A Protocol for Digital Phenotyping: Can Methods From Computational Models of Decision-Making Be Used To Predict Those Most Likely To Be Non-Adherent to Fitness Goals? (Preprint)
UNSTRUCTURED Can methods from computational models of decision-making be used to build a predictive model to identify individuals most likely to be non-adherent to personal physical goals? This predictive model may have significant value in the global battle against obesity. Despite the growing awareness of the considerable impact of physical inactivity on human health, sedentary behavior is increasingly linked to premature death in the developed world. The annual impact of sedentary behaviors is significant, causing an estimated 2 million deaths. From a global perspective, sedentary behavior is one of the ten leading causes of mortality and morbidity. Annually considerable funding and countless public health initiatives promote physical fitness with little impact on sustained behavioral change. Predictive models developed from multimodal methodologies combining data from decision-making tasks with contextual insights and objective physical activity data can be used to identify those most likely to abandon their fitness goals. This information has the potential to be used to develop more targeted support to ensure those who embark on fitness programs are successful. This research aims to determine if it is possible to use decision-making tasks such as the Iowa Gambling Task (IGT) to help determine those most likely to abandon their fitness goals? Predictive models built using methods from computational models of decision making, combining objective data from a fitness tracker with personality traits and modeling from decision-making games delivered via a mobile application, will be used to ascertain if a predictive algorithm can identify digital personae's most likely to be non-adherent to self-determine exercise goals. If it is possible to phenotype these individuals, then it may be possible to tailor initiatives to support these individuals to stay the course. This study design is entirely virtual and based on a "Bring your own device" (BYOD) model. Two hundred healthy adults who are novice exercisers and own a FITBIT physical activity tracker (FITBIT, Inc. San Francisco, USA) will be recruited via social media for the study. Subjects will e-consent via the study app, which they will download from the Google/Apple play store. They will also consent to share their FITBIT data. Necessary demographic information concerning age and gender will be collected as part of the recruitment process. Over 12 months, scheduled study assessments will be pushed to the subjects to complete. The IGT will be administered via a web application shared via a URL. Ethics approval was received in December 2020 from Dublin City University. At manuscript submission, study recruitment is pending. Expected results will be published in 2022. This study is registered with Clinical Trials.Gov: Registration number NCT04783298