Therapeutic Efficacy and Safety Evaluation of AI in the Management of Diabetes: A RCT Trial

Summary

Purpose: To evaluate the efficacy of artificial intelligence (AI)-based decision-making technology in managing glycated hemoglobin (HbA1c) and blood glucose levels compared to the control group.

Methods: For the AI Intervention group, the patients will be trained to independently use the diabetes telemedicine platform application. Each patient will be equipped with a glucometer and exercise bracelet, and the data will be automatically transmitted to the medical server via Bluetooth. The healthcare platform will analyze the uploaded data and provide feedback suggestions on medication, diet, and exercise automatically. The platform will also monitor the medical and lifestyle data of the patients every two weeks, offer feedback based on the analyses, and remind the patient to adhere to the self-management protocol based on the platform. The platform is a digitally integrated healthcare platform that patients can use independently without the need for monitoring and assistance by healthcare professionals. The glucometer and pedometer bracelet will automatically connect to the platform through Bluetooth. The patient lab sheet identification and structured conversion system, AI for food picture identification and calorie calculation systems, and the AI decision-making system are on the cloud server. Patients upload image information, such as lab sheets and meal pictures, through the patient's diabetes mobile health system, and the cloud platform intelligently analyzes the patient's disease, medication, and daily life status to develop personalized solutions according to individual control goals. Free outpatient visits will be provided to both the intervention and control groups every twelve weeks. For the conventional treatment group, patients will receive a free blood glucometer and will have regular outpatient appointments. There is no limit to the number of outpatient visits; however, they are required to regularly monitor and record their blood glucose, diet, and exercise data to ensure that the medical team objectively conduct their diagnosis and treatment activities. The medical team will provide free outpatient visits every 12 weeks, along with advice on medication, diet, and exercise based on the individual's blood glucose level.

Expected results: A significant difference in HbA1c change from baseline to 48 weeks and improved FPG and 2-hour postprandial blood glucose levels in the AI intervention group were observed.

Conditions

• Diabetes Mellitus Type 2 (T2DM)
• Artificial Intelligence (AI)

Interventions

OTHER

artificial intelligence

The platform will also monitor the medical and lifestyle data of the patients every two weeks,offer feedback based on the analyses, and remind the patient to adhere to the self-management protocol based on the platform.

OTHER

Routine diagnosis and treatment group for diabetes

There is no limit to the number of outpatient visits for the control group; however, they are required to regularly monitor and record their blood glucose, diet, and exercise data to ensure that the medical team (endocrinologist and nutritionist) objectively conducttheir diagnosis and treatment activities. The medical team will provide free outpatient visits every 12 weeks, along with advice on medication, diet, and exercise based on the individual's blood glucose level.

Sponsors & Collaborators

• The First Hospital of Jilin University

  lead OTHER

Principal Investigators

• Chenglin Sun, Doctor · The First Hospital of Jilin University

Study Design

Allocation

RANDOMIZED

Purpose

TREATMENT

Masking

NONE

Model

PARALLEL

Eligibility

Min Age

18 Years

Max Age

75 Years

Sex

ALL

Healthy Volunteers

No

Timeline & Regulatory

Start

2025-06-15

Primary Completion

2026-12-31

Completion

2026-12-31

Countries

• China

Study Locations