이 페이지는 자동 번역되었으며 번역의 정확성을 보장하지 않습니다. 참조하십시오 영문판 원본 텍스트의 경우.

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

2026년 11월 5일 업데이트: The University of Hong Kong

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 the same, offer the same three conversational companions, and provide the same set of in-app tools. The two versions differ 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. Several features depend on the language model and are available only in the first version: (1) memory of earlier conversations; (2) replies in the tone that the participant preferred at the start of the study; (3) follow-up questions during reminiscence; (4) weekly life-story chapters drafted by the model and sent by notification when ready; (5) the option to ask the companion Tung Tung about reading material; (6) activity suggestions and action plans personalised with intake information and memory; and (7) a weekly narrative summary on the progress page written by the model. In the other version, the weekly life-story chapter is assembled at once from the participant's own answers, and the progress page shows charts and counts only. 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 researchers who carry out the Week 0 and Week 4 assessments are also unaware of the assignment.

연구 개요

상세 설명

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 arms differ in the backend that generates companion responses and in the features that depend on the language model, which are available only in the Hybrid arm: (1) cross-session memory; (2) replies adjusted to the tone that the participant preferred at intake; (3) follow-up questions during reminiscence; (4) weekly life-story chapters drafted by the model and sent by notification when ready; (5) the option to ask Tung Tung about reading material; (6) activity suggestions and action plans personalised with intake information and memory; and (7) a weekly narrative summary on the progress page written by the model. In the Rule-based arm, the weekly life-story chapter is assembled at once from the participant's own answers, and the progress page shows charts and counts only. 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. A local safety classifier, hosted by the research team, is used in both arms.

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. Trained outcome assessors, who are unaware of allocation, explain the study, obtain written informed consent, and conduct the paper-based assessments at Week 0 and Week 4. The same assessor conducts both assessments for a participant. After the Week 0 assessment, the assessor leaves the room. The Principal Investigator then registers the participant, which triggers the allocation on the study server, and provides app onboarding. The allocation sequence is generated by a person who has no other role in the trial, and the Principal Investigator cannot read it. After the Week 4 assessment, the Principal Investigator conducts an exit interview. At Week 8, participants complete the follow-up questionnaires in the app.

The intervention period is four weeks, followed by four weeks of follow-up with continued application access and continuous usage logging. Participants are encouraged to use the application daily and at least five times per week; use is not mandatory. The primary analysis is a 2-1-2 multilevel structural equation model. Arm is the participant-level predictor. Perceived responsiveness is rated after conversations, and the model estimates each participant's latent mean. Emotional loneliness at Week 4, adjusted for baseline, is the outcome. The indirect effect is tested using a Monte Carlo confidence interval. The sample size is fixed by feasibility. In a sensitivity power analysis by simulation, sixty completers gave power of about 0.80 only when the effect of arm on perceived responsiveness was d = 0.8 and the standardised effect of perceived responsiveness on emotional loneliness was 0.4. The between-arm difference in emotional loneliness is reported as an effect estimate with a 95% confidence interval and is not tested confirmatorily. 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.

A pilot phase with six older adults preceded the randomised trial. Two pilot participants started on 15 October 2026 under a separate pilot consent form. Four further participants signed the main consent form and were registered on 19 October 2026 with an earlier allocation sequence. On that day, the Rule-based version of the app did not work correctly. The randomised analysis set was therefore restarted on 21 October 2026 with a newly generated allocation sequence, and these four participants were moved to the pilot phase. They continue to use the application and complete the scheduled assessments. Pilot-phase data are reported for feasibility and acceptability only and are excluded from all trial analyses. The randomised analysis set comprises participants enrolled from 21 October 2026 onwards; the target of 72 randomised participants, with about 60 expected to complete the trial, is unchanged.

연구 유형

중재적

등록 (추정된)

72

단계

  • 해당 없음

연락처 및 위치

이 섹션에서는 연구를 수행하는 사람들의 연락처 정보와 이 연구가 수행되는 장소에 대한 정보를 제공합니다.

연구 연락처

연구 장소

    • Hong Kong SAR
      • Hong Kong, Hong Kong SAR, 홍콩, 999077
        • 모병
        • The University of Hong Kong
        • 연락하다:

참여기준

연구원은 적격성 기준이라는 특정 설명에 맞는 사람을 찾습니다. 이러한 기준의 몇 가지 예는 개인의 일반적인 건강 상태 또는 이전 치료입니다.

