Use of a Mobile Lifestyle Intervention App as an Early Intervention for Adolescents With Obesity: Single-Cohort Study

A review of the application of deep learning in obesity: From early prediction aid to advanced management assistance

BACKGROUND AND AIMS

Obesity is a chronic disease which can cause severe metabolic disorders. Machine learning (ML) techniques, especially deep learning (DL), have proven to be useful in obesity research. However, there is a dearth of systematic reviews of DL applications in obesity. This article aims to summarize the current trend of DL usage in obesity research.

METHODS

An extensive literature review was carried out across multiple databases, including PubMed, Embase, Web of Science, Scopus, and Medline, to collate relevant studies published from January 2018 to September 2023. The focus was on research detailing the application of DL in the context of obesity. We have distilled critical insights pertaining to the utilized learning models, encompassing aspects of their development, principal results, and foundational methodologies.

RESULTS

Our analysis culminated in the synthesis of new knowledge regarding the application of DL in the context of obesity. Finally, 40 research articles were included. The final collection of these research can be divided into three categories: obesity prediction (n = 16); obesity management (n = 13); and body fat estimation (n = 11).

CONCLUSIONS

This is the first review to examine DL applications in obesity. It reveals DL's superiority in obesity prediction over traditional ML methods, showing promise for multi-omics research. DL also innovates in obesity management through diet, fitness, and environmental analyses. Additionally, DL improves body fat estimation, offering affordable and precise monitoring tools. The study is registered with PROSPERO (ID: CRD42023475159).

The impact of smartphone app-based interventions on adolescents' dietary intake: a systematic review and evaluation of equity factor reporting in intervention studies

CONTEXT

Adolescence is a critical stage for improving nutrition. The popularity of smartphones makes them an ideal platform for administering interventions to adolescents. A systematic review has yet to assess the impact of smartphone app-based interventions exclusively on adolescents' dietary intake. Furthermore, despite the impact of equity factors on dietary intake and the claim for mobile health of increased accessibility, there is minimal research on the reporting of equity factors in the evaluation of smartphone app-based nutrition-intervention research.

OBJECTIVES

This systematic review examines the effectiveness of smartphone app-based interventions on adolescents' dietary intake and the frequency with which equity factors and statistical analyses specific to equity factors are reported in these intervention studies.

DATA SOURCES

Databases (ie, Scopus, CINAHL, EMBASE, MEDLINE, PsycINFO, ERIC, and Cochrane Central Register for Randomized Control Trials) were searched for studies published from January 2008 to October 2022. Smartphone app-based intervention studies that were nutrition focused, evaluated at least 1 dietary intake variable, and included participants with a mean age between 10 and 19 years were included. All geographic locations were included.

DATA EXTRACTION AND ANALYSIS

Study characteristics, intervention results, and reported equity factors were extracted. Because of the heterogeneity of dietary outcomes, findings were reported as a narrative synthesis.

CONCLUSION

In total, 3087 studies were retrieved, 14 of which met the inclusion criteria. Eleven studies reported a statistically significant improvement in at least 1 dietary outcome because of the intervention. Reporting of at least 1 equity factor across articles' Introduction, Methods, Results, and Discussion sections was minimal (n = 5), and statistical analyses specific to equity factors were rare, occurring in only 4 of the 14 included studies. Future interventions should include a measurement of intervention adherence and report the impact of equity factors on the effectiveness and applicability of interventions for equity-deserving groups.

A mobile healthy lifestyle intervention to promote mental health in adolescence: a mixed-methods evaluation

BACKGROUND

A healthy lifestyle may improve mental health. It is yet not known whether and how a mobile intervention can be of help in achieving this in adolescents. This study investigated the effectiveness and perceived underlying mechanisms of the mobile health (mHealth) intervention #LIFEGOALS to promote healthy lifestyles and mental health. #LIFEGOALS is an evidence-based app with activity tracker, including self-regulation techniques, gamification elements, a support chatbot, and health narrative videos.

