AI-Assisted Mealtime Insulin Dosing in an Automated Insulin Delivery System for Type 1 Diabetes
Tests AI-learned meal patterns added to automated insulin delivery in adults with type 1 diabetes.
Key facts
- Who runs it
- Sue Brown
- Where
- Charlottesville, United StatesSee the site
- Trial code
- Registry title
- Effectiveness of Artificial-Intelligence (AI) Bolus Priming Added to an Existing Fully Automated Control Algorithm (AIDANET)
- Status
- Not yet recruiting
- People taking part
- 50 people, planned
- Started
- 1 May 2026
- Expected to end
- 30 Apr 2027
- Type of study
- Interventional, 2 groups
- Treatments tested
- Hybrid Closed Loop (HCL) x 2 weeks
- AIDANET x 2 weeks
- AIDANET AI x 4 weeks
- Record updated
- 8 April 2026
Who can take part
AI summary
From the trial's eligibility criteria. Machine-read from the registry text on this page, so it can be wrong. The registry text below and the trial team decide who can take part.
The trial is looking for adults with type 1 diabetes who already use an automated insulin delivery system. It tests an AI-based mealtime insulin addition to the study algorithm.
- Age
- 18 years or older
- Sex
- All sexes can join.
- Disease stage
- Type 1 diabetes for at least one year, currently using an automated insulin delivery (AID) system.
- Earlier treatment
- Must currently use an automated insulin delivery system. Must not plan to start a new non-insulin glucose-lowering medicine during the trial. Must not use oral or injectable steroids now or in the last 2 weeks.
Main reasons for not taking part
- Pregnant or breastfeeding, or planning to become pregnant during the study
- Taking an SGLT-2 or SGLT-1/2 inhibitor
- Severe low blood sugar with seizure or loss of consciousness, or a DKA event, in the last 12 months
- Unstable stage 4 chronic kidney disease, or on peritoneal dialysis or haemodialysis
- Hemophilia or another bleeding disorder
The registry criteria, word for word
Show all 28 criteriaShow less
Who can take part
- Age ≥18.0 years old at time of consent
- Clinical diagnosis, based on investigator assessment, of Type 1 Diabetes (T1D) for at least one year
- Currently using an automated insulin delivery (AID) system
- Willingness to switch to use a commercially approved personal insulin (e.g., lispro or aspart, or biosimilar approved products) within the study pump as directed by the study team
- Has one or more supportive companions knowledgeable about emergency procedures for severe hypoglycemia and able to contact emergency services and study staff that either live with participant or located within approximately 30 minutes of participant and able to locate participant in the event of an emergency
- Participant not currently known to be pregnant or breastfeeding
- If participant can become pregnant, they must agree to use a form of contraception to prevent pregnancy while a participant in the study. A negative serum or urine pregnancy test will be required for all females of childbearing potential. Participants who become pregnant will be discontinued from the study. Also, participants who during the study develop and express the intention to become pregnant within the timespan of the study will be discontinued
- Willingness to use the study AIDANET system (CGM, insulin pump, and phone) during the study period
- Willingness not to start any new non-insulin glucose-lowering agent during the course of the trial
- Willingness to participate in all study procedures
- Access to internet at home and willingness to upload data during the study as needed
- Investigator has confidence that the participant can successfully operate all study devices and is capable of adhering to the protocol
- Participant is proficient in reading and writing English
Who cannot take part
- Unstable Stage 4 chronic renal disease or currently on peritoneal or hemodialysis
- Use of oral or injectable steroids at the time of enrollment or within the last 2 weeks
- Planned surgery during the study period that results in prolonged disconnection from study devices
- Hemophilia or any other bleeding disorder
- History of severe hypoglycemic events with seizure or loss of consciousness in the last 12 months
- History of DKA event in the last 12 months
- Currently being treated for adrenal insufficiency
- Currently being treated for a seizure disorder
- A condition, which in the opinion of the investigator or designee, would put the participant or study at risk
- Plans to start a new non-insulin glucose-lowering agent (e.g., Glucagon-like peptide-1 (GLP-1) receptor agonists, Symlin, DPP-4 inhibitors, sulfonylureas). Participants may be on a stable dose of such an agent for at least the past month
- Current use of an sodium-glucose transport protein 2 (SGLT-2) or SGLT-1/2 inhibitor due to risk of euglycemic diabetic ketoacidosis (DKA)
- Hypothyroidism or hyperthyroidism that is not adequately treated
- Known ongoing adhesive intolerance that is not well managed
- Participation in another interventional trial at the time of enrollment
- Participant with a direct supervisor involved in the conduct of the trial
Where in United States
- University of Virginia Center for Diabetes TechnologyCharlottesville, United StatesContact: Sue Brown, MDNot yet recruiting
About the trial
What the trial wants to find out
Bolus Priming (BP) based on Artificial Intelligence (AI) learning of meal patterns, added to our established Automated insulin delivery as Adaptive Network (AIDANET) algorithm and running on iPhone Diabetes Assistant (iDiAs) phone wirelessly connected to Tandem Mobi insulin pump and Dexcom Continuous Glucose Monitor (CGM).
The 2 groups in the trial
- GROUP A: 2 weeks HCL, 2 weeks AIDANET, and 4 weeks AIDANET AITreatment being tested
Group A participants will continue to use their home HCL system for 2 weeks, then switch to AIDANET for two weeks, and the switch to AIDANET AI for another 4 weeks.
Treatment: Hybrid Closed Loop (HCL) x 2 weeks, AIDANET x 2 weeks, and AIDANET AI x 4 weeks
- GROUP B: 4 weeks AIDANET AI, 2 weeks AIDANET, and 2 weeks HCLTreatment being tested
Group B participants will begin with 4 weeks of AIDANET AI, then switch to AIDANET for 2 weeks and then revert to their home HCL systems for the last 2 weeks of the study
Treatment: Hybrid Closed Loop (HCL) x 2 weeks, AIDANET x 2 weeks, and AIDANET AI x 4 weeks
Questions to ask the study team
- How often do I need to come in, and for how long each time?
- Are travel costs paid?
- Can I keep my own doctor?
- What happens if I want to stop?
Contact the study team: see the registry record → Contacts and Locations
Print a page for my doctorSaves a reminder to your own calendar to look at this page again. Frontlight sends no messages and does not know you set it.
Data and sources
- Registry record
- Listed on ClinicalTrials.gov.How to verify a trial in the registry
- Official title
- Effectiveness of Artificial-Intelligence (AI) Bolus Priming Added to an Existing Fully Automated Control Algorithm (AIDANET)
- Plain-language title
- AI-Assisted Mealtime Insulin Dosing in an Automated Insulin Delivery System for Type 1 DiabetesGenerated from the registry record. The registry title is the official one.
- AI summary
- From the trial's eligibility criteria. Read by machine on 12 November 2026.
- Record updated
- 8 April 2026