An Evaluation of the Effect of App-Based Exercise Prescription Using RL on Satisfaction and Exercise Intensity (PERFORM-RL)

An Evaluation of the Effect of App-Based Exercise Prescription Using RL on Satisfaction and Exercise Intensity: Randomized Crossover Trial.

The PERFORM-RL study (Personalised Exercise Prescription for Remote Fitness Using Reinforcement Learning) was a 12-week randomised crossover trial designed to evaluate the effectiveness of an app-based exercise prescription system powered by reinforcement learning (RL). The study aimed to investigate whether exercise sessions tailored by RL would lead to greater user satisfaction and higher exercise intensity compared to generic, non-personalised exercise sessions.

The trial enrolled 62 participants (27 males, 42 females; mean age 42 years) who were randomly assigned to alternate between two conditions: an RL-driven intervention, which personalised exercise sessions based on user preferences and feedback, and a control condition with non-tailored, generic exercise sessions. Participants were instructed to complete three exercise sessions per week using the i80 BPM app, which offered a variety of video-guided exercises. The RL model customised these sessions based on user feedback, including satisfaction and perceived intensity, with the goal of optimising future sessions.

The primary outcome was user satisfaction, measured via the Physical Activity Enjoyment Scale (PACES-8) after each session. Secondary outcomes included exercise intensity, as assessed by the Borg Rating of Perceived Exertion (RPE) scale, and heart rate data collected through a Samsung Galaxy Fit 2 smartwatch.

The trial was conducted in Dublin, Ireland, and approved by the UCD Human Research Ethics Committee (LS-21-34-Tragos-Lawlor). Participants provided informed consent and were blinded to their group allocation. The trial was not registered prospectively, but steps are being taken for retrospective registration.

Study Overview

• Status: Completed
• Conditions: Exercise; Mobile Applications
• Intervention / Treatment: Device: Reinforcement Learning (RL) Personalised Exercise Prescription via i80 BPM App; Device: Generic Non-Personalised Exercise Prescription via i80 BPM App

Detailed Description

Study Overview The PERFORM-RL study was a 12-week randomised crossover trial conducted to evaluate the impact of app-based personalised exercise prescription on user satisfaction and exercise intensity, using reinforcement learning (RL) as the key mechanism for customisation. This study sought to determine whether RL-generated exercise sessions could improve user satisfaction and increase exercise intensity compared to non-personalised, generic sessions. The findings are expected to contribute to the growing field of digital health interventions, particularly in the area of scalable, app-based exercise programmes designed to enhance user engagement and long-term adherence.

Study Objectives The primary objective of the study was to compare user satisfaction between RL-generated exercise sessions and generic sessions. The hypothesis was that RL-driven personalisation would result in higher user satisfaction, as measured by the Physical Activity Enjoyment Scale (PACES-8). The secondary objective was to evaluate the effect of RL on exercise intensity, as measured by the Borg Rating of Perceived Exertion (RPE) scale. It was hypothesised that participants would exercise at a higher intensity in the RL condition due to the tailored nature of the sessions, which aligned with their preferences and fitness levels.

Study Design

This was a randomised, assessor-blinded crossover trial. Each participant completed two different conditions during the 12-week study:

Intervention Condition: Exercise sessions were personalised using a reinforcement learning model that adapted session difficulty and content based on participant preferences, past performance, and feedback.

Control Condition: Participants completed generic, non-personalised exercise sessions. These sessions were pre-designed and did not adapt based on the user's feedback or preferences.

Participants alternated weekly between the intervention and control conditions, meaning that each week they experienced a different approach to exercise prescription. This design ensured that each participant acted as their own control, reducing variability and increasing the robustness of the findings. All exercise sessions were delivered through the i80 BPM app, developed by Samsung, which also facilitated data collection.

