An interventional study of AI-powered sleep hygiene mentor in Sleep Wake Disorders, Sleep Initiation and Maintenance Disorders and HIV Infections, sponsored by Universitas Indonesia. Not yet recruiting at 1 site in Indonesia. Open to participants aged 18 Years and older. Per ClinicalTrials.gov, last updated 2026-10-26.
Sponsored by Universitas Indonesia · Not applicable, Interventional, and Supportive care
Poor sleep is common among people living with HIV and is linked to fatigue, psychological distress and poorer adherence to antiretroviral therapy. This study develops a mobile sleep hygiene mentor that uses artificial intelligence to give personalised sleep recommendations, with a dashboard that lets nurses follow participants and respond to risks. The mentor is built with adults living with HIV and HIV nurses and then tested for usability and feasibility. In the main evaluation, about 70 adults living with HIV with poor sleep use the mentor daily for four weeks, with two online nurse sessions, and are followed up four weeks later. The study measures sleep quality, insomnia severity, depression, anxiety and stress, fatigue, adherence to antiretroviral therapy, technology acceptance, engagement and safety.
The study uses bilateral strategic action research in three plan, act, observe and reflect cycles over about 12 months. In Cycle 1, focus groups with adults living with HIV and interviews with HIV nurses and informatics experts define the requirements of the mentor, a prototype of the mobile mentor and the nurse dashboard is built, and experts validate its content and recommendations. Cycle 1 does not involve use of the mentor by participants. In Cycle 2, about 30 adults living with HIV use the prototype for four weeks with two nurse monitoring sessions, and usability (System Usability Scale), usage logs, system errors and interviews are collected. A joint reflection with the international partner, nurses and community representatives decides on changes, and the version of the mentor (content library, machine learning model and alert rules) is then frozen. In Cycle 3, about 70 adults living with HIV use the frozen version for four weeks (weeks 1 to 4), with nurse monitoring sessions in weeks 2 and 4, and complete questionnaires at baseline and at week 8. The mentor selects recommendations only from an expert-validated library, does not give advice on medicines, and sends alerts to nurses for severe insomnia, possible sleep apnoea, high distress, missed doses and inactivity. Feasibility is judged against prespecified progression criteria for a future randomised controlled trial. About 10 to 15 participants and the nurses are interviewed at follow-up.
804 studies on the registry are indexed under Sleep Wake Disorders; 188 are open to participants now.
This study's planned enrollment of 100 is above the median of 62 across 556 interventional studies indexed under Sleep Wake Disorders.
Browse Sleep Wake Disorders studies →Universitas Indonesia is the lead sponsor of 29 studies on the registry; 12 are open to participants now.
Counted across the registry records on this site, refreshed daily.
Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.
Exclusion Criteria:
Four weeks of daily use of the mobile sleep hygiene mentor with nurse oversight through a dashboard and two online nurse monitoring sessions (weeks 2 and 4).
Behavioral: AI-powered sleep hygiene mentor
A mobile application with a daily check-in of 5 to 10 minutes on sleep, daily habits, stress and the time antiretroviral medicine was taken. A machine learning model selects one to three recommendations a day from an expert-validated sleep hygiene library and explains why each was chosen. Educational modules cover sleep and HIV, a regular sleep schedule, the sleep environment, caffeine and alcohol, evening screen use, relaxation and worry management, and links between sleep, mood and adherence. Trained nurses monitor participants through a dashboard with rule-based alerts and hold two online sessions of 20 to 30 minutes in weeks 2 and 4. An optional online peer support group may be offered.
Also known as: Sleep Hygiene Mentor, AI sleep mentor
Change in sleep quality
Change from baseline in the Pittsburgh Sleep Quality Index global score. Range 0 to 21; higher scores indicate poorer sleep quality.
Time frame: Baseline (week 0) and week 8
Insomnia severity
Insomnia Severity Index total score. Range 0 to 28; higher scores indicate more severe insomnia.
Time frame: Weeks 0 and 8
Depression
Depression subscale of the 21-item Depression Anxiety Stress Scales, multiplied by 2. Range 0 to 42; higher scores indicate more depression.
Time frame: Weeks 0 and 8
Anxiety
Anxiety subscale of the 21-item Depression Anxiety Stress Scales, multiplied by 2. Range 0 to 42; higher scores indicate more anxiety.
Time frame: Weeks 0 and 8
Stress
Stress subscale of the 21-item Depression Anxiety Stress Scales, multiplied by 2. Range 0 to 42; higher scores indicate more stress.
Time frame: Weeks 0 and 8
Fatigue
FACIT-Fatigue subscale score. Range 0 to 52; higher scores indicate less fatigue.
Time frame: Weeks 0 and 8
Adherence to antiretroviral therapy
Three-item self-report adherence scale for the past 30 days. Range 0 to 100; higher scores indicate better adherence.
Time frame: Weeks 0 and 8
Perceived usefulness of the mentor
Mean score of study-specific Technology Acceptance Model items on perceived usefulness, developed and validated in Cycle 1; higher scores indicate greater perceived usefulness.
Time frame: Weeks 0 and 8
Perceived ease of use of the mentor
Mean score of study-specific Technology Acceptance Model items on perceived ease of use, developed and validated in Cycle 1; higher scores indicate greater ease of use.
Time frame: Weeks 0 and 8
Health beliefs about sleep
Mean score of study-specific Health Belief Model items on sleep, developed and validated in Cycle 1; higher scores indicate stronger beliefs supporting healthy sleep behaviour.
Time frame: Weeks 0 and 8
Usability of the mentor
System Usability Scale total score. Range 0 to 100; higher scores indicate better usability.
Time frame: Week 4 (Cycle 2) and week 8 (Cycle 3)
Engagement with the mentor
Number of days with a completed daily check-in, from app usage logs.
Time frame: Weeks 1 to 4
Recruitment rate
Number of participants enrolled in Cycle 3, expressed as a percentage of the target sample of 70.
Time frame: 3 months from the start of Cycle 3 recruitment
Retention to follow-up
Percentage of enrolled Cycle 3 participants who complete the week 8 assessment.
Time frame: Week 8
Attendance at nurse monitoring sessions
Percentage of participants who attend at least 1 of the 2 nurse monitoring sessions.
Time frame: Weeks 2 and 4
Number of participants with adverse events
Number of participants with at least one adverse event, including events possibly related to the mentor.
Time frame: Weeks 0 to 8
Plan to share: Yes — De-identified individual participant data underlying the published results will be shared.
Supporting information: Study protocol
Time frame: After publication of the main findings.
Access criteria: Reasonable request to the corresponding author, subject to approval by the Ethics Review Committee, Faculty of Nursing, Universitas Indonesia.
No publications or documents are linked to this record.
Start is estimated for Mar 2027; primary completion for Nov 2027, 8 months later.
Of 229 non-industry interventional studies with no phase under Sleep Wake Disorders, half reached primary completion within 19 months of starting (the median), counting those still running; a quarter within 7 and three quarters within 37. This study's planned 8 months is below that.
Counting every sponsor, half of 266 studies reached it within 17 months; a quarter within 6 and three quarters within 35.
How these figures are worked out, and which studies are left out of them.
From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗
This study is not yet recruiting, as verified in Oct 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
Universitas Indonesia