GODART Pilot and Feasibility

Purpose

The purpose of this study is to pilot and assess the feasibility of implementing an artificial intelligence-assisted individualized lifestyle modification intervention for glycemic control in rural populations, which can be delivered even with regular landline phone service. This study will provide us with the knowledge to plan a well-powered optimization trial in the future to develop an optimal (low-cost) intervention package that can be delivered in a sustainable manner to the rural portions of America.

Condition

  • Diabetes Mellitus, Type 2

Eligibility

Eligible Ages
Over 18 Years
Eligible Genders
All
Accepts Healthy Volunteers
No

Inclusion Criteria

  1. a diagnosis of T2DM 2. HbA1C ≥7% to ≤ 10.5% for phase 1- 14 days and phase 2 of the study- 6 months. 3. ≥18 years of age 4. the ability to converse in and read English.

Exclusion Criteria

  1. Present or soon-planned pregnancy 2. Current enrollment in any structured lifestyle intervention study for diabetes or weight management. 3. Patients currently on insulin treatment 4. Major cardiac event in the past 6 months 5. Renal failure in the past 6 months 6. Listening and Speaking Impairment

Study Design

Phase
N/A
Study Type
Interventional
Allocation
Randomized
Intervention Model
Factorial Assignment
Intervention Model Description
We propose to use the multiphase optimization strategy (MOST) design, as an ideal approach for the study, that is based on the principle of resource management and continuous improvement. Our study aim aligns with the preparatory and optimization phases of MOST, and is structured to serve as the preparatory phase for a future large-scale MOST optimization phase.
Primary Purpose
Health Services Research
Masking
Double (Investigator, Outcomes Assessor)
Masking Description
Statistician and the assessor will be blinded/masked to participant assignment. The health coach will not be blinded. It will not be possible to blind the participants.

Arm Groups

ArmDescriptionAssigned Intervention
Experimental
Arm 1 		Adaptive Rewards + Weekly automated coaching
  • Behavioral: Weekly Automated Health Coaching
    This intervention will involve health coaching delivered by Artificial intelligence (AI). The automated health coaching mechanism will be coupled with AI-based responses, and recent advancements have made the voices generated through the AI, almost human-like voices. Every week participants enrolled in automated health coaching intervention will receive a health coaching and goal-setting call that will help guide the participants in managing their Type 2 Diabetes Mellitus. This technology-driven study group will inform us whether trained human coaches are required or if the automated technologies are sufficient to create clinically meaningful HbA1c improvements.
  • Behavioral: Adapted Reward Level
    In the adapted reward (gamified) variation, participants will receive 25 cents per day for the first week of daily-monitoring calls, 50 cents per day in the second week, 75 cents per day in the third week, and a dollar per day from the fourth week until the end of the study (Aim 2). In the adaptive variation, missing one day of monitoring (in the past seven days), drops the reward value by one level (example: 75 cents becomes 50 cents), two days of missed calls drop the reward level by two levels, and similarly for three days. In the adaptive variation, participants have to continue to daily monitor their behavior to again build up their reward levels.
Experimental
Arm 2 		Adaptive Rewards + Weekly human coaching
  • Behavioral: Weekly Human Health Coaching
    Every week participants enrolled in human health coaching intervention will receive a health coaching call and goal-setting call from their respective health coaches to guide them in managing their Type 2 Diabetes Mellitus.
  • Behavioral: Adapted Reward Level
    In the adapted reward (gamified) variation, participants will receive 25 cents per day for the first week of daily-monitoring calls, 50 cents per day in the second week, 75 cents per day in the third week, and a dollar per day from the fourth week until the end of the study (Aim 2). In the adaptive variation, missing one day of monitoring (in the past seven days), drops the reward value by one level (example: 75 cents becomes 50 cents), two days of missed calls drop the reward level by two levels, and similarly for three days. In the adaptive variation, participants have to continue to daily monitor their behavior to again build up their reward levels.
Experimental
Arm 3 		Fixed Reward + Weekly automated coaching
  • Behavioral: Weekly Automated Health Coaching
    This intervention will involve health coaching delivered by Artificial intelligence (AI). The automated health coaching mechanism will be coupled with AI-based responses, and recent advancements have made the voices generated through the AI, almost human-like voices. Every week participants enrolled in automated health coaching intervention will receive a health coaching and goal-setting call that will help guide the participants in managing their Type 2 Diabetes Mellitus. This technology-driven study group will inform us whether trained human coaches are required or if the automated technologies are sufficient to create clinically meaningful HbA1c improvements.
  • Behavioral: Fixed Gamified Reward Level
    In our fixed-reward arm, participants will be awarded 25 cents per day for answering the daily monitoring call - this serves simply as a reward for answering the daily calls. It is important that the rewards are for answering the calls and not for the actual values of the responses provided.
Experimental
Arm 4 		Fixed Reward + Weekly human coaching
  • Behavioral: Weekly Human Health Coaching
    Every week participants enrolled in human health coaching intervention will receive a health coaching call and goal-setting call from their respective health coaches to guide them in managing their Type 2 Diabetes Mellitus.
  • Behavioral: Fixed Gamified Reward Level
    In our fixed-reward arm, participants will be awarded 25 cents per day for answering the daily monitoring call - this serves simply as a reward for answering the daily calls. It is important that the rewards are for answering the calls and not for the actual values of the responses provided.

Recruiting Locations

Department of Family and Community Medicine, University of Alabama at Birmingham
Birmingham, Alabama 35205
Contact:
Tejossy John, MPH
205-659-8470
tjohn@uabmc.edu

More Details

Status
Recruiting
Sponsor
University of Alabama at Birmingham

Study Contact

Tapan Mehta, PhD
205-975-9171
tapan@uab.edu

Detailed Description

Evidence-based guidelines for type 2 diabetes mellitus (T2DM) management aimed at glycemic control (reduced hemoglobin A1c) include a combination of diet, physical activity (PA), glucose monitoring, and medication adherences. However, the majority of individuals with T2DM are unable to follow these guidelines due to a lack of consistent health behavior counseling offered in the primary care setting. This problem is amplified in remote rural communities within the U.S. In response, this project aims to create an optimized telehealth-based intervention - Gamified Optimized Diabetes management with Artificial Intelligence-powered Rural Telehealth (GODART). GODART is grounded in the social cognitive theory and will serve as an automated behavior-monitoring and telecoaching platform. At the core, GODART is an automated conversational-style behavior-monitoring system using natural language-understanding technologies. In this project, we propose to pilot and feasibility test the various components of GODART by leveraging a multiphase optimization strategy (MOST). MOST is an efficient and rigorous resource-management and continuous- improvement framework for developing optimized interventions. Our proposal focuses on the MOST preparatory phase and will use full factorial experimentation. We will pilot and assess the feasibility of and evaluate two different intervention components, with two levels in each of the groups, yielding four experimental conditions. These groups will test the effect of (i) a fixed vs. adaptive (gamified) rewards program and (ii) automated vs. human-delivered weekly health coaching. We will end the project with exit interviews conducted with a subset of participants. Study findings will help us learn the feasibility of delivering such an intervention and its preliminary effectiveness in reducing HbA1c, leading to adequately powered confirmatory effectiveness studies. Participants will be enrolled in the study in 2 phases: Phase 1-The Feasibility Phase: Up to 16 participants will be enrolled in this phase of the study. Participants will be in the study for a duration of 14 days. This phase of the study is conducted to access the feasibility, usability, and accessibility of the GODART platform, before the actual intervention phase. Phase 2- Intervention Phase: 88 participants will be enrolled in this phase of the study for a duration of 6 months.