Supplements

LLM-driven text-based coaching grounded in the Transtheoretical Model of Change increases daily step count compared to generic prompts in adults at risk for cardiovascular disease.

This study will test whether personalized coaching prompts generated by a large language model (LLM) can increase daily step count more than generic prompts in a fully digital, randomized crossover trial. The primary endpoint is change in daily step count, with a target enrollment of 15,000 adults across the US and UK. Recruitment began in March 2026 and is ongoing.

Last updated: Jul 8, 2026•1 RCTs•📖 Read as article →

Evidence Score

Evidence Score42/100
Human RCT★★☆☆☆
Meta-analysis☆☆☆☆☆
Mechanism★★★★★
Safety★★★★☆
Confidencelow

Study Evidence

Study 1. Design and rationale of the my heart counts cardiovascular health study: a large-scale, fully digital biobank, and randomized trial of large language model-driven coaching of physical activity.

observational

Schmiedmayer P, Johnson A, Schuetz N, Kollmer L, Goldschmidt P, Delgado-SanMartin J, Zhang KW, Mantena SD, Tolas A, Montalvo S, Ramirez-Posada M, O'Sullivan JW, Oppezzo M, King AC, Rodriguez F, Ashley E, Lawrie A, Kim DS · American journal of preventive cardiology (2026)

Participants: N/A
Duration: Not specified (crossover design with intervention weeks)
Intervention: LLM-driven text-based coaching prompts grounded in the Transtheoretical Model of Change vs. generic text-based prompts
Outcome: Change in daily step count (primary), mean active minutes, calorie burn, submaximal and maximal cardiorespiratory fitness, sleep quality, resting heart rate, heart rate variability
Effect Size: N/A
Population: Adults (N=15,000) across the United States and United Kingdom, recruited via smartphone application

Result:

PubMed: 42395096DOI: 10.1016/j.ajpc.2026.101565

Mechanism Graph

LLM generates personalized coaching prompts based on user data and Transtheoretical Model of Change
↓
User receives prompts via smartphone application
↓
User's daily step count is passively monitored via smartphone sensors
↓
Result: Change in daily step count compared to generic prompts

Limitations

  • ⚠Results are not yet available as the study is ongoing (recruitment started March 2026)
  • ⚠Relies on smartphone-based passive data collection, which may have measurement errors or compliance issues
  • ⚠Platform exclusivity (iOS only initially; Android planned for 2027) may limit generalizability

Frequently Asked Questions

What is the primary outcome of the My Heart Counts trial?▼

The primary outcome is the change in daily step count between LLM-driven and generic text-based coaching prompts.

How many participants are being recruited?▼

The target enrollment is 15,000 adults across the United States and United Kingdom.

What technology is used to generate the coaching prompts?▼

The coaching prompts are generated by a large language model (LLM) grounded in the Transtheoretical Model of Change.

When did recruitment for this study begin?▼

Recruitment commenced in March 2026 and is ongoing.

Products

Affiliate links coming soon. We only recommend products that match the doses and forms used in the cited research.

References

  1. 1.Schmiedmayer P, Johnson A, Schuetz N, Kollmer L, Goldschmidt P, Delgado-SanMartin J, Zhang KW, Mantena SD, Tolas A, Montalvo S, Ramirez-Posada M, O'Sullivan JW, Oppezzo M, King AC, Rodriguez F, Ashley E, Lawrie A, Kim DS. "Design and rationale of the my heart counts cardiovascular health study: a large-scale, fully digital biobank, and randomized trial of large language model-driven coaching of physical activity.." American journal of preventive cardiology, 2026. PMID: 42395096 DOI: 10.1016/j.ajpc.2026.101565
Disclaimer: This content is for educational purposes only and is not medical advice. Evidence scores reflect the quality and quantity of available research, not clinical recommendations. Always consult a healthcare professional before starting any supplement or intervention.