RecruitingNot ApplicableNCT07066891

Validation of Insulin Dose Prediction Model Based on Artificial Intelligence Algorithm

Validation of Insulin Dose Prediction Model Based on Long Short- Term Memory Artificial Intelligence Algorithm

Sponsor

Sun Yat-sen University

Enrollment

400 participants

Start Date

Jul 15, 2025

Study Type

INTERVENTIONAL

Conditions

Diabetes Mellitus Type 2 Diabetes

Summary

The present study aims to conduct a prospective controlled trial comparing an LSTM-based artificial intelligence (AI) prediction model and clinicians' experience in the efficacy and safety of blood glucose control in hospitalized patients with type 2 diabetes mellitus (T2DM) receiving continuous subcutaneous insulin infusion (CSII) treatment in the Department of Endocrinology. The main question it aims to answer is: Is the prediction model superior to or (at least) non-inferior to clinicians' experience? Eligible patients who receive CSII treatment are randomly allocated into the prediction model group and the empirical group. Patients will: 1. Receive CSII treatment as standard of care during hospitalization for 1-2 weeks, where the daily insulin dose regimen is determined by a prediction model or a clinician's experience. 2. Use continuous glucose monitoring (CGM) for glucose tracking. 3. Receive diabetes self-management education covering nutrition and physical activity.

Eligibility

Min Age: 18 YearsMax Age: 75 Years

Plain Language Summary

Simplified for easier understanding

This study is testing whether an artificial intelligence algorithm can accurately predict the correct insulin doses for people with type 2 diabetes who are using an insulin pump during a hospital stay. **You may be eligible if...** - You have type 2 diabetes - You are currently hospitalized and using an insulin pump (called CSII) to control your blood sugar - Your insulin pump treatment during this hospital stay will last at least 6 days but no more than 30 days **You may NOT be eligible if...** - You have a type of diabetes other than type 2 - You are 75 or older and not a good candidate for intensive insulin therapy - You are managing your blood sugar with oral medications or insulin injections (not a pump) during hospitalization - You have severe liver or kidney problems, or are in the acute phase of a cardiovascular event - You are pregnant Talk to your doctor to see if this trial is right for you.

This summary was AI-generated to explain the trial in plain language. It is not medical advice. Always discuss eligibility with your doctor before enrolling in a clinical trial.

Interested in this trial?

Get notified about updates and connect with the research team.

Interventions

DRUGCSII in the prediction model group

1. Everyday insulin dosage decided by AI prediction model. 2. CSII treatment continues for 1 to 2 weeks based on whehter or not the patient is newly diagnosed or with different disease duration.

DRUGCSII in the empirical group

1. Everyday insulin dosage decided by clinicans' experience. 2. CSII treatment continues for 1 to 2 weeks based on whether or not the patient is newly diagnosed or with different disease duration.

Locations(1)

Department of Endocrinology and Diabetes Center, The First Affiliated Hospital of Sun Yat-sen University

Guangzhou, Guangdong, China

View Full Details on ClinicalTrials.gov

For the most up-to-date information, visit the official listing.

Visit

NCT07066891

Related Trials

Prevalence of Diabetes-related Distress Among Patients Living With Type 2 Diabetes in a University Hospital Center and Identification of Its Associated Factors.

NCT073924371 location

Early Tracking of Childhood Health Determinants (ETCHED) Study

NCT034818291 location

LINK-IT: Leveraging vIdeos and commuNity Health worKers to Improve Diabetes OuTcomes

NCT063197161 location

Improving Insulin Sensitivity in Patients With Type 2 Diabetes Via Repeated Cold-induced Shivering Thermogenesis

NCT075739171 location

Continuous Glucose Monitoring (CGM) in an Underserved Population

NCT071355311 location