Neural-net Artificial Pancreas (NAP)

Overview

This study is intended to assess a Neural-net Artificial Pancreas (NAP) implementation of an established AP controller – the University of Virginia Model Predictive Control Algorithm (UMPC). The health outcomes achieved on NAP will be compared to the health outcomes achieved on UMPC in a randomized crossover design. The investigators will consent up to 20 participants, ages ≥18.0, with a goal of completing 15 participants.

Full Title of Study: “Adaptive Motif-Based Control (AMBC): Pilot 1 – Neural Net Implementation of Automated Insulin Delivery”

Study Type

• Study Type: Interventional
• Study Design
  • Allocation: Randomized
  • Intervention Model: Crossover Assignment
  • Primary Purpose: Treatment
  • Masking: None (Open Label)
• Study Primary Completion Date: September 2023

Detailed Description

The study will follow a randomized cross-over design assessing glycemic control on a Neural-net Artificial Pancreas (NAP), compared to the previously tested University of Virginia Model Predictive Control (UMPC) algorithm, in a supervised hotel setting: The study will involve Tandem t:slim X2 Control-IQ (CIQ) users who will continue to use their CIQ systems, except during the hotel sessions, which will use the DiAs prototyping platform, connected to a Tandem t:AP research pump and a Dexcom G6 sensor, and implementing NAP or UMPC. The study sensor will be the same sensor used by CIQ – it will be disconnected from CIQ and connected to DiAs. Following enrollment, one week of automated insulin delivery (AID) data will be downloaded from the participants' pumps or t:connect accounts and will be used to establish a baseline and initialize the control algorithms. Participants will be then studied at a local hotel for 20 hours, including an 18-hour experiment, randomly receiving either NAP or UMPC. Participants will then receive the opposite intervention either sequentially during the same hotel stay, or in a second hotel stay up to 28 days following the first hotel stay. During these 18-hour hotel sessions participants will be followed to compare blood glucose control on NAP vs. UMPC. The study meals and activities will be kept the same between study sessions. The investigators will analyze non-inferiority of NAP compared to UMPC, but this pilot feasibility study is not powered to formally test noninferiority. The primary outcome is percent time in range (TIR) (70 to 180 mg/dL) on NAP vs UMPC. Secondary outcomes include frequency of hypoglycemia (time below range = TBR) and hyperglycemia (time above range = TAR), as well as other safety and control metrics.

Interventions

• Device: Neural-net Artificial Pancreas
  • NAP is a neural-net implementation of the previously tested UMPC algorithm (below).
• Device: University of Virginia Model Predictive Control
  • A previously tested artificial pancreas control algorithm, based on a differential-equation model of the human metabolic system in diabetes.

Arms, Groups and Cohorts

• Experimental: NAP first, then UMPC
  • Participants will use the Neural Net Artificial Pancreas (NAP) algorithm for 18 hours. Then switch to the University of Virginia Model-Predictive Control (UMPC) for 18 hours.
• Experimental: UMPC first, then NAP
  • Participants will use the UMPC for 18 hours, then switch to NAP for 18 hours.

Clinical Trial Outcome Measures

Primary Measures

• Percent of Time-in-Range (TIR) on NAP versus UMPC.
  • Time Frame: 36 hours (two 18-hour experiments)
  • The primary outcome is percent of time in 70 to 180 mg/dL range on NAP vs UMPC.

Secondary Measures

• Percent of Time in Hyperglycemia.
  • Time Frame: 36 hours (two 18-hour experiments)
  • Percent CGM readings above 180 mg/dL.
• Percent of Time in Hypoglycemia.
  • Time Frame: 36 hours (two 18-hour experiments)
  • Percent CGM readings below 70 mg/dL.
• System Functionality
  • Time Frame: 36 hours (two 18-hour experiments)
  • The investigator will observe, record, and tabulate any system malfunctions requiring study team intervention.
• Participant Feedback
  • Time Frame: 36 hours (two 18-hour experiments)
  • The investigator will obtain qualitative feedback form the participants regarding system functionality.

Participating in This Clinical Trial

Inclusion Criteria

1. Age ≥18.0 at time of consent. 2. Clinical diagnosis, based on investigator assessment, of type 1 diabetes for at least one year. 3. Currently using insulin for at least six months. 4. Currently using the Control-IQ automated insulin delivery system for at least one mont. 5. Hemoglobin A1c of ≤9%. 6. Using insulin parameters such as insulin to carb ratio and correction factor consistently in order to dose insulin for meals or corrections. 7. Access to internet and willingness to upload data during the study as needed. 8. If female of childbearing potential and sexually active, 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 within 24 hours prior to initiating the experimental algorithms. 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. 9. Willingness to use the University of Virginia Diabetes Assistant system throughout study session. 10. Willingness to use personal Lispro (Humalog) or aspart (Novolog) during the study session. 11. Willingness not to start any new non-insulin glucose-lowering agent during the course of the trial (including Sodium-glucose cotransporter-2 inhibitors, metformin/biguanides, glucagon-like peptide-1 receptor agonists, Pramlintide, Dipeptidyl peptidase-4 inhibitors, Sulfonylureas and nutraceuticals). 12. Willingness to reschedule the hotel portion of the study if placed on systemic steroids (e.g. intravenous injection, intramuscular injection, intra-articular or oral routes). 13. An understanding and willingness to follow the protocol and signed informed consent. Exclusion Criteria:

1. History of Diabetic Ketoacidosis (DKA) in the 12 months prior to enrollment. 2. Severe hypoglycemia resulting in seizure or loss of consciousness in the 12 months prior to enrollment. 3. Currently pregnant or intent to become pregnant during the trial. 4. Currently breastfeeding. 5. Currently being treated for a seizure disorder. 6. Treatment with Meglitinides/Sulfonylureas at the time of hotel study. 7. Use of metformin/biguanides, glucagon-like peptide-1 agonists, Pramlintide, Dipeptidyl peptidase-4 inhibitors, Sodium-glucose cotransporter-2 inhibitors, or nutraceuticals intended for glycemic control with a change in dose in the past month. 8. History of significant cardiac arrhythmia (except for benign premature atrial contractions and benign premature ventricular contractions which are permitted or previous ablation of arrhythmia without recurrence which may be permitted) or active cardiovascular disease. 9. A known medical condition that in the judgment of the investigator might interfere with the completion of the protocol such as the following examples: 1. Inpatient psychiatric treatment in the past 6 months. 2. Presence of a known adrenal disorder. 3. Uncontrolled thyroid disease. 10. A known medical condition that in the judgment of the investigator might interfere with the completion of the protocol.

Gender Eligibility: All

Minimum Age: 18 Years

Maximum Age: N/A

Are Healthy Volunteers Accepted: No

Investigator Details

• Lead Sponsor
  • University of Virginia
• Collaborator
  • National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK)
• Provider of Information About this Clinical Study
  • Principal Investigator: Boris Kovatchev, PhD, Principal Investigator – University of Virginia
• Overall Official(s)
  • Boris P Kovatchev, PhD, Study Director, University of Virginia Center for Diabetes Technology
  • Sue A Brown, MD, Principal Investigator, University of Virginia Center for Diabetes Technology
• Overall Contact(s)
  • Morgan R Fuller, 434-242-9379, mf2nu@uvahealth.org