AIDANET Algorithm for Type 1 Diabetes

Overseen By Lianna Smith

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Sue Brown

Must be taking: Insulin

Must not be taking: Sulfonylureas, SGLT-2 inhibitors

Disqualifiers: Bleeding disorders, Severe hypoglycemia, DKA, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

40 Participants Needed

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial tests a new insulin delivery system called AIDANET, designed to help people with Type 1 Diabetes manage their blood sugar levels more effectively. Participants will try different versions of the system, including fully and partially automated modes, to determine which works best. The study involves using devices such as a continuous glucose monitor and an insulin pump. It suits individuals who have had Type 1 Diabetes for at least a year, use insulin, and have recent experience with an automated insulin delivery system. As an unphased trial, it offers a unique opportunity to explore innovative technology in diabetes management.

Do I have to stop taking my current medications for the trial?

The trial requires that you do not start any new non-insulin glucose-lowering medications during the study. If you are currently using sulfonylurea medications, SGLT-2 inhibitors, or steroids, you will need to stop these before participating. Other medications may be continued if they have been stable for at least a month.

What prior data suggests that the AIDANET algorithm is safe for managing Type 1 Diabetes?

Research has shown that the AIDANET system has been tested in several studies to assess its safety and effectiveness for people with Type 1 Diabetes. One study found no serious unexpected problems with the AIDANET system. It safely managed blood sugar levels with its smart insulin delivery features, meaning most participants did not experience harmful side effects, indicating the system is well-tolerated.

The system uses an AI-driven closed-loop method, automatically adjusting insulin (the hormone that controls blood sugar) based on real-time glucose data. This helps maintain blood sugar levels within a safe range and reduces the time they are outside these target levels.

Overall, these early findings suggest the AIDANET system is safe, with no major safety concerns reported in the studies. This provides a strong basis for considering its use in managing Type 1 Diabetes. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about AIDANET for Type 1 Diabetes because it represents a new way to manage blood sugar levels using advanced algorithms. Unlike traditional insulin therapy, which requires manual adjustments, AIDANET offers an automated approach that adapts in real-time to a patient’s needs. This could mean more precise control of blood sugar levels and fewer episodes of high or low blood sugar. Additionally, the flexibility of combinations in the treatment arms, such as AIDANET-FCL and AIDANET-HCL, allows for personalized management, which is a significant step forward from the one-size-fits-all nature of many current treatments.

What evidence suggests that the AIDANET algorithm is effective for glycemic control in Type 1 Diabetes?

Research has shown that the AIDANET system can help people with Type 1 Diabetes manage their blood sugar levels safely. A small initial study found that AIDANET provided safe control of blood sugar levels. In this trial, participants in Group A will first use the AID system, followed by different versions of AIDANET, while those in Group B will start with AIDANET-FCL and progress through other versions. The system uses artificial intelligence to automatically adjust insulin delivery, potentially making diabetes management easier. By automatically adjusting insulin, AIDANET aims to keep blood sugar levels stable without constant manual changes. Early results suggest it could be a helpful tool for improving life with diabetes. ^{5 6 7 8 9}

Who Is on the Research Team?

Sue Brown, MD

Principal Investigator

University of Virginia Center for Diabetes Technology

Are You a Good Fit for This Trial?

Adults over 18 with Type 1 Diabetes, proficient in English, who've used an FDA approved Automated Insulin Delivery system recently. They must be willing to use the AIDANET system and a Dexcom CGM during the study, have internet access at home, not be pregnant or breastfeeding, agree to use contraception if necessary, and have support for emergency hypoglycemia situations.

Inclusion Criteria

Willingness to use the study AIDANET system during relevant study periods

Participating in all study procedures including in-person training

Having access to internet at home and willingness to upload data as needed

Exclusion Criteria

I have a history of hemophilia or another bleeding disorder.

I have had severe low blood sugar with seizure or fainting in the past year.

I am currently undergoing dialysis.

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Usual Care AID System

Participants use a usual care Automated Insulin Delivery system

4 weeks

AIDANET-FCL or AIDANET-HCL

Participants use the AIDANET system in either Fully Closed Loop or Hybrid Closed Loop mode

4 weeks

AIDANET-HCL or AIDANET-FCL

Participants switch to the other mode of AIDANET system not used in the previous phase

4 weeks

AIDANET-FCL-HCL Mix

Participants use the AIDANET system with the ability to switch between Fully Closed Loop and Hybrid Closed Loop modes as preferred

4 weeks

Follow-up

Participants are monitored for safety and effectiveness after treatment

4 weeks

What Are the Treatments Tested in This Trial?

