Personalization in Real-Time Physical Activity Coaching Using Mobile Applications: A Scoping Review

Monteiro-Guerra, Francisco; Rivera-Romero, Octavio; Fernández-Luque, Luis; Caulfield, Brian

doi:10.1109/jbhi.2019.2947243

Cited by 63 publications

(63 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This can include feedback, goal setting or user targeting (ie, conveying that communication is designed specifically for the user). 21 However, more complex forms of personalisation might be needed to increase and maintain engagement with PA interventions, 22 a requirement for a digital intervention to be effective.…”

Section: Introduction Backgroundmentioning

confidence: 99%

mHealth app using machine learning to increase physical activity in diabetes and depression: clinical trial protocol for the DIAMANTE Study

et al. 2020

View full text Add to dashboard Cite

IntroductionDepression and diabetes are highly disabling diseases with a high prevalence and high rate of comorbidity, particularly in low-income ethnic minority patients. Though comorbidity increases the risk of adverse outcomes and mortality, most clinical interventions target these diseases separately. Increasing physical activity might be effective to simultaneously lower depressive symptoms and improve glycaemic control. Self-management apps are a cost-effective, scalable and easy access treatment to increase physical activity. However, cutting-edge technological applications often do not reach vulnerable populations and are not tailored to an individual’s behaviour and characteristics. Tailoring of interventions using machine learning methods likely increases the effectiveness of the intervention.Methods and analysisIn a three-arm randomised controlled trial, we will examine the effect of a text-messaging smartphone application to encourage physical activity in low-income ethnic minority patients with comorbid diabetes and depression. The adaptive intervention group receives messages chosen from different messaging banks by a reinforcement learning algorithm. The uniform random intervention group receives the same messages, but chosen from the messaging banks with equal probabilities. The control group receives a weekly mood message. We aim to recruit 276 adults from primary care clinics aged 18–75 years who have been diagnosed with current diabetes and show elevated depressive symptoms (Patient Health Questionnaire depression scale-8 (PHQ-8) >5). We will compare passively collected daily step counts, self-report PHQ-8 and most recent haemoglobin A1c from medical records at baseline and at intervention completion at 6-month follow-up.Ethics and disseminationThe Institutional Review Board at the University of California San Francisco approved this study (IRB: 17-22608). We plan to submit manuscripts describing our user-designed methods and testing of the adaptive learning algorithm and will submit the results of the trial for publication in peer-reviewed journals and presentations at (inter)-national scientific meetings.Trial registration numberNCT03490253; pre-results.

show abstract

Section: Introduction Backgroundmentioning

confidence: 99%

mHealth app using machine learning to increase physical activity in diabetes and depression: clinical trial protocol for the DIAMANTE Study

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Furthermore, it is suggested that breast cancer survivors want a PA app experience targeted not only to their needs on a group level but also tailored to each individual user [ 13 , 23 , 24 ]. In line with this, personalized or tailored coaching mechanisms can be leveraged to help create experiences that are individualized for each user [ 25 , 26 ]. These are believed to influence the user’s attention and contribute to long-term engagement and adherence to these apps [ 27 ].…”

Section: Introductionmentioning

confidence: 99%

“…These are believed to influence the user’s attention and contribute to long-term engagement and adherence to these apps [ 27 ]. In addition, theory-based behavior change methods have been shown to influence the effectiveness of technology-supported interventions [ 7 ] and should be considered in the design of tools that aim to increase PA [ 8 , 26 ].…”

Section: Introductionmentioning

confidence: 99%

A Personalized Physical Activity Coaching App for Breast Cancer Survivors: Design Process and Early Prototype Testing

