Automated Personalized Feedback for Physical Activity and Dietary Behavior Change With Mobile Phones: A Randomized Controlled Trial on Adults

Abstract

BackgroundA dramatic rise in health-tracking apps for mobile phones has occurred recently. Rich user interfaces make manual logging of users’ behaviors easier and more pleasant, and sensors make tracking effortless. To date, however, feedback technologies have been limited to providing overall statistics, attractive visualization of tracked data, or simple tailoring based on age, gender, and overall calorie or activity information. There are a lack of systems that can perform automated translation of behavioral data into specific actionable suggestions that promote healthier lifestyle without any human involvement.ObjectiveMyBehavior, a mobile phone app, was designed to process tracked physical activity and eating behavior data in order to provide personalized, actionable, low-effort suggestions that are contextualized to the user’s environment and previous behavior. This study investigated the technical feasibility of implementing an automated feedback system, the impact of the suggestions on user physical activity and eating behavior, and user perceptions of the automatically generated suggestions.MethodsMyBehavior was designed to (1) use a combination of automatic and manual logging to track physical activity (eg, walking, running, gym), user location, and food, (2) automatically analyze activity and food logs to identify frequent and nonfrequent behaviors, and (3) use a standard machine-learning, decision-making algorithm, called multi-armed bandit (MAB), to generate personalized suggestions that ask users to either continue, avoid, or make small changes to existing behaviors to help users reach behavioral goals. We enrolled 17 participants, all motivated to self-monitor and improve their fitness, in a pilot study of MyBehavior. In a randomized two-group trial, investigators randomly assigned participants to receive either MyBehavior’s personalized suggestions (n=9) or nonpersonalized suggestions (n=8), created by professionals, from a mobile phone app over 3 weeks. Daily activity level and dietary intake was monitored from logged data. At the end of the study, an in-person survey was conducted that asked users to subjectively rate their intention to follow MyBehavior suggestions.ResultsIn qualitative daily diary, interview, and survey data, users reported MyBehavior suggestions to be highly actionable and stated that they intended to follow the suggestions. MyBehavior users walked significantly more than the control group over the 3 weeks of the study (P=.05). Although some MyBehavior users chose lower-calorie foods, the between-group difference was not significant (P=.15). In a poststudy survey, users rated MyBehavior’s personalized suggestions more positively than the nonpersonalized, generic suggestions created by professionals (P<.001).ConclusionsMyBehavior is a simple-to-use mobile phone app with preliminary evidence of efficacy. To the best of our knowledge, MyBehavior represents the first attempt to create personalized, contextualized, actionable suggestions automatically from self-tracked information...

Characteristics of Smartphone Applications for Nutrition Improvement in Community Settings: A Scoping Review

“…Of the 4818 titles identified from the database search, 64 articles were included: 9 reporting dietary self-monitoring trials (38)(39)(40)(41)(42)(43)(44)(45)(46), 18 reporting nutritionimprovement trials (36,(47)(48)(49)(50)(51)(52)(53)(54)(55)(56)(57)(58)(59)(60)(61)(62)(63), 30 reporting applicationdevelopment projects (37,, and 7 reporting qualitative studies with consumers (93)(94)(95)(96)(97)(98)(99). Five reports were published in 2016, 16 each in 2015 and 2014, 11 in 2013, and 16 between 2008 and 2012.…”

“…Achieving a balance of simplicity and detail in food logging was important for all populations, with manual entry considered boring and burdensome (51,56,90,93,97). Autocomplete functions (41,93,98), crowdsourcing-based semi-automated approaches (51), barcode scanners and drop-down menus (51,56), and comprehensive (exact products and brands) databases improved logging (93,98). Additionally, reports of progress based on logging commenting on overall diet quality, rather than just calorie tracking, were highly valued (38,43,93,95,(97)(98)(99).…”

“…The evaluation that was reported pertained only to content tailoring and presentation. The tailoring of educational information and environmental supports, such as food product recommendations, to match the nutritional needs of subpopulations (age, life-stage, SES, cultural heritage, and disease status) was considered important for general (51) and young-adult populations (95,97). Regarding tailored feedback, both positive and negative reinforcement were considered motivating by overweight (90) and young-adult populations (99), although young adults were clear this should not feel like "telling off " (93).…”

Feasibility and Acceptability of Mobile Phone–Based Auto-Personalized Physical Activity Recommendations for Chronic Pain Self-Management: Pilot Study on Adults (Preprint)

“…Using this data, MyBehaviorCBP automatically generates and issues physical activity recommendations based on an individual's past behavior. This strategy of persuasion has been shown to be effective in our predicating system designed for general populations -MyBehavior [33,34]. This earlier system was designed to promote both more energetic exercising and lower calorie dietary intake based on a user's past actions.…”

“…The method for this grouping is a data-clustering algorithm; details about this approach have been previously published [34,35]. The main intuition is that the same type of activities will co-occur at similar locations and are therefore assigned to the same cluster.…”