Adaptive Self-Efficacy-Based AI Coaching for Cycling
NCT07318233 · Status: NOT_YET_RECRUITING · Phase: NA · Type: INTERVENTIONAL · Enrollment: 120
Last updated 2026-03-03
Summary
The primary objective of this study is to evaluate whether adaptive, AI-delivered personalized self-efficacy-based AI coaching based on real-time physiological and performance feedback enhance indoor cycling power output during a 20-minute time trial compared to static affirmations and exercise-only control conditions.
Conditions
- Exercise Training
- Exercise Behavior
- Exercise Adherence Challenges
- Motivation for Physical Activity
- Motivational Enhancement
Interventions
- BEHAVIORAL
-
Group 1: Self-efficacy-based AI coaching
The Thompson Sampling contextual bandit algorithm, trained on Session 1 data, monitors performance continuously and evaluates every 5 seconds whether to deliver an affirmation. The policy is trained to maximize a multi-objective "efficacy-preserving performance" function that rewards: * Maintaining target power relative to rolling 30s/2min/5min baselines * Stabilizing short-horizon power variability (30s coefficient of variation) * Stabilizing heart-rate (HR) trajectory consistent with efficient pacing The decision process considers: * Current power relative to 30-second, 2-minute, and 5-minute rolling averages * Power output variability (coefficient of variation over past 30 seconds) * Heart rate trajectory and cardiac drift patterns * Cadence stability and changes from baseline * Time elapsed and expected fatigue progression based on power-duration curve Self-efficacy-based AI coaching adapts to physiological measures (power and heart rate).
- BEHAVIORAL
-
Group 2: Static AI Affirmations
Generic motivational messages delivered at fixed intervals (minutes 3, 6, 9, 12, 15, and 18) regardless of performance state. Messages follow the same complexity gradient based on elapsed time rather than individual response: * Minutes 3, 6: "You're building momentum with every pedal stroke-maintain this strong rhythm" * Minutes 9, 12: "Strong effort-push through this challenge" * Minutes 15, 18: "Final push-finish strong"
Sponsors & Collaborators
-
University of Miami
lead OTHER
Principal Investigators
-
Anna Queiroz, Ph.D. · University of Miami
Study Design
- Allocation
- RANDOMIZED
- Purpose
- BASIC_SCIENCE
- Masking
- SINGLE
- Model
- PARALLEL
Eligibility
- Min Age
- 18 Years
- Max Age
- 40 Years
- Sex
- ALL
- Healthy Volunteers
- Yes
Timeline & Regulatory
- Start
- 2026-06-01
- Primary Completion
- 2028-12-23
- Completion
- 2028-12-28
Countries
- United States
Study Locations
More Related Trials
-
Real-time Behavioral Interventions
NCT04457128 ·Status: UNKNOWN ·Phase: NA
-
Efficacy of Exercise Videogames for Physical Activity Adoption and Maintenance
NCT03298919 ·Status: COMPLETED ·Phase: NA
-
Precision Assignment of Intervention Messages to Promote Physical Activity - Precision AIM
NCT04972279 ·Status: UNKNOWN ·Phase: PHASE1/PHASE2
-
The Fitness, Game Bike Adherence, Motivation and Exercise Study
NCT01373762 ·Status: COMPLETED ·Phase: NA
-
Individualized Motivational Print Materials to Encourage More Physical Activity
NCT00367029 ·Status: COMPLETED ·Phase: PHASE3
-
Smart mHealth Strategy for Physical Activity and Health Promotion
NCT06423014 ·Status: RECRUITING ·Phase: NA
-
Utilizing Tailored Step-Count Feedback to Enhance Physical Activity in the Elderly
NCT01158638 ·Status: UNKNOWN ·Phase: PHASE2
-
Motivation for Exercise: A Mood-Based Focus
NCT06706180 ·Status: COMPLETED ·Phase: NA
-
Machine-based Algorithm for Increased Physical Activity and Sustained User Engagement
NCT06388317 ·Status: COMPLETED ·Phase: NA
-
Testing Responses of Young Adults to Intervention Messages for Promoting Physical Activity Trial
NCT05794178 ·Status: ACTIVE_NOT_RECRUITING ·Phase: NA
-
eMOTION: Examining Affective Mechanisms in Physical Activity Engagement
NCT06570642 ·Status: RECRUITING ·Phase: NA
-
A Mobile App to Increase Physical Activity in Students
NCT04440553 ·Status: COMPLETED ·Phase: NA
-
Effects of Physical Activity Coaching on Health and Behaviour Parameters in Diabetic Persons
NCT02064335 ·Status: COMPLETED ·Phase: NA
-
Interactive Technologies to Increase Exercise Behavior
NCT00200317 ·Status: COMPLETED ·Phase: PHASE1/PHASE2
-
The YourMove Study: Optimizing Individualized and Adaptive mHealth Interventions Via Control Systems Engineering Methods
NCT05598996 ·Status: COMPLETED ·Phase: NA
-
Evaluating Mechanisms of Action of Adaptive Goal-Setting for Physical Activity
NCT04505241 ·Status: COMPLETED ·Phase: NA
-
A Study to Test the Effectiveness of Different Interventions to Improve Physical Activity in Adults.
NCT04902014 ·Status: COMPLETED ·Phase: NA
-
The Impact of Real-time Feedback on Physical Activity Patterns in Flemish Employees
NCT01432327 ·Status: COMPLETED ·Phase: NA
-
Health Coaching to Promote Physical Activity for Coronary Heart Disease Prevention
NCT01089842 ·Status: UNKNOWN ·Phase: NA
-
Evaluating the Impact of Personalized Move Goals on Physical Activity
NCT05123989 ·Status: UNKNOWN ·Phase: NA
-
Physical Activity in Persons Newly Diagnosed With Multiple Sclerosis
NCT05641532 ·Status: COMPLETED ·Phase: NA
-
Web-based Physical Activity Program
NCT01218412 ·Status: UNKNOWN ·Phase: PHASE1
-
The Engaged4Life Study: Enhancing the Health-Promoting Effects of Older Adults' Activity Portfolios
NCT03337204 ·Status: COMPLETED ·Phase: NA
-
Evaluating Motivational Interviewing and Habit Formation to Enhance the Effect of Activity Trackers on Physical Activity
NCT03837366 ·Status: COMPLETED ·Phase: NA
-
Artificial Intelligence and Physical Activity Among People From Ethnic Minority Groups
NCT05779696 ·Status: UNKNOWN