자격 기준

공부할 수 있는 나이

60년 이상 (성인, 고령자)

건강한 자원 봉사자를 받아들입니다

예

연구 대상 성별

모두

설명

Inclusion Criteria:

  • 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 on which the study app can be installed
  • Able to demonstrate understanding of the study using the teach-back method
  • Willing to provide written informed consent

Exclusion Criteria:

  • 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 pilot runs of this trial
  • Another member of the same household has already registered for the study

공부 계획

이 섹션에서는 연구 설계 방법과 연구가 측정하는 내용을 포함하여 연구 계획에 대한 세부 정보를 제공합니다.

연구는 어떻게 설계됩니까?

디자인 세부사항

  • 주 목적: 기초 과학
  • 할당: 무작위
  • 중재 모델: 병렬 할당
  • 마스킹: 더블

무기와 개입

참가자 그룹 / 팔
개입 / 치료
실험적: Hybrid arm (LLM-driven)

Companion responses are generated by a large language model through the official DeepSeek API, accessed via Firebase Cloud Functions. The model version is not fixed, so the model identifier returned with each response is logged. Responses are conditioned on the companion's system prompt, conversation history, cross-session memory, and the current input. In reminiscence, the model asks one follow-up question after each answer, and at the end of each week a DeepSeek model drafts a short life-story chapter that a second model checks against the conversation. Four in-app tools (Action Loop, Thought Exercise, Education, Progress). Five LLM-distinctive behaviours are tagged in logs as a cumulative within-arm exposure variable. Conversational text is sent to the model provider; participants are advised not to include identifying information. Participants are encouraged to use the app daily and at least five times per week for four weeks; use is not mandatory and is logged.

Companion responses are generated by a large language model through the official DeepSeek API, accessed via Firebase Cloud Functions. The model version is not fixed, so the model identifier returned with each response is logged. Responses are conditioned on the companion's system prompt, conversation history, cross-session memory, and the current input. In reminiscence, the model asks one follow-up question after each answer, and at the end of each week a DeepSeek model drafts a short life-story chapter that a second model checks against the conversation. Four in-app tools (Action Loop, Thought Exercise, Education, Progress). Five LLM-distinctive behaviours are tagged in logs as a cumulative within-arm exposure variable. Conversational text is sent to the model provider; participants are advised not to include identifying information. Participants are encouraged to use the app daily and at least five times per week for four weeks; use is not mandatory and is logged.

활성 비교기: Rule-based arm (template-driven)

Identical interface, navigation, companion names and personae, tool layer, notification schedule, and in-app assessment prompts. Replies are assembled from pre-written templates by keyword matching and conversational state; no language model is used. In free conversation, Siu Yan's replies are drawn in rotation from a pool of pre-written sentences. The daily check-in is a short conversation with fixed questions, followed by a pre-written response chosen by the participant's answer. In reminiscence, both arms use the same open questions; in this arm each answer is followed by a fixed acknowledgement, and the participant's own answers are arranged, unchanged, into a weekly life-story chapter. No cross-session memory. Conversational content is not sent to any external service; a local safety classifier, hosted by the research team, is used in both arms. Attention- and interface-matched active comparator. Recommended use, expected daily duration, and logging are identical to the experimen

Identical interface, navigation, companion names and personae, tool layer, notification schedule, and in-app assessment prompts. Replies are assembled from pre-written templates by keyword matching and conversational state; no language model is used. In free conversation, Siu Yan's replies are drawn in rotation from a pool of pre-written sentences. The daily check-in is a short conversation with fixed questions, followed by a pre-written response chosen by the participant's answer. In reminiscence, both arms use the same open questions; in this arm each answer is followed by a fixed acknowledgement, and the participant's own answers are arranged, unchanged, into a weekly life-story chapter. No cross-session memory. Conversational content is not sent to any external service; a local safety classifier, hosted by the research team, is used in both arms. Attention- and interface-matched active comparator. Recommended use, expected daily duration, and logging are identical to the experiment

연구는 무엇을 측정합니까?

