An interventional study of Personalized LLM Coaching and Generic Activity Prompts in Cardiovascular Health and Physical Activity, sponsored by Stanford University. Not yet recruiting. Open to participants aged 18 Years and older, including healthy volunteers. Per ClinicalTrials.gov, last updated 2026-02-23.
Sponsored by Stanford University · Not applicable, Interventional, and Prevention
The My Heart Counts Cardiovascular Health Study will utilize mobile health capabilities of smartphones to assess daily activity measures and compare these to measures of cardiovascular health risk factors and fitness. The study aims to collect cardiovascular health data on a diverse population by making the application available on both iOS and Android platforms. Using smartphone sensors and connected devices, the study will collect physical activity metrics, heart rate data, and responses to health questionnaires. The study includes a randomized crossover trial component examining the effectiveness of personalized activity coaching prompts generated by a language model compared to generic prompts.
My Heart Counts is a smartphone-based mobile cardiovascular health research study designed to collect data on physical activity and heart health across a broad population. This new version expands on the original study (IRB-31409) with several key improvements: inclusion of Android users alongside iOS, creation of a Spanish-language version, and, for future versions of the app, development of a platform architecture that can host multiple sub-studies.
The study will utilize smartphone sensors and connected devices to measure physical activity patterns, fitness levels through standardized tests (6-minute walk test, 12-minute run/walk test), and cardiovascular risk factors reported through health questionnaires. All data collection occurs remotely through participants' smartphones without requiring clinical visits.
A key component of the study is a 14-day randomized crossover trial evaluating the effectiveness of different physical activity coaching approaches.
Participants will experience both personalized coaching messages generated by a large language model and standard activity prompts, each for 7 days, in a randomly assigned order. The primary outcome will be the change in physical activity levels between intervention periods.
The study will serve as a digital biobank, with data made available to qualified researchers after appropriate de-identification. This platform approach will enable efficient recruitment for future cardiovascular health sub-studies without requiring development of new applications.
2,418 studies on the registry are indexed under Motor Activity; 1,162 are open to participants now.
This study's planned enrollment of 15,000 is above the median of 60 across 2,111 interventional studies indexed under Motor Activity.
Browse Motor Activity studies →Stanford University is the lead sponsor of 2,117 studies on the registry; 425 are open to participants now.
Of its 259 completed or terminated interventional studies of FDA-regulated products, 197 (76%) have results posted.
Counted across the registry records on this site, refreshed daily.
Exclusion Criteria:
Behavioral: Personalized LLM Coaching
Behavioral: Generic Activity Prompts
Participants receive daily text messages containing exercise coaching prompts generated by a large language model (LLM) that are personalized to the user's demographic information for a period of 7 days.
Participants receive generic daily activity prompts for a period of 7 days (e.g., "Push yourself! Reach 10,000 steps today.")
Change in Physical Activity levels
Change in daily physical activity levels as measured by step count smartphone sensors and connected health devices.
Time frame: Time Frame: 14 days (7 days in each intervention period)
No study locations are listed for this record.
Plan to share: No
No publications or documents are linked to this record.
This study is not yet recruiting, as verified in Feb 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
Stanford University