NCT Number: NCT07787403
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.
Trial opening soon.
Get Notified18 year and older
All sexes
Interventional
Not applicable
This study is a pilot randomized controlled trial designed to assess the feasibility, effectiveness, and acceptance of the PIPE-AI platform enhanced by DiabetesGPT before broader implementation in primary healthcare settings. The PIPE-AI platform integrates individualized risk assessments and a locally fine-tuned large language model, DiabetesGPT, to generate personalized health advice and patient empowerment support for people with prediabetes or diabetes.
Approximately 50 participants will be recruited and randomized in a 1:1 ratio to the intervention group or waitlist control group. Eligibility will be assessed by nurses and doctors in participating primary healthcare settings. After written informed consent, trained research assistants will conduct baseline assessments, including demographic and socioeconomic data, lifestyle behaviours, medical history, current medications, patient-reported outcome measures, and venous blood sampling for fasting glucose and HbA1c.
Randomization will be performed before recruitment by a statistician using R software. After baseline assessment, participants will receive an opaque letter containing their assigned group and follow-up instructions. Research assistants involved in subject recruitment and baseline assessment will be blinded to grouping to reduce measurement bias where operationally feasible.
Participants in the intervention group will install the PIPE-AI app and receive instructions on how to use it. An individualized patient empowerment programme will be provided during the 3-month follow-up period. App login frequency will be monitored on the server, and reminders may be sent by SMS, WhatsApp, or WeChat if a participant does not log in within one week after recruitment or stops logging in for more than one month.
Participants in the control group will follow a waitlist approach. During the first 3 months, they will receive usual care, including group-based patient empowerment programmes where available through 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 app.
All RCT participants in both groups will use Abbott FreeStyle Libre 2 Plus continuous glucose monitoring sensors intermittently during the 3-month trial. After successful enrolment and baseline assessments, participants receive two CGM sensors for use during Weeks 1-4. If CGM data are successfully collected in the study system, the research team will contact the participant near the end of the trial to collect a third CGM sensor for use during Weeks 11-12. CGM data will be downloaded or exported for research analysis using pseudonymized study IDs.
Participants in both groups will complete a 3-month follow-up assessment, including patient-reported outcome measures, clinical outcomes, healthcare service utilization, and CGM-related data where applicable. Main analysis will adopt an intention-to-treat principle, with per-protocol analysis as sensitivity analysis. As this is a pilot RCT, CGM analyses will be exploratory and will assess feasibility, adherence, completeness of CGM data collection, glycaemic profiles, and signal of change for future definitive trials.
Healthy volunteers accepted: No
Only the study team can determine whether someone qualifies for participation.
Inclusion criteria
Exclusion criteria
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.
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.
Time frame: Baseline and 3-month follow-up
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.
Time frame: Baseline and 3-month follow-up
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.
Time frame: Baseline and 3-month follow-up
HbA1c will be tested by the study team or obtained through study procedures. The endpoint is the change in HbA1c from baseline to the 3-month follow-up, using the same unit at both time points.
Time frame: 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.
Time frame: 3-month follow-up
User satisfaction with the PIPE-AI programme will be assessed at follow-up using study questionnaires among participants with access to the intervention. Scores or item responses will be summarized descriptively according to the final questionnaire scoring rule.
Time frame: Baseline to 3-month follow-up
Adverse events will be recorded during the trial and summarized as the number and proportion of participants reporting any adverse event. CGM-related discomforts, skin reactions, sensor issues, and other device-related problems will be summarized separately when applicable.
Time frame: Weeks 1-4 and Weeks 11-12
Mean sensor glucose will be calculated as the arithmetic mean of all valid Abbott FreeStyle Libre 2 Plus sensor glucose readings within each planned wear period and reported in mmol/L. Values will be summarized separately for Weeks 1-4 and Weeks 11-12 and compared descriptively within and between randomized groups.
Time frame: Weeks 1-4 and Weeks 11-12
Glucose variability will be reported as the coefficient of variation, calculated as 100 multiplied by the standard deviation of valid sensor glucose readings divided by mean sensor glucose within each planned wear period. The unit is percent; lower values indicate less glucose variability. Values will be summarized separately for Weeks 1-4 and Weeks 11-12.