주요 결과 측정

결과 측정
측정값 설명
기간
Session-level perceived responsiveness (primary mediator)
기간: After valid conversation sessions, at most once per companion per day, Weeks 1 through 4

Brief perceived-responsiveness measure administered in the app after valid conversation sessions. Four single items, each rated from 1 to 7, cover Understanding, Validation, Caring, and Insensitivity (reverse-scored). A free-conversation session is valid when the participant sends at least three messages and receives replies; a check-in or reminiscence session is valid when the participant completes the module. In the pre-specified primary mediation model, each participant's latent mean of these ratings is the mediator; this is not an efficacy endpoint.

After valid conversation sessions, at most once per companion per day, Weeks 1 through 4
Change in emotional loneliness (De Jong Gierveld emotional subscale)
기간: Baseline (Week 0) and Week 4

3 items, 0-3. Change from baseline to Week 4. Outcome in the primary mediation model. Assessed on paper at Weeks 0 and 4 by a trained outcome assessor who is unaware of allocation; in principle, the same assessor conducts both assessments for a participant. Power for the indirect effect was examined in a sensitivity simulation; the trial is not powered for confirmatory testing of the between-arm difference, which is reported as an effect estimate with a 95% CI.

Baseline (Week 0) and Week 4

2차 결과 측정

결과 측정
측정값 설명
기간
Emotional loneliness at Week 8
기간: Baseline (Week 0) and Week 8

De Jong Gierveld emotional subscale, 3 items, 0-3, self-administered in the app at Week 8 (the questionnaire opens on Day 56 and closes on Day 63).

Baseline (Week 0) and Week 8
Social loneliness at Week 4
기간: Baseline (Week 0) and Week 4

De Jong Gierveld social subscale, 3 items, 0-3. Tests the prediction that any difference between arms appears in emotional but not in social loneliness.

Baseline (Week 0) and Week 4
Dimensions of session-level perceived responsiveness
기간: After valid conversation sessions, Weeks 1 through 4

Understanding, Validation, Caring, and Insensitivity (reverse-scored), each rated from 1 to 7. Each dimension is examined as a mediator in a secondary analysis without correction for multiple comparisons.

After valid conversation sessions, Weeks 1 through 4
Social network size (LSNS-6)
기간: Baseline (Week 0), Week 4, and Week 8

Lubben Social Network Scale, 6-item version, completed on paper at Weeks 0 and 4 and in the app at Week 8. It is used to examine whether participants' social networks become smaller while they use the app. Within each arm, the Week 4 and Week 8 scores are compared with Week 0; no direction is predicted for the difference between arms.

Baseline (Week 0), Week 4, and Week 8

기타 결과 측정

결과 측정
측정값 설명
기간
Weekly emotional loneliness
기간: Weeks 0 through 4

De Jong Gierveld emotional subscale, 3 items, 0-3, completed in the app at Weeks 1 to 3. Together with Weeks 0 and 4, it is used to describe the trajectory of emotional loneliness with a mixed model that includes the interaction between arm and time, and to examine its within-person lagged association with weekly perceived responsiveness (exploratory).

Weeks 0 through 4
Weekly perceived responsiveness
기간: Weeks 1 through 4

Weekly perceived responsiveness questionnaire, 12 items, completed in the app.

Weeks 1 through 4
Patient Global Impression of Change in loneliness
기간: Weeks 1 through 8

One item asking how loneliness has changed compared with before the participant started using the app, with 7 options from much better to much worse, completed in the app.

Weeks 1 through 8
Weekly social contact
기간: Weeks 1 through 4

Two items completed in the app, on the number of days with in-person contact and the number of days with remote contact in the past 7 days. Used to examine whether participants use the app in place of contact with other people (exploratory).

Weeks 1 through 4
Loneliness (UCLA-3)
기간: Weeks 0, 4, and 8

Three-item UCLA Loneliness Scale.

Weeks 0, 4, and 8
Depressive symptoms (PHQ-9)
기간: Weeks 0 and 4
Weeks 0 and 4
Anxiety symptoms (GAD-7)
기간: Weeks 0 and 4
Weeks 0 and 4
Number of valid sessions
기간: Weeks 1 through 4

Number of valid conversation sessions logged by the app, using the same definition of a valid session as Primary Outcome 1.

Weeks 1 through 4
Manipulation-check ratings
기간: Weeks 1 through 4

Ratings of the companions' responses in three randomly sampled valid sessions per participant, on understanding, validation, caring, and insensitivity. The Principal Investigator codes all sampled sessions; a second coder who is not told the arm codes about 20% of them.

