Using Methods From Computational Decision-making to Predict Nonadherence to Fitness Goals: Protocol for an...

Area of Science:

• Behavioral Science
• Computational Modeling
• Health Informatics

Background:

• Sedentary behavior is a leading cause of preventable death, contributing to 2 million deaths annually.
• Despite public health initiatives, sustained behavioral change in physical fitness remains a challenge.
• Predictive models integrating decision-making data and physical activity metrics could identify individuals at risk of nonadherence.

Purpose of the Study:

• To determine if decision-making tasks, like the Iowa Gambling Task, can predict nonadherence to fitness goals.
• To build a predictive model using computational decision-making methods, fitness tracker data, personality traits, and mobile app games.
• To identify digital personas likely to abandon self-determined exercise goals for targeted interventions.

Main Methods:

• A siteless, bring-your-own-device study involving 200 healthy, novice exercisers using Fitbit trackers.
• Participants recruited via social media will provide consent and share Fitbit data through a study app.
• The Iowa Gambling Task will be administered via a web app over a 12-month period.

Main Results:

• Ethics approval obtained from Dublin City University in December 2020.
• Study recruitment was pending at the time of manuscript submission.
• Expected results publication is scheduled for 2022.

Conclusions:

• The study aims to support the development of a predictive model for fitness goal adherence.
• Findings are expected to inform future research on personalized interventions for sustained physical activity.
• Successful identification of at-risk individuals could lead to tailored support strategies.