Interventions

• AIDANET

Trial Overview The trial is testing the AIDANET algorithm's effectiveness in managing blood sugar levels when used in three different modes: Fully Closed Loop (FCL), Hybrid Closed Loop (HCL), and a mixed mode of FCL-HCL. Participants will also spend time using their usual care AID systems without AIDANET.

How Is the Trial Designed?

Group I: Group B Experimental Treatment 4 Interventions

Group B: AIDANET-FCL first followed by AIDANET-HCL, AIDANET- FCL-HCL mix and AID

Group II: Group A Experimental Treatment 4 Interventions

Group A: AID first followed by AIDANET-FCL, AIDANET-HCL and then AIDANET-FCL-HCL mix

Who Is Running the Clinical Trial?

Sue Brown

Lead Sponsor

Trials

3

Recruited

100+

Tandem Diabetes Care, Inc.

Industry Sponsor

Trials

43

Recruited

5,800+

DexCom, Inc.

Industry Sponsor

Trials

151

Recruited

35,700+

Kevin Sayer

DexCom, Inc.

Chief Executive Officer since 2015

Bachelor’s and Master’s degrees in Accounting and Information Systems from Brigham Young University

Dr. Shelly Lane

DexCom, Inc.

Chief Medical Officer since 2023

MD from University of California, San Diego

National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK)

Collaborator

Trials

2,513

Recruited

4,366,000+

Citations

1. clinicaltrials.gov clinicaltrials.gov/study/NCT07039617

Study Details | NCT07039617 | AIDANET At Home Study A randomized cross-over trial assessing glycemic control on Automated insulin delivery as Adaptive Network (AIDANET) algorithm when used in three modes: ...

2. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC12479459/

A Pilot Study Featuring Flexible Meal Announcement Options This pilot-feasibility study demonstrates that the AIDANET system provides safe glycemic control. The small sample size (n = 6) limits overall ...

3. withpower.com withpower.com/trial/phase-diabetes-mellitus-type-1-7-2025-8757d

AIDANET Algorithm for Type 1 Diabetes This N/A medical study run by Sue Brown is evaluating whether AIDANET will have tolerable side effects & efficacy for patients with Type 1 Diabetes.

4. datascience.virginia.edu datascience.virginia.edu/news/new-uva-clinical-trial-explores-ai-powered-insulin-delivery-better-diabetes-care

New UVA Clinical Trial Explores AI-Powered Insulin Delivery ... A new clinical trial at UVA is aiming to simplify diabetes management by testing an innovative AI-powered device designed to improve automated insulin delivery.

5. uvahealth.com uvahealth.com/clinical-trials/trial/302656

Clinical Trials | Fully Closed Loop Study for Adults ages 18 ... The purpose of this study is to find out if a system called AIDANET (Automated Insulin Delivery Adaptive NETwork) is safe and can help control blood sugar ...

6. diabetesjournals.org diabetesjournals.org/diabetes/article/74/Supplement_1/962-P/159109/962-P-Evaluating-Type-1-Diabetes-T1D-Care-across

962-P: Evaluating Type 1 Diabetes (T1D) Care across All ... The AIDANET system uses an adaptive algorithm that removes the need for meal announcement. This may help address age-specific obstacles in T1D.

7. clinicaltrials.gov clinicaltrials.gov/ct2/show/NCT06728059

Safety and Feasibility of a Machine-Learning Bolus Priming ... This is a research study about the UVA Automated Insulin Delivery System known as Adaptive NETwork (AIDANET). This system consists of a Reinforcement Learning ...

8. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC12183835/

Effectiveness and safety of AI-driven closed-loop systems ... AI-based closed-loop systems can analyze glucose data in real-time and automatically adjust insulin delivery, resulting in reduced time outside target glucose ...

9. journals.sagepub.com journals.sagepub.com/doi/10.1177/19322968251364283

A Pilot Study Featuring Flexible Meal Announcement Options There were no serious adverse events during the study. The hybrid bolusing options provided safe glycemic control, with carbohydrate counting ...