AI-guided app to help manage type 2 diabetes

Evaluation of the Therapeutic Efficacy and Safety of Artificial Intelligence-based Decision-making Technology in the Integrated Management of Diabetes Mellitus: a Longitudinal, Open-labeled, Randomized Controlled Trial

This project will try an AI-guided app that uses glucose and activity data to give adults with type 2 diabetes personalized medication, diet, and exercise suggestions to help lower blood sugar.

Quick facts

• Phase: Not applicable
• Study type: Interventional
• Enrollment: 400 (estimated)
• Ages: 18 Years to 75 Years
• Sex: All
• Sponsor: The First Hospital of Jilin University (Academic / other)
• Locations: 1 site (Changchun, Jilin)
• Trial ID: NCT06957093 on ClinicalTrials.gov

What this trial studies

The trial randomizes adults with type 2 diabetes to an AI-supported telemedicine platform versus routine care. Participants in the AI arm will be trained to use a smartphone app connected by Bluetooth to a glucometer and an activity bracelet so data are automatically uploaded to a medical server. The platform analyzes glucose, activity, and lifestyle data every two weeks and provides automated feedback, reminders, and recommendations about medication, diet, and exercise. Clinical visits and lab tests including HbA1c are scheduled at baseline and every 12 weeks up to 48 weeks to compare glycemic outcomes between groups.

Who should consider this trial

Good fit: Adults aged 18–75 with type 2 diabetes for at least one year, HbA1c between 7.0% and 11%, BMI ≥18.5 kg/m2, and comfortable using a smartphone are the intended participants.

Not a fit: Patients with type 1 or gestational diabetes, severe diabetic complications, significant liver or kidney disease, recent substance abuse, major psychiatric illness, or inability to use a smartphone are unlikely to benefit from or be eligible for this intervention.

Why it matters

Potential benefit: If successful, the AI platform could lower HbA1c and improve day-to-day glucose control by delivering timely, personalized self-management advice.

How similar studies have performed: Previous telemedicine and AI-assisted diabetes programs have shown modest HbA1c improvements in some randomized trials but results are variable and long-term benefits remain uncertain.

Eligibility criteria

Inclusion Criteria：

* Age: ≥18 years，≤75 years;
* Diagnosed with type 2 diabetes for ≥1 year;
* 7.0% ≤HbA1c ≤11%;
* Body mass index ≥18.5 kg/m2;
* Proficient ability to use smart phones;
* Agreed to utilize a digital integrated healthcare platform for diabetes care and research;
* Informed consents are obtained from the participants.

Exclusion Criteria:

* Presence of other types of diabetes, such as type 1 diabetes and gestational diabetes;
* Severe diabetic complications;
* Medical history of chronic liver diseases, including hemochromatosis, hepatocellular carcinoma, autoimmune liver disease, cirrhosis, viral hepatitis (including hepatitis A, B, and C), or hepatolenticular degeneration;
* Kidney injury (serum creatinine ≥1.5 times the upper limit of the reference) ; Serum ALT and AST levels elevated \>2-fold;
* Medical history of mental disorders, such asschizophrenia, depression, or bipolar affective disorder;
* Excessive alcohol intake or drug abuse in the past 3 months;
* Use of medications affecting glucose metabolism, such as corticosteroids or ·consumption of immunosuppressive and anti-obesity medications in the past 3 months;
* Pregnancy, planning for pregnancy, or lactation; or any other conditions unsuitable for trial participation;
* Participatingor plan to participate in other clinical trials; and other cases that are inappropriate to participate.

Where this trial is running

Changchun, Jilin

• The First Hospital of Jilin University — Changchun, Jilin, China (Recruiting)

Study contacts

• Principal investigator: Chenglin Sun, Doctor — The First Hospital of Jilin University
• Study coordinator: Chenglin Sun, Doctor

Conditions Diabetes Mellitus Type 2; Artificial Intelligence; Diabetes mellitus type 2