このページは自動翻訳されたものであり、翻訳の正確性は保証されていません。を参照してください。 英語版 ソーステキスト用。

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

2026年11月5日 更新者: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.

調査の概要

詳細な説明

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.

研究の種類

介入

入学 (推定)

72

段階

  • 適用できない

連絡先と場所

このセクションには、調査を実施する担当者の連絡先の詳細と、この調査が実施されている場所に関する情報が記載されています。

研究連絡先

研究場所

    • Hong Kong SAR
      • Hong Kong、Hong Kong SAR、香港、999077
        • 募集
        • The University of Hong Kong
        • コンタクト:

参加基準

研究者は、適格基準と呼ばれる特定の説明に適合する人を探します。これらの基準のいくつかの例は、人の一般的な健康状態または以前の治療です。

適格基準

就学可能な年齢

60年歳以上 (大人、高齢者)

健康ボランティアの受け入れ

はい

受講資格のある性別

全て

説明

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

研究計画

このセクションでは、研究がどのように設計され、研究が何を測定しているかなど、研究計画の詳細を提供します。

研究はどのように設計されていますか?

デザインの詳細

  • 主な目的:基礎科学
  • 割り当て:ランダム化
  • 介入モデル:並列代入
  • マスキング:ダブル

武器と介入

参加者グループ / アーム
介入・治療
実験的: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.

アクティブコンパレータ: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

この研究は何を測定していますか?

主要な結果の測定

結果測定
メジャーの説明
時間枠
Session-level perceived responsiveness (primary mediator)
時間枠: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)
時間枠: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

二次結果の測定

結果測定
メジャーの説明
時間枠
Emotional loneliness at Week 8
時間枠: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
時間枠: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
時間枠: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)
時間枠: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

その他の成果指標

結果測定
メジャーの説明
時間枠
Weekly emotional loneliness
時間枠: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
時間枠: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
時間枠: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
時間枠: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)
時間枠:Weeks 0, 4, and 8

Three-item UCLA Loneliness Scale.

Weeks 0, 4, and 8
Depressive symptoms (PHQ-9)
時間枠:Weeks 0 and 4
Weeks 0 and 4
Anxiety symptoms (GAD-7)
時間枠:Weeks 0 and 4
Weeks 0 and 4
Number of valid sessions
時間枠: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
時間枠: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
時間枠: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)
時間枠:Weeks 0, 4, and 8 (optional at Week 8)
Weeks 0, 4, and 8 (optional at Week 8)
App quality and acceptability (uMARS)
時間枠:Week 4
Week 4
Concerns about AI
時間枠:Week 4

4 study-specific items.

Week 4
Continuance intention
時間枠:Weeks 4 and 8

3 items.

Weeks 4 and 8
Retrospective pre-test of attitudes toward AI in mental health
時間枠: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
時間枠: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
時間枠: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)
時間枠: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

協力者と研究者

ここでは、この調査に関係する人々や組織を見つけることができます。

スポンサー

捜査官

  • 主任研究者:Junyu Zhao、The University of Hong Kong

研究記録日

これらの日付は、ClinicalTrials.gov への研究記録と要約結果の提出の進捗状況を追跡します。研究記録と報告された結果は、国立医学図書館 (NLM) によって審査され、公開 Web サイトに掲載される前に、特定の品質管理基準を満たしていることが確認されます。

主要日程の研究

研究開始 (実際)

2026年10月21日

一次修了 (推定)

2027年2月28日

研究の完了 (推定)

2027年2月28日

試験登録日

最初に提出

2026年9月10日

QC基準を満たした最初の提出物

2026年9月10日

最初の投稿 (実際)

2026年9月16日

学習記録の更新

投稿された最後の更新 (実際)

2026年11月10日

QC基準を満たした最後の更新が送信されました

2026年11月5日

最終確認日

2026年10月1日

詳しくは

本研究に関する用語

個々の参加者データ (IPD) の計画

個々の参加者データ (IPD) を共有する予定はありますか?

はい

IPD プランの説明

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 共有時間枠

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 共有アクセス基準

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 共有サポート情報タイプ

  • STUDY_PROTOCOL
  • SAP
  • ANALYTIC_CODE

医薬品およびデバイス情報、研究文書

米国FDA規制医薬品の研究

いいえ

米国FDA規制機器製品の研究

いいえ

この情報は、Web サイト clinicaltrials.gov から変更なしで直接取得したものです。研究の詳細を変更、削除、または更新するリクエストがある場合は、register@clinicaltrials.gov。 までご連絡ください。 clinicaltrials.gov に変更が加えられるとすぐに、ウェブサイトでも自動的に更新されます。

購読する