Integration of a Trained Language Model to Improve Glycemic Control Through Increased Physical Activity: a Fully Digital My Heart Counts Smartphone App Randomized Trial

Not Applicable

Not yet recruiting

• Conditions: Type2diabetes
• Interventions: Behavioral: Validation of language model prompts in increasing short-term physical activity; Behavioral: Assessment of long-term changes to physical activity and glycemic control

• Registration Number: NCT06596330
• Lead Sponsor: Stanford University

Brief Summary

Type 2 diabetes (T2D) is one of the most common and fastest growing diseases, affecting 1 in 8 adults (nearly 800 million) worldwide by 2045. Sedentary behavior and increased adiposity are major risk factors for T2D. Cardiovascular disease is the leading cause of death in those with T2D, while diabetic microvascular disease, causing kidney disease, neuropathy, and retinopathy, contributes to T2D morbidity.

Physical activity is one of the most potent therapies in preventing/treating T2D and its complications. Mean daily steps is a proxy for physical activity, with even modest improvements in step count (i.e., +500 steps) associated with decreased T2D and mortality. However, adherence to regular physical activity remains low in T2D patients, with short-term decreases in daily step count associated with impaired glycemic control and T2D recurrence.

The investigators have developed an artificial intelligence (AI) language model (similar to ChatGPT), which can automatically generate coaching prompts to encourage physical activity by incorporating an individual's stage of change. The investigators will extend our research using the My Heart Counts (MHC) smartphone app to 1) validate the efficacy of the AI-generated prompts in patients with T2D and 2) perform a longer-term randomized crossover trial using the language model as a social accountability chatbot - encouraging participants to maintain their physical activity changes over months. The investigators hypothesize that my AI-assisted coaching prompts will significantly increase 1) mean daily step count by 500 steps in 1,000 adults recruited nationwide over a 7-day period, and 2) improve HbA1c and weight via long-term behavior change over a 24-week intervention period.

Detailed Description

Not available

Study Timeline

• Status Verified: 2024-08
• Study First Submitted: 2024-08-26
• Study First Submitted QC: 2024-09-12
• Last Update Submitted: 2024-09-12
• Study First Posted: 2024-09-19
• Last Update Posted: 2024-09-19
• Study Start: 2025-07
• Primary Completion: 2029-07
• Study Completion: 2029-07

Recruitment & Eligibility

• Status: NOT_YET_RECRUITING
• Sex: All
• Target Recruitment: 1000

Inclusion Criteria

• Individuals aged ≥18 years old, with a clinical diagnosis of T2D, able to read and understand English, and who are physically able to walk, will be included in our study

Exclusion Criteria

• Criteria that fall outside of the inclusion criteria.

Study & Design

• Study Type: INTERVENTIONAL
• Study Design: CROSSOVER

Arm && Interventions

Group	Intervention	Description
LLM-generated coaching prompt	Validation of language model prompts in increasing short-term physical activity	-
LLM-generated coaching prompt	Assessment of long-term changes to physical activity and glycemic control	-
10,000 Step Reminder	Validation of language model prompts in increasing short-term physical activity	-
10,000 Step Reminder	Assessment of long-term changes to physical activity and glycemic control	-

Primary Outcome Measures

Name	Time	Method
Mean daily steps	7 days and 24 weeks	Mean daily steps over the course of an intervention week (aim 1) and 24 week period (aim 2).

Secondary Outcome Measures

Name	Time	Method
Change in weight	24 Weeks	Change in weight over the long term intervention (Aim 2)
Change in HbA1c	24 Weeks	Change in HbA1c over the long term intervention (Aim 2)
Weekly Active Minutes	7 days and 24 Weeks	Total weekly active minutes over the course of an intervention week (aim 1) and 24 week period (aim 2).