Pilot RCT of PIPE-AI for Prediabetes and Diabetes Self-Management

NCT07787403 | Not Yet Recruiting

• 4 other identifiers: PIPE-AI-RCT22231421HSEARS20240614004CIRB-2024-566-4
• Study Type: interventional
• Target: 50
• Locations: 0 countries
• Sites: N/A

Brief Summary

This pilot randomized controlled trial evaluates the feasibility, effectiveness, and acceptance of the Personalized Interactive Patient Empowerment Artificial Intelligence Platform (PIPE-AI) enhanced by DiabetesGPT among adults with prediabetes or diabetes in Hong Kong primary healthcare settings. Participants will be randomized in a 1:1 ratio to an intervention group receiving PIPE-AI or to a waitlist control group receiving usual care during the first 3 months. Both groups will complete baseline and 3-month assessments, including patient-reported outcome measures, clinical outcomes, healthcare service utilization, and intermittent continuous glucose monitoring using Abbott FreeStyle Libre 2 Plus sensors.

Conditions

Prediabetes / Type 2 Diabetes; Diabetes Mellitus, Type 2; Prediabetes

Keywords

PIPE-AI; DiabetesGPT; Prediabetes; Type 2 diabetes; Diabetes self-management; Patient empowerment; Digital health; Artificial intelligence; Continuous glucose monitoring; Primary healthcare; Hong Kong; Pilot randomized controlled trial

Outcome Measures

Primary Outcomes (2)

• Change in Diabetes Self-Management Questionnaire total score from baseline to 3 months

  Diabetes self-management is assessed using the 16-item Diabetes Self-Management Questionnaire (DSMQ). After reverse scoring the applicable items, the DSMQ total score is transformed to a scale from 0 to 10 points; higher scores indicate better diabetes self-management. The reported outcome is the change score calculated as the 3-month total score minus the baseline total score, with a possible range from -10 to 10 points. A positive change indicates improvement.

  Baseline and 3-month follow-up

• Change in Michigan Diabetes Knowledge Test 2 general knowledge score from baseline to 3 months

  Diabetes knowledge is assessed using the 14-item general knowledge section of the Michigan Diabetes Knowledge Test 2 (DKT2). Each correct answer receives 1 point and an incorrect or missing answer receives 0 points. The general knowledge score ranges from 0 to 14 points; higher scores indicate greater diabetes knowledge. The reported outcome is the change score calculated as the 3-month score minus the baseline score, with a possible range from -14 to 14 points. A positive change indicates improvement.

  Baseline and 3-month follow-up

Secondary Outcomes (3)

• Change in HbA1c from baseline to 3 months

  Baseline and 3-month follow-up

• Change in fasting glucose from baseline to 3 months

  Baseline and 3-month follow-upFasting glucose will be measured by the study team or obtained through study procedures. The endpoint is the change in fasting glucose from baseline to the 3-month follow-up, using the same unit at both time points.

• User satisfaction with the PIPE-AI programme

  3-month follow-up

Other Outcomes (10)

• Incidence of adverse events

  Baseline to 3-month follow-up

• Mean sensor glucose during planned CGM wear periods

  Weeks 1-4 and Weeks 11-12

• Glucose coefficient of variation during planned CGM wear periods

  Weeks 1-4 and Weeks 11-12

Study Arms (2)

PIPE-AI Intervention Group

EXPERIMENTAL

Participants assigned to the intervention group will install and use the PIPE-AI app. Research assistants will provide detailed instructions on app use. An individualized patient empowerment programme will be provided during the 3-month follow-up period. App login frequency will be monitored, and reminders may be sent by SMS, WhatsApp, or WeChat when needed. Participants will also undergo the same baseline and 3-month assessments and intermittent CGM procedures as the control group.

Behavioral: PIPE-AI digital patient empowerment intervention

Waitlist Control Group

ACTIVE COMPARATOR

Participants assigned to the waitlist control group will receive usual care during the first 3 months. Depending on recruitment source, usual care may include group-based patient empowerment programmes provided by the District Health Centre, general guidance from the Hong Kong Reference Framework for Diabetes Care for Adults in Primary Care Settings, or routine diabetes education and management services in their respective clinics. After the 3-month follow-up assessment, control group participants will be given access to the PIPE-AI app. Participants will also undergo the same baseline and 3-month assessments and intermittent CGM procedures as the intervention group.

Other: Waitlist usual care control

Interventions

PIPE-AI digital patient empowerment intervention BEHAVIORAL

PIPE-AI is a personalized interactive patient empowerment artificial intelligence platform enhanced by DiabetesGPT. It integrates individualized risk assessment and a locally fine-tuned large language model to provide personalized health advice, diabetes self-management support, and patient empowerment during the 3-month follow-up period.

PIPE-AI Intervention Group

Waitlist usual care control OTHER

Participants receive usual care during the first 3 months and are given access to the PIPE-AI app after completion of the 3-month follow-up assessment.

Waitlist Control Group

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Adults aged 18 years or older.
• Diagnosed with prediabetes or diabetes by their family doctors.
• Able to understand Chinese.
• Possess a mobile phone that can install the app developed for this project.

You may not qualify if:

• Under legal guardianship.
• Comorbid schizophrenia.
• Intellectual disability.
• Incompetent in giving consent.
• Other significant cognitive disorders.

Sponsors & Collaborators

• The Hong Kong Polytechnic University: lead

MeSH Terms

Conditions

Prediabetic State; Diabetes Mellitus, Type 2; Patient Participation

Condition Hierarchy (Ancestors)

Diabetes Mellitus; Glucose Metabolism Disorders; Metabolic Diseases; Nutritional and Metabolic Diseases; Endocrine System Diseases; Patient Acceptance of Health Care; Treatment Adherence and Compliance; Health Behavior; Behavior

Study Officials

• Lin Yang, Doctor

  The Hong Kong Polytechnic University

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Shuya Lu

CONTACT

+86 18030800242; shuya.lu@connect.polyu.hk

Yang Lin, Doctor

CONTACT

+852 27666398; l.yang@polyu.edu.hk

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Masking Details: Participants and intervention staff cannot be blinded because the intervention group receives access to the PIPE-AI app. Participants will be randomized in a 1:1 ratio using sequentially numbered, opaque, sealed envelopes prepared before recruitment according to a pre-generated randomization list. After eligibility confirmation, written informed consent, and baseline assessment, the next available envelope will be opened according to the study SOP to reveal the assigned group and follow-up instructions. The envelope system is used for allocation concealment before assignment and to reduce selection bias.
• Purpose: SUPPORTIVE CARE
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: Randomization will be performed before recruitment by a statistician. After baseline assessment, each participant will receive an opaque letter containing the assigned group and follow-up instructions. Research assistants involved in subject recruitment and baseline assessment will be blinded to group allocation to reduce measurement bias where operationally feasible. Participants cannot be blinded to PIPE-AI access.

Study Record Dates

• First Submitted: July 23, 2026
• First Posted: August 26, 2026
• Study Start: August 29, 2026
• Primary Completion (Estimated): November 29, 2026
• Study Completion (Estimated): November 29, 2026
• Last Updated: August 26, 2026

Record last verified: 2026-08