METHODS

A quasi-randomized controlled trial (N = 279) with 12-week intervention period and process evaluation interviews (n = 13) took place during the COVID-19 pandemic. Adolescents (12-15y) from the general population were allocated at school-level to the intervention (n = 184) or to a no-intervention group (n = 95). Health-related quality of life (HRQoL), psychological well-being, mood, self-perception, peer support, resilience, depressed feelings, sleep quality and breakfast frequency were assessed via a web-based survey; physical activity, sedentary time, and sleep routine via Axivity accelerometers. Multilevel generalized linear models were fitted to investigate intervention effects and moderation by pandemic-related measures. Interviews were coded using thematic analysis.

RESULTS

Non-usage attrition was high: 18% of the participants in the intervention group never used the app. An additional 30% stopped usage by the second week. Beneficial intervention effects were found for physical activity (χ21 = 4.36, P = .04), sedentary behavior (χ21 = 6.44, P = .01), sleep quality (χ21 = 6.11, P = .01), and mood (χ21 = 2.30, P = .02). However, effects on activity-related behavior were only present for adolescents having normal sports access, and effects on mood only for adolescents with full in-school education. HRQoL (χ22 = 14.72, P < .001), mood (χ21 = 6.03, P = .01), and peer support (χ21 = 13.69, P < .001) worsened in adolescents with pandemic-induced remote-education. Interviewees reported that the reward system, self-regulation guidance, and increased health awareness had contributed to their behavior change. They also pointed to the importance of social factors, quality of technology and autonomy for mHealth effectiveness.

CONCLUSIONS

#LIFEGOALS showed mixed results on health behaviors and mental health. The findings highlight the role of contextual factors for mHealth promotion in adolescence, and provide suggestions to optimize support by a chatbot and narrative episodes.

TRIAL REGISTRATION

ClinicalTrials.gov [NCT04719858], registered on 22/01/2021.

Effectiveness of a Scalable mHealth Intervention for Children With Overweight and Obesity

Background: Multicomponent interventions are the first line of treatment for pediatric obesity, but are challenging to access. Mobile health (mHealth) interventions hold promise as they address commonly cited barriers for attending in person programs and have potential for wide scale dissemination. Methods: This retrospective cohort study examined data from youth who enrolled in the Kurbo program, which includes personal health coaching and a mobile app. Hierarchical linear regression was used to examine the impact of baseline percentage of the 95th% percentile for body mass index (%BMIp95), number of coaching sessions, and length of time enrolled in the program on change in %BMIp95, controlling for baseline age and sex. Results: A total of 3500 youth (mean age of 12.79 years, 71.3% female) were included. Youth experienced a 0.70 U decrease in BMI [standard deviation (SD) = 2.19] and a 4.45% decrease (SD = 8.5) in %BMIp95 over a mean of 31.5 weeks. The overall regression model was significant, R2 = 0.066, F(3,3494) = 77.18, and p < 0.001. Predictors of decrease in weight status included being female (b = -1.11, p < 0.001), higher baseline %BMIp95, (b = -0.58, p < 0.001), and greater number of coaching sessions (b = -0.12, p < 0.001), while greater time enrolled in the program (b = 0.02, p < 0.001) was associated with less change. Conclusion: Findings suggest a scalable coaching program with integrated digital tools for monitoring diet and activity can lead to significant reductions in weight status. Findings need to be replicated with more rigorous study designs, including a comparison condition and verified assessment of height and weight.

Exploring the Effect of the Dynamics of Behavioral Phenotypes on Health Outcomes in an mHealth Intervention for Childhood Obesity: Longitudinal Observational Study

BACKGROUND

Advancements in mobile health technologies and machine learning approaches have expanded the framework of behavioral phenotypes in obesity treatment to explore the dynamics of temporal changes.

OBJECTIVE

This study aimed to investigate the dynamics of behavioral changes during obesity intervention and identify behavioral phenotypes associated with weight change using a hybrid machine learning approach.

METHODS

In total, 88 children and adolescents (ages 8-16 years; 62/88, 71% male) with age- and sex-specific BMI ≥85th percentile participated in the study. Behavioral phenotypes were identified using a hybrid 2-stage procedure based on the temporal dynamics of adherence to the 5 behavioral goals during the intervention. Functional principal component analysis was used to determine behavioral phenotypes by extracting principal component factors from the functional data of each participant. Elastic net regression was used to investigate the association between behavioral phenotypes and weight change.