Monteiro-Guerra¹,

Signorelli²,

Tadas³

et al. 2020

JMIR Mhealth Uhealth

Self Cite

View full text Add to dashboard Cite

Background Existing evidence supports the many benefits of physical activity (PA) in breast cancer survival. However, few breast cancer survivors adhere to the recommended levels of activity. A PA coaching app that provides personalized feedback, guidance, and motivation to the user might have the potential to engage these individuals in a more active lifestyle, in line with the general recommendations. To develop a successful tool, it is important to involve the end users in the design process and to make theoretically grounded design decisions. Objective This study aimed to execute the design process and early prototype evaluation of a personalized PA coaching app for posttreatment breast cancer survivors. In particular, the study explored a design combining behavioral theory and tailored coaching strategies. Methods The design process was led by a multidisciplinary team, including technical and health professionals, and involved input from a total of 22 survivors. The process comprised 3 stages. In stage 1, the literature was reviewed and 14 patients were interviewed to understand the needs and considerations of the target population toward PA apps. In stage 2, the global use case for the tool was defined, the features were ideated and refined based on theory, and a digital interactive prototype was created. In stage 3, the prototype went through usability testing with 8 patients and was subjected to quality and behavior change potential evaluations by 2 human-computer interaction experts. Results The design process has led to the conceptualization of a personalized coaching app for walking activities that addresses the needs of breast cancer survivors. The main features of the tool include a training plan and schedule, adaptive goal setting, real-time feedback and motivation during walking sessions, activity status through the day, activity history, weekly summary reports, and activity challenges. The system was designed to measure users’ cadence during walking, use this measure to infer their training zone, and provide real-time coaching to control the intensity of the walking sessions. The outcomes from user testing and expert evaluation of the digital prototype were very positive, with scores from the system usability scale, mobile app rating scale, and app behavior change scale of 95 out of 100, 4.6 out of 5, and 15 out of 21, respectively. Conclusions Implementing a user-centered design approach for the development and early evaluation of an app brings essential considerations to tailor the solution to the user’s needs and context. In addition, informing the design on behavioral and tailored coaching theories supports the conceptualization of the PA coaching system. This is critical for optimizing the usability, acceptability, and long-term effectiveness of the tool. After successful early in-laboratory testing, the app will be developed and evaluated in a pilot study in a real-world setting.

show abstract

“…Most recreational runners train by following reasonably generic advice that is, at best, tailored to their projected or target finishtime. The recent availability of wearable sensors and mobile fitness applications promises to re-balance this state of affairs by facilitating the provision of tailored training advice Cau et al 2019;Monteiro-Guerra et al 2019;Mulas et al 2013], personalised motivational supports [Boratto et al 2017;Buttussi et al 2006;Hosseinpour and Terlutter 2019;Mulas et al 2011;, sophisticated performance analysis and prediction [Bartolucci and Murphy 2015;, and even in-race guidance [Berndsen et al 2019]. In this work, we build on these ideas by using raw training data to support marathon runners in two important ways: (1) by predicting their projected marathon time at different points in their training; and (2) by providing tailored training recommendations based on their recent training and their current performance goals.…”

Section: Introductionmentioning

confidence: 99%

“…an injury or period of illness)then they can request a revised training plan based on their recent training and their new goals. While the promise of personalised training recommendations has long been cited as an important goal for these types of system [Monteiro-Guerra et al 2019;Schneider 2017;Zahran et al 2019] progress has so far been limited, notwithstanding some noteworthy early attempts such as [Fister Jr and Fister 2017]. This is, in part at least, because generating personalised training plans ordinarily requires a deep domain model to use as the basis for decision making and recommendation.…”

Section: Introductionmentioning

confidence: 99%

Providing Explainable Race-Time Predictions and Training Plan Recommendations to Marathon Runners

Feely¹,

Caulfield²,

Lawlor³

et al. 2020

Fourteenth ACM Conference on Recommender Systems

Self Cite

View full text Add to dashboard Cite

Millions of people participate in marathon events every year, typically devoting at least 12-16 weeks to building their endurance and fitness so that they can safely complete these gruelling 42.2km races. Most runners follow a training plan that is tailored to their expected finish-time (e.g. sub-4 hours or 4-5 hours), and these plans will prescribe a complex mixture of training sessions to help them achieve these times. However, such plans cannot adapt to the individual needs (fitness levels, changing goals, personal preferences) of runners, providing only broad training guidance rather than more personalised support. The development of wearable sensors and mobile fitness applications facilitates the collection of a large amount of training data from runners. In this paper, we propose a recommender system that utilizes such training data to deliver more personalised training advice to runners, using ideas from casebased reasoning to reuse and adapt the training habits of similar runners. Explainability plays a significant role in this type of system, and we also describe how the predictions and recommendation advice can be presented to runners. An initial off-line evaluation is presented based on a large-scale, real-world dataset. CCS CONCEPTS • Computing methodologies → Machine learning algorithms; Feature selection; • Applied computing → Health informatics.

show abstract

Personalization in Real-Time Physical Activity Coaching Using Mobile Applications: A Scoping Review

Cited by 63 publications

References 79 publications

mHealth app using machine learning to increase physical activity in diabetes and depression: clinical trial protocol for the DIAMANTE Study

mHealth app using machine learning to increase physical activity in diabetes and depression: clinical trial protocol for the DIAMANTE Study

A Personalized Physical Activity Coaching App for Breast Cancer Survivors: Design Process and Early Prototype Testing

Providing Explainable Race-Time Predictions and Training Plan Recommendations to Marathon Runners

Contact Info

Product

Resources

About