Tämä sivu käännettiin automaattisesti, eikä käännösten tarkkuutta voida taata. Katso englanninkielinen versio lähdetekstiä varten.

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

torstai 5. marraskuuta 2026 päivittänyt: 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.

Tutkimuksen yleiskatsaus

Yksityiskohtainen kuvaus

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.

Opintotyyppi

Interventio

Ilmoittautuminen (Arvioitu)

72

Vaihe

  • Ei sovellettavissa

Yhteystiedot ja paikat

Tässä osiossa on tutkimuksen suorittajien yhteystiedot ja tiedot siitä, missä tämä tutkimus suoritetaan.

Opiskeluyhteys

Opiskelupaikat

    • Hong Kong SAR
      • Hong Kong, Hong Kong SAR, Hong Kong, 999077
        • Rekrytointi
        • The University of Hong Kong
        • Ottaa yhteyttä:

Osallistumiskriteerit

Tutkijat etsivät ihmisiä, jotka sopivat tiettyyn kuvaukseen, jota kutsutaan kelpoisuuskriteereiksi. Joitakin esimerkkejä näistä kriteereistä ovat henkilön yleinen terveydentila tai aiemmat hoidot.

Kelpoisuusvaatimukset

Opintokelpoiset iät

60 vuotta ja vanhemmat (Aikuinen, Vanhempi Aikuinen)

Hyväksyy terveitä vapaaehtoisia

Joo

Sukupuolet, jotka voivat opiskella

Kaikki

Kuvaus

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

Opintosuunnitelma

Tässä osiossa on tietoja tutkimussuunnitelmasta, mukaan lukien kuinka tutkimus on suunniteltu ja mitä tutkimuksella mitataan.

Miten tutkimus on suunniteltu?

Suunnittelun yksityiskohdat

  • Ensisijainen käyttötarkoitus: Perustiede
  • Jako: Satunnaistettu
  • Inventiomalli: Rinnakkaistehtävä
  • Naamiointi: Kaksinkertainen

Aseet ja interventiot

Osallistujaryhmä / Arm
Interventio / Hoito
Kokeellinen: 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.

Active Comparator: 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

Mitä tutkimuksessa mitataan?

Ensisijaiset tulostoimenpiteet

Tulosmittaus
Toimenpiteen kuvaus
Aikaikkuna
Session-level perceived responsiveness (primary mediator)
Aikaikkuna: 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)
Aikaikkuna: 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

Toissijaiset tulostoimenpiteet

Tulosmittaus
Toimenpiteen kuvaus
Aikaikkuna
Emotional loneliness at Week 8
Aikaikkuna: 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
Aikaikkuna: 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
Aikaikkuna: 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)
Aikaikkuna: 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

Muut tulostoimenpiteet

Tulosmittaus
Toimenpiteen kuvaus
Aikaikkuna
Weekly emotional loneliness
Aikaikkuna: 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
Aikaikkuna: 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
Aikaikkuna: 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
Aikaikkuna: 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)
Aikaikkuna: Weeks 0, 4, and 8

Three-item UCLA Loneliness Scale.

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

4 study-specific items.

Week 4
Continuance intention
Aikaikkuna: Weeks 4 and 8

3 items.

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

Yhteistyökumppanit ja tutkijat

Täältä löydät tähän tutkimukseen osallistuvat ihmiset ja organisaatiot.

Tutkijat

  • Päätutkija: Junyu Zhao, The University of Hong Kong

Opintojen ennätyspäivät

Nämä päivämäärät seuraavat ClinicalTrials.gov-sivustolle lähetettyjen tutkimustietueiden ja yhteenvetojen edistymistä. National Library of Medicine (NLM) tarkistaa tutkimustiedot ja raportoidut tulokset varmistaakseen, että ne täyttävät tietyt laadunvalvontastandardit, ennen kuin ne julkaistaan ​​julkisella verkkosivustolla.

Opi tärkeimmät päivämäärät

Opiskelun aloitus (Todellinen)

Keskiviikko 21. lokakuuta 2026

Ensisijainen valmistuminen (Arvioitu)

Sunnuntai 28. helmikuuta 2027

Opintojen valmistuminen (Arvioitu)

Sunnuntai 28. helmikuuta 2027

Opintoihin ilmoittautumispäivät

Ensimmäinen lähetetty

Torstai 10. syyskuuta 2026

Ensimmäinen toimitettu, joka täytti QC-kriteerit

Torstai 10. syyskuuta 2026

Ensimmäinen Lähetetty (Todellinen)

Keskiviikko 16. syyskuuta 2026

Tutkimustietojen päivitykset

Viimeisin päivitys julkaistu (Todellinen)

Tiistai 10. marraskuuta 2026

Viimeisin lähetetty päivitys, joka täytti QC-kriteerit

Torstai 5. marraskuuta 2026

Viimeksi vahvistettu

Torstai 1. lokakuuta 2026

Lisää tietoa

Tähän tutkimukseen liittyvät termit

Yksittäisten osallistujien tietojen suunnitelma (IPD)

Aiotko jakaa yksittäisten osallistujien tietoja (IPD)?

JOO

IPD-suunnitelman kuvaus

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-jaon aikakehys

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-jaon käyttöoikeuskriteerit

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-jakamista tukeva tietotyyppi

  • STUDY_PROTOCOL
  • MAHLA
  • ANALYTIC_CODE

Lääke- ja laitetiedot, tutkimusasiakirjat

Tutkii yhdysvaltalaista FDA sääntelemää lääkevalmistetta

Ei

Tutkii yhdysvaltalaista FDA sääntelemää laitetuotetta

Ei

Nämä tiedot haettiin suoraan verkkosivustolta clinicaltrials.gov ilman muutoksia. Jos sinulla on pyyntöjä muuttaa, poistaa tai päivittää tutkimustietojasi, ota yhteyttä register@clinicaltrials.gov. Heti kun muutos on otettu käyttöön osoitteessa clinicaltrials.gov, se päivitetään automaattisesti myös verkkosivustollemme .

Tilaa