Weeks 1 through 4
Safety events
기간: Weeks 1 through 8

Safety events reported separately by source (participant input, scans of the AI reply, questionnaires, and assessor entries).

Weeks 1 through 8
Attitudes toward AI in mental health (AIMHS)
기간: Weeks 0, 4, and 8 (optional at Week 8)
Weeks 0, 4, and 8 (optional at Week 8)
App quality and acceptability (uMARS)
기간: Week 4
Week 4
Concerns about AI
기간: Week 4

4 study-specific items.

Week 4
Continuance intention
기간: Weeks 4 and 8

3 items.

Weeks 4 and 8
Retrospective pre-test of attitudes toward AI in mental health
기간: Week 4

AIMHS answered at Week 4 about how the participant felt before using the app (then-test).

Week 4
Ratings of the weekly life-story chapter
기간: Weeks 1 through 4

Three study-specific items, each rated from 1 to 7 after each weekly chapter is shown, on whether the chapter matches what the participant said, satisfaction with the chapter, and willingness to show it to family or friends.

Weeks 1 through 4
Daily mood
기간: Weeks 1 through 8

One optional item with five faces, which can be answered more than once a day; each answer is time-stamped.

Weeks 1 through 8
Acceptability of the app (Theoretical Framework of Acceptability questionnaire)
기간: Week 4

Generic acceptability questionnaire based on the Theoretical Framework of Acceptability (Sekhon, Cartwright and Francis, 2022), 9 items each scored from 1 to 5, covering affective attitude, burden, ethicality (2 items), intervention coherence, perceived effectiveness, self-efficacy, opportunity costs, and general acceptability. Items are reported separately by arm; no total score is formed. Completed on paper at Week 4; Cantonese translation by the research team.

Week 4

공동 작업자 및 조사자

여기에서 이 연구와 관련된 사람과 조직을 찾을 수 있습니다.

수사관

  • 수석 연구원: Junyu Zhao, The University of Hong Kong

연구 기록 날짜

이 날짜는 ClinicalTrials.gov에 대한 연구 기록 및 요약 결과 제출의 진행 상황을 추적합니다. 연구 기록 및 보고된 결과는 공개 웹사이트에 게시되기 전에 특정 품질 관리 기준을 충족하는지 확인하기 위해 국립 의학 도서관(NLM)에서 검토합니다.

연구 주요 날짜

연구 시작 (실제)

2026년 10월 21일

기본 완료 (추정된)

2027년 2월 28일

연구 완료 (추정된)

2027년 2월 28일

연구 등록 날짜

최초 제출

2026년 9월 10일

QC 기준을 충족하는 최초 제출

2026년 9월 10일

처음 게시됨 (실제)

2026년 9월 16일

연구 기록 업데이트

마지막 업데이트 게시됨 (실제)

2026년 11월 10일

QC 기준을 충족하는 마지막 업데이트 제출

2026년 11월 5일

마지막으로 확인됨

2026년 10월 1일

추가 정보

이 연구와 관련된 용어

개별 참가자 데이터(IPD) 계획

개별 참가자 데이터(IPD)를 공유할 계획입니까?

예

IPD 계획 설명

After publication, de-identified questionnaire and rating data will be provided through the Open Science Framework on reasonable request, subject to privacy review. Conversation text will not be shared.

IPD 공유 기간

The data will be available after publication of the primary results, for as long as the de-identified data are kept under the data retention policy of The University of Hong Kong.

IPD 공유 액세스 기준

Researchers can request the data by contacting the Principal Investigator through the study's Open Science Framework project page and describing the intended analysis. Data are shared after a privacy review. Applicants must sign a data use agreement before they receive the data. Conversation text is not shared.

IPD 공유 지원 정보 유형

  • 연구_프로토콜
  • 수액
  • ANALYTIC_CODE

약물 및 장치 정보, 연구 문서

미국 FDA 규제 의약품 연구

아니

미국 FDA 규제 기기 제품 연구

아니

이 정보는 변경 없이 clinicaltrials.gov 웹사이트에서 직접 가져온 것입니다. 귀하의 연구 세부 정보를 변경, 제거 또는 업데이트하도록 요청하는 경우 register@clinicaltrials.gov. 문의하십시오. 변경 사항이 clinicaltrials.gov에 구현되는 즉시 저희 웹사이트에도 자동으로 업데이트됩니다. .

구독하다