Participants Participants were recruited from Dublin, Ireland, and its surrounding areas via word of mouth and social media. A total of 62 participants (27 males, 42 females; mean age 42 years) completed at least one exercise session, with 559 sessions completed overall during the 12-week trial period. Participants were healthy, recreationally active adults aged 18 to 65 years. They were screened for eligibility using the "Exercise Preparticipation Health Screening Questionnaire for Exercise Professionals." Exclusion criteria included physical disability, severe cognitive impairment, or an inability to read and write in English.

Interventions Reinforcement Learning (RL) Intervention

The RL model employed by the i80 BPM app personalised exercise sessions based on user preferences, perceived exertion, and feedback from previous sessions. The RL framework used a decision-making agent, which selected exercises from a pre-existing database based on the user's fitness level, goals, and real-time feedback. The model's reward function aimed to maximise user satisfaction and session effectiveness by adapting the exercise difficulty and content in response to the user's evolving needs.

For example, if a participant reported high satisfaction and moderate intensity in a previous session, the RL model would suggest similar or slightly more challenging exercises for the next session. The RL system continuously learned from user interactions, adjusting the exercise prescription to maintain optimal engagement and effectiveness.

Control Condition

In the control condition, participants received generic exercise sessions that were not personalised or adapted based on user feedback. These sessions included a fixed selection of exercises and did not evolve over time, providing a baseline against which the personalised RL intervention could be compared.

Outcome Measures Primary Outcome: User Satisfaction

User satisfaction was assessed after each session using an abbreviated 8-item version of the Physical Activity Enjoyment Scale (PACES-8). This validated scale measures the extent to which participants enjoyed their exercise sessions. Scores range from 1 (low satisfaction) to 5 (high satisfaction), with higher scores indicating greater enjoyment and overall satisfaction with the exercise experience.

Secondary Outcome: Exercise Intensity

Exercise intensity was measured using the Borg Rating of Perceived Exertion (RPE) scale, which ranges from 1 (very easy) to 10 (maximum exertion). Participants were prompted to rate their perceived exertion after each session via the app, ensuring real-time capture of their experience. Heart rate data, collected using a Samsung Galaxy Fit 2 smartwatch, served as an additional measure of intensity, validating the subjective RPE scores.

Additional Outcome: Heart Rate

Heart rate was continuously monitored during each session using the Samsung Galaxy Fit 2 smartwatch. The heart rate data was automatically relayed to the i80 BPM app and used to track physiological responses to the exercise sessions.

Data Collection and Management Data were collected through the i80 BPM app, which recorded user satisfaction, exercise intensity, heart rate, and the duration of each exercise session. To ensure participant confidentiality, all data were anonymised before analysis. Participants were assigned a unique identification code, and all sensitive documents were stored securely, with only authorised personnel granted access.

Sample Size and Power Calculations Based on a previous feasibility study, the sample size was estimated to be a minimum of 40 participants to detect a mean difference of 8 points on the PACES-8 scale with 80% power. A total of 69 participants were recruited to account for potential dropouts, and 62 participants completed at least one exercise session. The final sample size provided sufficient power to detect differences between the RL and control conditions.

Statistical Analysis Generalised Estimating Equations (GEE) were used to analyse the primary and secondary outcomes. GEE models were applied to account for the correlation of repeated measures within subjects. The dependent variables in the models were user satisfaction (PACES-8 scores) and perceived exertion (Borg scale scores), while the independent variables were condition (RL vs control) and trial week. Covariates included age, gender, and baseline physical activity levels, with participant ID included as a subject effect.

• Study Type: Interventional
• Enrollment (Actual): 69
• Phase: Not Applicable

Contacts and Locations

Study Locations

• Ireland
  • Co. Dublin
    • Dublin, Co. Dublin, Ireland, D04C7X2
      • University College Dublin

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

Healthy, recreationally active adults aged 18 to 65 years. Able to engage in aerobic activity for a total of 80 minutes at moderate intensity, no more than two times per week.

Able to provide informed consent. Ability to read and understand English to engage with the study materials and complete the app-based exercises.

Access to a compatible smartphone to download and use the i80 BPM app.

Exclusion Criteria:

Individuals with any physical disability or motor impairment that prevents participation in exercise.