RESULTS

Functional principal component analysis identified 2 distinctive behavioral phenotypes, which were named the high or low adherence level and late or early behavior change. The first phenotype explained 47% to 69% of each factor, whereas the second phenotype explained 11% to 17% of the total behavioral dynamics. High or low adherence level was associated with weight change for adherence to screen time (β=-.0766, 95% CI -.1245 to -.0312), fruit and vegetable intake (β=.1770, 95% CI .0642-.2561), exercise (β=-.0711, 95% CI -.0892 to -.0363), drinking water (β=-.0203, 95% CI -.0218 to -.0123), and sleep duration. Late or early behavioral changes were significantly associated with weight loss for changes in screen time (β=.0440, 95% CI .0186-.0550), fruit and vegetable intake (β=-.1177, 95% CI -.1441 to -.0680), and sleep duration (β=-.0991, 95% CI -.1254 to -.0597).

CONCLUSIONS

Overall level of adherence, or the high or low adherence level, and a gradual improvement or deterioration in health-related behaviors, or the late or early behavior change, were differently associated with weight loss for distinctive obesity-related lifestyle behaviors. A large proportion of health-related behaviors remained stable throughout the intervention, which indicates that health care professionals should closely monitor changes made during the early stages of the intervention.

TRIAL REGISTRATION

Clinical Research Information Science KCT0004137; https://tinyurl.com/ytxr83ay.

Behavior Change Effectiveness Using Nutrition Apps in People With Chronic Diseases: Scoping Review

BACKGROUND

Cardiovascular disease, cancer, diabetes mellitus, and obesity are common chronic diseases, and their prevalence is reaching an epidemic level worldwide. As the impact of chronic diseases continues to increase, finding strategies to improve care, access to care, and patient empowerment becomes increasingly essential. Health care providers use mobile health (mHealth) to access clinical information, collaborate with care teams, communicate over long distances with patients, and facilitate real-time monitoring and interventions. However, these apps focus on improving general health care concerns, with limited apps focusing on specific chronic diseases and the nutrition involved in the disease state. Hence, available evidence on the effectiveness of mHealth apps toward behavior change to improve chronic disease outcomes is limited.

OBJECTIVE

The objective of this scoping review was to provide an overview of behavior change effectiveness using mHealth nutrition interventions in people with chronic diseases (ie, cardiovascular disease, diabetes mellitus, cancer, and obesity). We further evaluated the behavior change techniques and theories or models used for behavior change, if any.

METHODS

A scoping review was conducted through a systematic literature search in the MEDLINE, EBSCO, PubMed, ScienceDirect, and Scopus databases. Studies were excluded from the review if they did not involve an app or nutrition intervention, were written in a language other than English, were duplicates from other database searches, or were literature reviews. Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines, the systematic review process included 4 steps: identification of records through the database search, screening of duplicate and excluded records, eligibility assessment of full-text records, and final analysis of included records.

RESULTS

In total, 46 studies comprising 256,430 patients were included. There was diversity in the chronic disease state, study design, number of participants, in-app features, behavior change techniques, and behavior models used in the studies. In addition, our review found that less than half (19/46, 41%) of the studies based their nutrition apps on a behavioral theory or its constructs. Of the 46 studies, 11 (24%) measured maintenance of health behavior change, of which 7 (64%) sustained behavior change for approximately 6 to 12 months and 4 (36%) showed a decline in behavior change or discontinued app use.

CONCLUSIONS

The results suggest that mHealth apps involving nutrition can significantly improve health outcomes in people with chronic diseases. Tailoring nutrition apps to specific populations is recommended for effective behavior change and improvement of health outcomes. In addition, some studies (7/46, 15%) showed sustained health behavior change, and some (4/46, 9%) showed a decline in the use of nutrition apps. These results indicate a need for further investigation on the sustainability of the health behavior change effectiveness of disease-specific nutrition apps.