record Dates

• First Submitted: September 10, 2026
• First Posted: September 16, 2026
• Study Start: September 21, 2026
• Primary Completion (Estimated): December 31, 2026
• Study Completion (Estimated): December 31, 2026
• Last Updated: September 16, 2026

Record last verified: 2026-09