Time frame: Weeks 1-4 and Weeks 11-12
Time in range is the percentage of valid sensor glucose readings from 3.9 to 10.0 mmol/L, inclusive, within each planned CGM wear period. The possible range is 0% to 100%; a higher percentage indicates more time within the target glucose range. Values will be summarized separately for Weeks 1-4 and Weeks 11-12.
Time frame: Weeks 1-4 and Weeks 11-12
Time above range is the percentage of valid sensor glucose readings greater than 10.0 mmol/L within each planned CGM wear period. The possible range is 0% to 100%; a lower percentage indicates less exposure to hyperglycaemia. Values will be summarized separately for Weeks 1-4 and Weeks 11-12.
Time frame: Weeks 1-4 and Weeks 11-12
Time below range is the percentage of valid sensor glucose readings less than 3.9 mmol/L within each planned CGM wear period. The possible range is 0% to 100%; a lower percentage indicates less exposure to hypoglycaemia. Values will be summarized separately for Weeks 1-4 and Weeks 11-12.
Time frame: Weeks 1-4 and Weeks 11-12
A CGM-detected hypoglycaemia episode is defined as sensor glucose less than 3.9 mmol/L for at least 15 consecutive minutes. The outcome is the number of episodes within each planned CGM wear period, reported as a count from 0 upward; a lower count indicates fewer hypoglycaemia episodes. Counts will be summarized separately for Weeks 1-4 and Weeks 11-12.
Time frame: Weeks 1-4 and Weeks 11-12
For CGM-detected hypoglycaemia episodes defined as sensor glucose less than 3.9 mmol/L for at least 15 consecutive minutes, the total duration of all qualifying episodes within each planned CGM wear period will be reported in minutes. The possible range is 0 minutes upward; a lower duration indicates less exposure to hypoglycaemia.
Time frame: Weeks 1-4 and Weeks 11-12
A CGM-detected hyperglycaemia episode is defined as sensor glucose greater than 10.0 mmol/L for at least 15 consecutive minutes. The outcome is the number of episodes within each planned CGM wear period, reported as a count from 0 upward; a lower count indicates fewer hyperglycaemia episodes. Counts will be summarized separately for Weeks 1-4 and Weeks 11-12.
Time frame: Weeks 1-4 and Weeks 11-12
For CGM-detected hyperglycaemia episodes defined as sensor glucose greater than 10.0 mmol/L for at least 15 consecutive minutes, the total duration of all qualifying episodes within each planned CGM wear period will be reported in minutes. The possible range is 0 minutes upward; a lower duration indicates less exposure to hyperglycaemia.
Contact information is provided by the study sponsor or research team.
Shuya Lu
CONTACT
Yang Lin, Doctor
CONTACT
The Hong Kong Polytechnic University
Other
A Personalized Interactive Patient Empowerment Artificial Intelligence Platform (PIPE-AI) Enhanced by DiabetesGPT in Prediabetes and Diabetes Patients in Primary Healthcare Settings
Acronym: PIPE-AI
OpenTrials presents study information sourced from ClinicalTrials.gov. The official registry record should be consulted for the latest information.
View the official ClinicalTrials.gov record (opens in a new tab)This listing is for discovery and informational purposes only. It is not medical advice, does not guarantee that a study is recruiting, and does not determine eligibility. Contact the study team and a qualified healthcare professional when considering participation.
Published trials that share one or more normalized conditions with this study.
NCT07795918
Diabetes Mellitus, Diabetes Mellitus, Type 2
Irbid, Irbid Governorate, Jordan
View Trial DetailsNCT07377097
Cardiovascular (CV) Risk, Cardiovascular Diseases
View Trial DetailsNCT07728591
Body Weight, Diabetes Mellitus
Luzhou, Sichuan, China
View Trial DetailsNCT07652528
Diabetes Mellitus, Diabetes Mellitus, Type 2
View Trial Details