An interventional study of AI-Personalized Digital Exercise Programme and Standardized Digital Exercise Programme in Physical Activity, Exercise Adherence and Wellbeing, sponsored by Transilvania University of Brasov. Completed at 1 site in Romania. Open to participants aged 18 Years to 65 Years, including healthy volunteers. Per ClinicalTrials.gov, last updated 2026-09-22.
Sponsored by Transilvania University of Brasov · Not applicable, Interventional, and Other
This study evaluated whether an AI-personalized digital exercise programme could improve exercise adherence, physical activity, wellbeing, and physical performance among university students compared with a standardized digital exercise programme. University students were randomly assigned to one of two digital exercise programmes for 8 weeks. The AI-personalized programme adjusted exercise recommendations using participant characteristics, previous exercise adherence, readiness, pain, safety information, and physical performance measures. The comparator provided a standardized digital exercise programme without adaptive weekly personalization. The primary outcome was mean weekly exercise adherence. Secondary outcomes included physical activity, wellbeing, countermovement jump performance, lower-limb reaction time, engagement, usability, and safety.
This was an 8-week, two-group randomized controlled trial conducted among undergraduate students at Transilvania University of Brașov, Romania. The study compared an AI-personalized digital exercise programme with a standardized digital exercise programme delivered within the same digital study environment.
Participants assigned to the AI-personalized group received exercise recommendations through MoveAI-Student version 2.1.0 using the version-controlled v1.3-adaptive system. The system combined prespecified safety rules with a supervised recommendation model. Personalization used participant characteristics, sport participation, weekly training volume, countermovement jump performance, simple and choice reaction time, readiness, pain, previous-week adherence, and safety information. Exercise recommendations could specify session frequency, duration, intensity, and additional emphasis on lower-limb power or reactive drills. Recommendations were updated once per intervention week. Progression was limited by predefined safety rules, and exercise load could be reduced when pain or an adverse-event flag was present. Human override of recommendations was permitted when required.
Participants assigned to the standardized digital comparator used the same digital study environment but did not receive the adaptive weekly prescription procedure. The comparator programme prescribed three exercise sessions per week, with each session lasting 35 minutes.
The primary outcome was mean weekly exercise adherence, calculated from completed sessions relative to prescribed sessions across the 8-week intervention. Secondary outcomes included total physical activity assessed with the International Physical Activity Questionnaire Short Form, WHO-5 wellbeing, countermovement jump performance, simple reaction time, choice reaction time, moderate-to-vigorous physical activity, application engagement, satisfaction, perceived usefulness, usability, sitting time, body weight, body mass index, and adverse events.
The study was designed to estimate the effect of the adaptive programme as a complete intervention compared with standardized digital exercise. It was not designed to isolate the independent effect of the algorithm from differences in exercise prescription or completed exercise exposure.
Exclusion Criteria:
Participants received an 8-week digital exercise programme delivered through MoveAI-Student version 2.1.0. Exercise prescriptions were personalized using the v1.3-adaptive system and updated weekly based on participant characteristics, previous-week adherence, readiness, pain, safety information, and physical performance measures. Recommendations could modify exercise frequency, duration, intensity, and task emphasis.
Behavioral: AI-Personalized Digital Exercise Programme
Participants received an 8-week standardized digital exercise programme through the same study application. The programme prescribed three exercise sessions per week, with each session lasting 35 minutes. Participants did not receive the adaptive weekly personalization procedure used in the experimental group.
Behavioral: Standardized Digital Exercise Programme
An 8-week digital exercise intervention using MoveAI-Student version 2.1.0 and the v1.3-adaptive system. Initial exercise prescriptions ranged from three to five sessions per week, 30 to 45 minutes per session, at moderate-to-vigorous intensity. Recommendations were updated weekly using adherence and safety information. Prescriptions could modify session frequency, duration, intensity, and emphasis on lower-limb power or reactive drills. Predefined safety rules limited weekly progression and allowed reduced exercise load when pain or an adverse-event flag was present.
An 8-week standardized digital exercise intervention delivered through the same study application. Participants were prescribed three exercise sessions per week, with each session lasting 35 minutes. The programme did not use the adaptive weekly prescription procedure applied in the AI-personalized group.
Mean Weekly Exercise Adherence
Weekly adherence was calculated as completed exercise sessions relative to prescribed exercise sessions within each intervention week. The participant-level mean across the 8-week intervention was used as the primary outcome.
Time frame: From intervention initiation through the end of Week 8
Total Physical Activity Assessed With the International Physical Activity Questionnaire-Short Form
Total physical activity was assessed using the International Physical Activity Questionnaire-Short Form (IPAQ-SF) and expressed as metabolic equivalent of task (MET)-minutes per week. Total MET-minutes per week were calculated from reported walking, moderate-intensity activity, and vigorous-intensity activity. The minimum possible value is 0 MET-minutes/week. There is no fixed upper limit for this derived physical-activity measure. Higher values indicate a greater amount of total physical activity.
Time frame: Baseline and at the end of Week 8
5-item World Health Organization Well-Being Index (WHO-5) Score
Well-being was assessed using the 5-item World Health Organization Well-Being Index (WHO-5). Each of the five items is scored from 0 to 5, producing a raw total score from 0 to 25. The raw score was multiplied by 4 to obtain the reported score ranging from 0 to 100. Higher scores indicate better subjective well-being.
Time frame: Baseline and at the end of Week 8
Countermovement Jump Best Height
Best countermovement jump height was assessed using OptoJump Next and expressed in centimeters.
Time frame: Baseline and at the end of Week 8
Countermovement Jump Mean Height
Mean countermovement jump height was assessed using OptoJump Next and expressed in centimeters.
Time frame: Baseline and at the end of Week 8
Simple Reaction Time
Description: Lower-limb simple reaction time was assessed using BlazePod and expressed in milliseconds.
Time frame: Baseline and at the end of Week 8
Choice Reaction Time
Lower-limb choice reaction time was assessed using BlazePod and expressed in milliseconds.
Time frame: Baseline and at the end of Week 8
Plan to share: Yes — Deidentified individual participant data underlying the results reported in the published article will be available upon reasonable request. Shared data may include baseline characteristics, exercise adherence, physical activity, WHO-5 wellbeing, countermovement jump outcomes, simple and choice reaction time, engagement and usability measures, and adverse-event data, as applicable.
Supporting information: Study protocol, Sap
No publications or documents are linked to this record.
This study is completed, as verified in Sep 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.
Transilvania University of Brasov