Trading pounds for points: Engagement and weight loss in a mobile health intervention.

OBJECTIVE: The objective of this study was to describe participant engagement and examine predictors of weight loss and points earned through the point-based incentive system of the Social Pounds Off Digitally (POD) app. MATERIALS AND METHODS: Overweight and obese adults with Android smartphones/tablets (body mass index 25-49.9 kg/m2; N = 24) were recruited for a 3-month weight loss intervention. Participants completed a survey assessing demographics and personality and had their weight measured. Participants received the content of the intervention via podcasts and used the Social POD app to self-monitor diet, physical activity, and weight. The Social POD app contained: tracking features; in-app notifications to track; pre-set goals for tracking; newsfeed for updates on others' goal attainment; ability to earn and track points for usage (exchanged for study-provided prizes); and a message screen. Analyses examined relationships between percent weight loss, personality characteristics, and total points earned. RESULTS: A total of 4843 points were earned (mean = 202 ± 105 points/participant). Most participants earned all three prizes (62.5%), followed by two prizes (21%), no prizes (12.5%), and one prize (4%). Total points earned significantly predicted percent weight loss (B = -0.02, p = .01), and higher conscientiousness significantly predicted greater total points earned (B = 10.27, p = .01), but other personality characteristics assessed did not. CONCLUSION: A mobile app yielded moderately high participant engagement, as demonstrated by points earned. Earning points was significantly associated with percent weight loss, and conscientiousness was significantly associated with total points earned. Future research should examine whether point systems impact health behavior and weight loss when rewards are discontinued. CLINICAL TRIAL REGISTRATION NUMBER: NCT02344836.

Social networks for improving healthy weight loss behaviors for overweight and obese adults: A randomized clinical trial of the social pounds off digitally (Social POD) mobile app.

OBJECTIVE: To test the efficacy of a weight loss mobile app based on recommender systems and developed by experts in health promotion and computer science to target social support and self-monitoring of diet, physical activity (PA), and weight (Social POD app), compared to a commercially available diet and PA tracking app (standard). MATERIALS AND METHODS: Overweight adults [N=51] were recruited and randomly assigned to either the experimental group [n=26; theory-based podcasts (TBP)+Social POD app] or the comparison group (n=25; TBP+standard app). The Social POD app issued notifications to encourage users to self-monitor and send theory-based messages to support users who had not self-monitored in the previous 48h. Independent samples t-test were used to examine group differences in kilograms lost and change in BMI. Analysis of covariance was used to analyze secondary outcomes while controlling for baseline values. RESULTS: Participant attrition was 12% (n=3 experimental and n=3 comparison). Experimental group participants lost significantly more weight (-5.3kg, CI: -7.5, -3.0) than comparison group (-2.23kg, CI: -3.6, -1.0; d=0.8, r=0.4, p=0.02) and had a greater reduction in BMI (p=0.02). While there were significant differences in positive outcome expectations between groups (p=0.04) other secondary outcomes (e.g., caloric intake and social support) were not significant. DISCUSSION: Use of the Social POD app resulted in significantly greater weight loss than use of a commercially available tracking app. This mobile health intervention has the potential to be widely disseminated to reduce the risk of chronic disease associated with overweight and obesity.

A Mixed-Methods Approach to the Development, Refinement, and Pilot Testing of Social Networks for Improving Healthy Behaviors.

BACKGROUND: Mobile health (mHealth) has shown promise as a way to deliver weight loss interventions, including connecting users for social support. OBJECTIVE: To develop, refine, and pilot test the Social Pounds Off Digitally (POD) Android app for personalized health monitoring and interaction. METHODS: Adults who were overweight and obese with Android smartphones (BMI 25-49.9 kg/m(2); N=9) were recruited for a 2-month weight loss pilot intervention and iterative usability testing of the Social POD app. The app prompted participants via notification to track daily weight, diet, and physical activity behaviors. Participants received the content of the behavioral weight loss intervention via podcast. In order to re-engage infrequent users (did not use the app within the previous 48 hours), the app prompted frequent users to select 1 of 3 messages to send to infrequent users targeting the behavioral theory constructs social support, self-efficacy, or negative outcome expectations. Body weight, dietary intake (2 24-hr recalls), and reported calories expended during physical activity were assessed at baseline and 2 months. All participants attended 1 of 2 focus groups to provide feedback on use of the app. RESULTS: Participants lost a mean of 0.94 kg (SD 2.22, P=.24) and consumed significantly fewer kcals postintervention (1570 kcal/day, SD 508) as compared to baseline (2384 kcal/day, SD 993, P=.01). Participants reported expending a mean of 171 kcal/day (SD 153) during intentional physical activity following the intervention as compared to 138 kcal/day (SD 139) at baseline, yet this was not a statistically significant difference (P=.57). There was not a statistically significant correlation found between total app entries and percent weight loss over the course of the intervention (r=.49, P=.19). Mean number of app entries was 77.2 (SD 73.8) per person with a range of 0 to 219. Messages targeting social support were selected most often (32/68, 47%), followed by self-efficacy (28/68, 41%), and negative outcome expectations (8/68, 12%). Themes from the focus groups included functionality issues, revisions to the messaging system, and the addition of a point system with rewards for achieving goals. CONCLUSIONS: The Social POD app provides an innovative way to re-engage infrequent users by encouraging frequent users to provide social support. Although more time is needed for development, this mHealth intervention can be disseminated broadly for many years and to many individuals without the need for additional intensive in-person hours.

Use artificial neural network to align biological ontologies.

BACKGROUND: Being formal, declarative knowledge representation models, ontologies help to address the problem of imprecise terminologies in biological and biomedical research. However, ontologies constructed under the auspices of the Open Biomedical Ontologies (OBO) group have exhibited a great deal of variety, because different parties can design ontologies according to their own conceptual views of the world. It is therefore becoming critical to align ontologies from different parties. During automated/semi-automated alignment across biological ontologies, different semantic aspects, i.e., concept name, concept properties, and concept relationships, contribute in different degrees to alignment results. Therefore, a vector of weights must be assigned to these semantic aspects. It is not trivial to determine what those weights should be, and current methodologies depend a lot on human heuristics. RESULTS: In this paper, we take an artificial neural network approach to learn and adjust these weights, and thereby support a new ontology alignment algorithm, customized for biological ontologies, with the purpose of avoiding some disadvantages in both rule-based and learning-based aligning algorithms. This approach has been evaluated by aligning two real-world biological ontologies, whose features include huge file size, very few instances, concept names in numerical strings, and others. CONCLUSION: The promising experiment results verify our proposed hypothesis, i.e., three weights for semantic aspects learned from a subset of concepts are representative of all concepts in the same ontology. Therefore, our method represents a large leap forward towards automating biological ontology alignment.