Individuals with severe cognitive impairment. Individuals unable to read or write in English. Known contraindications to exercise, as identified by the 'Exercise Preparticipation Health Screening Questionnaire for Exercise Professionals'.

Participation in another clinical trial or study that could interfere with the trial results.

Engaging in high-level or professional athletic training or more than three days of vigorous physical activity per week.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Treatment
• Allocation: Randomized
• Interventional Model: Crossover Assignment
• Masking: Double

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Reinforcement Learning (RL) Personalised Exercise Prescription; Participants in this arm received personalised exercise sessions via the i80 BPM app, which utilised a reinforcement learning (RL) model. The RL algorithm adapted exercise parameters (e.g., intensity, type of exercise, duration) based on individual preferences, performance, and feedback to optimise user satisfaction and engagement. Sessions were tailored specifically to each participant over the 12-week trial period.	Device: Reinforcement Learning (RL) Personalised Exercise Prescription via i80 BPM App; This intervention involved the use of a smartphone app, i80 BPM, which delivered personalised exercise prescriptions using a reinforcement learning (RL) model. The RL algorithm tailored the exercise sessions by adapting variables such as intensity, duration, and exercise type based on individual user preferences, real-time feedback, and performance data. This dynamic personalisation was designed to enhance user satisfaction and engagement over the 12-week study period. Participants completed three exercise sessions per week.
Active Comparator: Generic Non-Personalised Exercise Prescription; Participants in this arm received generic, non-personalised exercise sessions using the same i80 BPM app. These sessions did not adapt to user preferences or feedback and consisted of pre-designed exercises that were uniform across all participants. This arm served as a control to compare against the RL-personalised intervention.	Device: Generic Non-Personalised Exercise Prescription via i80 BPM App; This intervention used the same i80 BPM smartphone app to deliver generic, pre-designed exercise sessions that did not adapt based on user preferences or feedback. The exercise sessions were standardised for all participants, with no customisation. The control arm served as a comparator to evaluate the impact of personalised, RL-driven exercise prescriptions. Participants completed three exercise sessions per week.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
User Satisfaction with Exercise Sessions (PACES-8 Scale)	User satisfaction was measured using the Physical Activity Enjoyment Scale (PACES-8), an abbreviated 8-item version. Participants rated their satisfaction with each exercise session on a scale from 1 (low satisfaction) to 5 (high satisfaction). Higher scores indicate greater enjoyment and overall satisfaction with the exercise experience. The measure was administered after each session.	At the end of each exercise session during the 12-week study.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Exercise Intensity (Borg Rating of Perceived Exertion Scale)	Exercise intensity was assessed using the Borg Rating of Perceived Exertion (RPE) scale, ranging from 1 (very easy) to 10 (maximum exertion). Participants reported their perceived intensity of each exercise session via the app immediately after the session. Additionally, heart rate data collected from the Samsung Galaxy Fit 2 smartwatch was used to validate intensity levels.	At the end of each exercise session during the 12-week study.

Collaborators and Investigators

• Sponsor: University College Dublin

Study record dates

Study Major Dates

• Study Start (Actual): September 1, 2022
• Primary Completion (Actual): November 16, 2022
• Study Completion (Actual): November 30, 2022

Study Registration Dates

• First Submitted: October 15, 2024
• First Submitted That Met QC Criteria: October 20, 2024
• First Posted (Actual): October 22, 2024

Study Record Updates

• Last Update Posted (Actual): October 22, 2024
• Last Update Submitted That Met QC Criteria: October 20, 2024
• Last Verified: October 1, 2024

More Information

Terms related to this study

• Keywords: mHealth; Exercise therapy; Reinforcement Learning
• Other Study ID Numbers: LS-21-34-Tragos-Lawlor; 12/RC/2289_P2 (Other Grant/Funding Number: Science Foundation Ireland)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Individual participant data (IPD) will not be shared, as the data are considered valuable intellectual property by the industry partners involved in the study. Sharing the data would conflict with existing agreements regarding the protection and use of proprietary information.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No