Artificial Intelligence-based Methods to Predict Disease Progression in Youth With Type 2 Diabetes

Summary

Currently, clinicians are unable to predict a patient's risk of long-term disease progression and development of a long-term complication based on the data that is available to them. The first aim of this is to develop and validate an Artificial Intelligence (AI) powered prediction model for Type 2 Diabetes (T2D) disease progression using existing data from previously collected studies and real-world electronic health medical data. Investigators will use clinical, pharmacologic, and genomic factors to develop the prediction model based on the most relevant clinical outcomes of change in Hemoglobin A1c (HbA1c) and the development of a microvascular complication.

Despite the availability of newer medication options, lifestyle intervention is not effective in most youth and current therapeutic options are ineffective at producing sustained glycemic control. Newer and innovative methods are needed to identify the youth at highest risk of progression in terms of increase in HbA1c and development of long-term complications and to motivate behavioral change in youth. The goal of this aim is to create an AI-powered digital twin model for 50 youth with T2D using their baseline clinical, genetic, pharmacologic and lifestyle data and utilize AI algorithms developed in Aim 1 to simulate disease progression and treatment response. Investigators will then evaluate the digital twin model in an randomized controlled trail and prospectively compare the generated digital twin data to observed values over one year. Investigators will also measure whether knowledge of the digital twin prediction with targeted healthcare recommendations influence medication and lifestyle change adherence in the digital twin arm (n= 25) compared to the control arm (n= 25).

Conditions

• Type 2 Diabetes

Interventions

DEVICE

phone application

Participants in the digital twin arm will receive information on their disease progression which will be based on projected change in HbA1C in alternative realities and specific recommendations on medication dosing and lifestyle changes based on this data. The digital twin information will be presented on an iPad in a game- like manner. The alternate realities will include scenarios of change in medication adherence, physical activity metrics, dietary changes etc.

OTHER

Standard of Care (SOC)

Participants in the control arm will receive standard of care which is medication change recommendations based on HbA1C and blood glucose values every 3 months and standard lifestyle education.

Sponsors & Collaborators

• Stanford University

  collaborator OTHER

• American Diabetes Association

  collaborator OTHER

• University of California, San Francisco

  lead OTHER

Principal Investigators

• Shylaja A Srinivasan, MD · University of California, San Francisco

Study Design

Allocation

RANDOMIZED

Purpose

DIAGNOSTIC

Masking

NONE

Model

PARALLEL

Eligibility

Min Age

10 Years

Max Age

21 Years

Sex

ALL

Healthy Volunteers

No

Timeline & Regulatory

Start

2026-04-30

Primary Completion

2026-09-30

Completion

2026-09-30

FDA Device

Yes

Countries

• United States

Study Locations