Ignite Creation Date:
2026-03-26 @ 3:19 PM
Ignite Modification Date:
2026-03-31 @ 12:40 PM
Study NCT ID:
NCT07318233
Status:
NOT_YET_RECRUITING
Last Update Posted:
2026-03-03
First Post:
2025-12-19
Is NOT Gene Therapy:
True
Has Adverse Events:
False
Brief Title:
Adaptive Self-Efficacy-Based AI Coaching for Cycling
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2026-03-25'}, 'conditionBrowseModule': {'meshes': [{'id': 'D009043', 'term': 'Motor Activity'}], 'ancestors': [{'id': 'D001519', 'term': 'Behavior'}]}}, 'protocolSection': {'designModule': {'phases': ['NA'], 'studyType': 'INTERVENTIONAL', 'designInfo': {'allocation': 'RANDOMIZED', 'maskingInfo': {'masking': 'SINGLE', 'whoMasked': ['PARTICIPANT']}, 'primaryPurpose': 'BASIC_SCIENCE', 'interventionModel': 'PARALLEL'}, 'enrollmentInfo': {'type': 'ESTIMATED', 'count': 120}}, 'statusModule': {'overallStatus': 'NOT_YET_RECRUITING', 'startDateStruct': {'date': '2026-06-01', 'type': 'ESTIMATED'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2026-02', 'completionDateStruct': {'date': '2028-12-28', 'type': 'ESTIMATED'}, 'lastUpdateSubmitDate': '2026-02-27', 'studyFirstSubmitDate': '2025-12-19', 'studyFirstSubmitQcDate': '2025-12-22', 'lastUpdatePostDateStruct': {'date': '2026-03-03', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2026-01-05', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2028-12-23', 'type': 'ESTIMATED'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'Mean cycling power output during 20-minute time trial', 'timeFrame': 'Day 2', 'description': "Average cycling power output over the full 20-minute time trial. The outcome compares mean power between intervention arms (adaptive AI coaching vs. static affirmations vs. exercise-only control). Power is captured continuously via the cycling ergometer and summarized as the mean watts for each participant's trial."}]}, 'oversightModule': {'oversightHasDmc': False, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'keywords': ['Physical Activity', 'AI affirmations', 'just-in-time adaptive intervention', 'cycling'], 'conditions': ['Exercise Training', 'Exercise Behavior', 'Exercise Adherence Challenges', 'Motivation for Physical Activity', 'Motivational Enhancement']}, 'descriptionModule': {'briefSummary': '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.'}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['ADULT'], 'maximumAge': '40 Years', 'minimumAge': '18 Years', 'healthyVolunteers': True, 'eligibilityCriteria': 'Inclusion Criteria:\n\n* Age 18-40 years\n\n * Recreationally active\n * Familiar with stationary cycling\n * Able to complete 20 minutes of vigorous cycling\n\nExclusion Criteria:\n\n* Cardiovascular, metabolic, or respiratory conditions\n\n * Medications affecting heart rate response\n * Lower extremity injury within past 3 months\n * Competitive cyclists (\\>10 hours cycling/week)\n * Pregnancy'}, 'identificationModule': {'nctId': 'NCT07318233', 'acronym': 'AI', 'briefTitle': 'Adaptive Self-Efficacy-Based AI Coaching for Cycling', 'organization': {'class': 'OTHER', 'fullName': 'University of Miami'}, 'officialTitle': 'Adaptive Self-Efficacy-Based AI Coaching for Enhanced Indoor Cycling Performance: A Personalized Machine Learning Approach', 'orgStudyIdInfo': {'id': '20251354'}}, 'armsInterventionsModule': {'armGroups': [{'type': 'NO_INTERVENTION', 'label': 'Control Group', 'description': 'No affirmations delivered. Participants receive only time notifications at 5, 10, 15, and 19 minutes for pacing awareness. Same equipment worn to control for potential monitoring effects.'}, {'type': 'EXPERIMENTAL', 'label': 'Group 1: Self-efficacy-based AI coaching', 'description': 'The Thompson Sampling contextual bandit algorithm, trained on Session 1 data, monitors performance continuously and evaluates every 5 seconds whether to deliver an affirmation.', 'interventionNames': ['Behavioral: Group 1: Self-efficacy-based AI coaching']}, {'type': 'ACTIVE_COMPARATOR', 'label': 'Group 2: Static AI Affirmations', 'description': '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.', 'interventionNames': ['Behavioral: Group 2: Static AI Affirmations']}], 'interventions': [{'name': 'Group 1: Self-efficacy-based AI coaching', 'type': 'BEHAVIORAL', 'description': '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:\n\n* Maintaining target power relative to rolling 30s/2min/5min baselines\n* Stabilizing short-horizon power variability (30s coefficient of variation)\n* Stabilizing heart-rate (HR) trajectory consistent with efficient pacing\n\nThe decision process considers:\n\n* Current power relative to 30-second, 2-minute, and 5-minute rolling averages\n* Power output variability (coefficient of variation over past 30 seconds)\n* Heart rate trajectory and cardiac drift patterns\n* Cadence stability and changes from baseline\n* Time elapsed and expected fatigue progression based on power-duration curve Self-efficacy-based AI coaching adapts to physiological measures (power and heart rate).', 'armGroupLabels': ['Group 1: Self-efficacy-based AI coaching']}, {'name': 'Group 2: Static AI Affirmations', 'type': 'BEHAVIORAL', 'description': '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:\n\n* Minutes 3, 6: "You\'re building momentum with every pedal stroke-maintain this strong rhythm"\n* Minutes 9, 12: "Strong effort-push through this challenge"\n* Minutes 15, 18: "Final push-finish strong"', 'armGroupLabels': ['Group 2: Static AI Affirmations']}]}, 'contactsLocationsModule': {'locations': [{'zip': '33146', 'city': 'Coral Gables', 'state': 'Florida', 'country': 'United States', 'contacts': [{'name': 'Anna Queiroz, Ph.D.', 'role': 'CONTACT', 'email': 'aqueiroz@miami.edu', 'phone': '305-284-3752'}, {'name': 'Meshak Cole, B.S.', 'role': 'CONTACT', 'email': 'mwc94@miami.edu', 'phone': '305 2843752'}], 'facility': 'University of Miami', 'geoPoint': {'lat': 25.72149, 'lon': -80.26838}}], 'centralContacts': [{'name': 'Anna Queiroz, Ph.D.', 'role': 'CONTACT', 'email': 'aqueiroz@miami.edu', 'phone': '305-284-3752'}, {'name': 'Meshak Cole, B.S.', 'role': 'CONTACT', 'email': 'mwc94@miami.edu', 'phone': '305-284-3752'}], 'overallOfficials': [{'name': 'Anna Queiroz, Ph.D.', 'role': 'PRINCIPAL_INVESTIGATOR', 'affiliation': 'University of Miami'}]}, 'ipdSharingStatementModule': {'ipdSharing': 'NO'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'University of Miami', 'class': 'OTHER'}, 'responsibleParty': {'type': 'PRINCIPAL_INVESTIGATOR', 'investigatorTitle': 'Associate Professor', 'investigatorFullName': 'Anna Queiroz', 'investigatorAffiliation': 'University of Miami'}}}}