LLM-Generated Coaching Prompts

NCT06880315 | Not Yet Recruiting

• 1 other identifier: 79946
• Study Type: interventional
• Target: 50
• Locations: 0 countries
• Sites: N/A

Brief Summary

This pilot study aims to evaluate whether personalized coaching prompts generated by a large language model (LLM) can effectively increase physical activity levels among participants. The study will involve 50 participants who will receive daily text messages, either personalized by the LLM or generic, over a 14-day period. Participants will share their HealthKit data for analysis. The findings will inform the development of future versions of the My Heart Counts application, enhancing user engagement and health outcomes.

Conditions

Exercise

Outcome Measures

Primary Outcomes (1)

• Physical Activity Levels

  14 days from enrollment

Study Arms (2)

Personalized LLM-Generated Coaching Prompts

EXPERIMENTAL

Behavioral: Pre-Generated Personalized LLM Coaching Impact

Generic Activity Prompts

ACTIVE COMPARATOR

Behavioral: Pre-Generated Personalized LLM Coaching Impact

Interventions

Pre-Generated Personalized LLM Coaching Impact BEHAVIORAL

After the initial 7 days, participants will switch to the other type of prompting for another 7 days. This means that participants who initially received personalized LLM-generated prompts will then receive generic activity prompts, and vice versa. This crossover design allows for each participant to experience both types of interventions, providing a within-subject comparison of the effectiveness of personalized versus generic prompts in increasing physical activity levels.

Generic Activity Prompts; Personalized LLM-Generated Coaching Prompts

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Age: Participants must be 18 years or older.
• Health Status: Participants must be healthy enough to engage in physical activity.
• Language Proficiency: Participants must be able to read, understand, and consent in English or Spanish (dependent on which is being studied).
• Device Ownership: Participants must possess an iPhone and an Apple Watch.
• Data Sharing: Participants must be willing to share their HealthKit data via secure upload.

You may not qualify if:

• Age: Participants under the age of 18.
• Health Status: Participants who are not healthy enough to engage in physical activity.
• Language Proficiency: Participants who cannot read, understand, or consent in English or Spanish.
• Device Ownership: Participants who do not have both an iPhone and an Apple Watch.
• Data Sharing: Participants unwilling to share their HealthKit data via secure upload.

Sponsors & Collaborators

• Stanford University: lead

MeSH Terms

Conditions

Motor Activity

Condition Hierarchy (Ancestors)

Behavior

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: BASIC SCIENCE
• Intervention Model: CROSSOVER
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Fellow, Cardiovascular Medicine

Study Record Dates

• First Submitted: March 11, 2025
• First Posted: March 17, 2025
• Study Start: February 20, 2026
• Primary Completion (Estimated): July 30, 2026
• Study Completion (Estimated): December 1, 2026
• Last Updated: January 23, 2026

Record last verified: 2026-01