Engagement in Digital Health App-Based Prevention Programs Is Associated With Weight Loss Among Adults Age 65+

Effectiveness of artificial intelligence vs. human coaching in diabetes prevention: a study protocol for a randomized controlled trial

BACKGROUND

Prediabetes is a highly prevalent condition that heralds an increased risk of progression to type 2 diabetes, along with associated microvascular and macrovascular complications. The Diabetes Prevention Program (DPP) is an established effective intervention for diabetes prevention. However, participation in this 12-month lifestyle change program has historically been low. Digital DPPs have emerged as a scalable alternative, accessible asynchronously and recognized by the Centers for Disease Control and Prevention (CDC). Yet, most digital programs still incorporate human coaching, potentially limiting scalability. Furthermore, existing effectiveness results of digital DPPs are primarily derived from per protocol, longitudinal non-randomized studies, or comparisons to control groups that do not represent the standard of care DPP. The potential of an AI-powered DPP as an alternative to the DPP is yet to be investigated. We propose a randomized controlled trial (RCT) to directly compare these two approaches.

METHODS

This open-label, multicenter, non-inferiority RCT will compare the effectiveness of a fully automated AI-powered digital DPP (ai-DPP) with a standard of care human coach-based DPP (h-DPP). A total of 368 participants with elevated body mass index (BMI) and prediabetes will be randomized equally to the ai-DPP (smartphone app and Bluetooth-enabled body weight scale) or h-DPP (referral to a CDC recognized DPP). The primary endpoint, assessed at 12 months, is the achievement of the CDC's benchmark for type 2 diabetes risk reduction, defined as any of the following: at least 5% weight loss, at least 4% weight loss and at least 150 min per week on average of physical activity, or at least a 0.2-point reduction in hemoglobin A1C. Physical activity will be objectively measured using serial actigraphy at baseline and at 1-month intervals throughout the trial. Secondary endpoints, evaluated at 6 and 12 months, will include changes in A1C, weight, physical activity measures, program engagement, and cost-effectiveness. Participants include adults aged 18-75 years with laboratory confirmed prediabetes, a BMI of ≥ 25 kg/m2 (≥ 23 kg/m2 for Asians), English proficiency, and smartphone users. This U.S. study is conducted at Johns Hopkins Medicine in Baltimore, MD, and Reading Hospital (Tower Health) in Reading, PA.

DISCUSSION

Prediabetes is a significant public health issue, necessitating scalable interventions for the millions affected. Our pragmatic clinical trial is unique in directly comparing a fully automated AI-powered approach without direct human coach interaction. If proven effective, it could be a scalable, cost-effective strategy. This trial will offer vital insights into both AI and human coach-based behavioral change strategies in real-world clinical settings.

TRIAL REGISTRATION

ClinicalTrials.gov NCT05056376. Registered on September 24, 2021, https://clinicaltrials.gov/study/NCT05056376.

A Digitally Enabled Combined Lifestyle Intervention for Weight Loss: Pilot Study in a Dutch General Population Cohort

BACKGROUND

Overweight and obesity rates among the general population of the Netherlands keep increasing. Combined lifestyle interventions (CLIs) focused on physical activity, nutrition, sleep, and stress management can be effective in reducing weight and improving health behaviors. Currently available CLIs for weight loss (CLI-WLs) in the Netherlands consist of face-to-face and community-based sessions, which face scalability challenges. A digitally enabled CLI-WL with digital and human components may provide a solution for this challenge; however, the feasibility of such an intervention has not yet been assessed in the Netherlands.

OBJECTIVE

The aim of this study was two-fold: (1) to determine how weight and other secondary cardiometabolic outcomes (lipids and blood pressure) change over time in a Dutch population with overweight or obesity and cardiometabolic risk participating in a pilot digitally enabled CLI-WL and (2) to collect feedback from participants to guide the further development of future iterations of the intervention.

METHODS

Participants followed a 16-week digitally enabled lifestyle coaching program rooted in the Fogg Behavior Model, focused on nutrition, physical activity, and other health behaviors, from January 2020 to December 2021. Participants could access the digital app to register and track health behaviors, weight, and anthropometrics data at any time. We retrospectively analyzed changes in weight, blood pressure, and lipids for remeasured users. Surveys and semistructured interviews were conducted to assess critical positive and improvement points reported by participants and health care professionals.

RESULTS

Of the 420 participants evaluated at baseline, 53 participated in the pilot. Of these, 37 (70%) were classified as overweight and 16 (30%) had obesity. Mean weight loss of 4.2% occurred at a median of 10 months postintervention. The subpopulation with obesity (n=16) showed a 5.6% weight loss on average. Total cholesterol decreased by 10.2% and low-density lipoprotein cholesterol decreased by 12.9% on average. Systolic and diastolic blood pressure decreased by 3.5% and 7.5%, respectively. Participants identified the possibility of setting clear action plans to work toward and the multiple weekly touch points with coaches as two of the most positive and distinctive components of the digitally enabled intervention. Surveys and interviews demonstrated that the digital implementation of a CLI-WL is feasible and well-received by both participants and health care professionals.

CONCLUSIONS

Albeit preliminary, these findings suggest that a behavioral lifestyle program with a digital component can achieve greater weight loss than reported for currently available offline CLI-WLs. Thus, a digitally enabled CLI-WL is feasible and may be a scalable alternative to offline CLI-WL programs. Evidence from future studies in a Dutch population may help elucidate the mechanisms behind the effectiveness of a digitally enabled CLI-WL.

Exploring the benefits and costs of a growth mindset in a digital app weight management program

We explored the potential benefits and costs of believing one can change their weight (i.e. growth mindset) in the context of a digital weight management program. We investigated mechanisms by which growth mindsets relate to weight loss achievement and body shame. Among participants seeking to lose weight (N = 1626; 74.7% female; 77.9% White; Mage = 45.7), stronger growth mindsets indirectly predicted greater weight loss achievement through positive offset expectations and subsequent increased program engagement. Additionally, stronger growth mindsets predicted less body shame through positive offset expectations but predicted more body shame through increased onset responsibility, replicating the double-edged sword model of growth mindsets. We conclude with applications that leverage growth mindsets for optimal behavior change while mitigating costs such as body shame.

The Efficacy of an mHealth App in Facilitating Weight Loss Among Japanese Fitness Center Members: Regression Analysis Study

BACKGROUND

Self-tracking smartphone apps have emerged as promising tools to encourage healthy behaviors. In this longitudinal study, we used gym use data from members of a major fitness club that operates gyms throughout Japan from January 2014 to December 2019.

OBJECTIVE

Our objective was to assess the extent to which a health and fitness self-tracking mobile app introduced to gym members on January 1, 2018, contributed to their weight loss. The app allows users to input information regarding diet, sleep, weight, and gym exercise so that they can receive personalized feedback from an artificial intelligence chatbot to improve their health behaviors.

METHODS

We used linear regression to quantify the association between app use and weight loss. The primary outcome of the study was the weight loss achieved by each gym user, which was calculated as the difference between their initial and final weights in kilograms, as recorded in the app. Individuals who did not attend the gym or failed to use the mobile app at least twice during the study period were excluded from the analysis. The model accounted for age, gender, distance between the gym and the member's residence, average weekly number of times a member used the gym, user's gym membership length in weeks, average weekly number of times a member input information into the app, and the number of weeks that the app was used at least once.

RESULTS

Data from 26,589 participants were analyzed. Statistically significant associations were detected between weight loss and 2 metrics related to app use: the average weekly frequency of use and the total number of weeks in which the app was used at least once. One input per week was found to be associated with a loss of 62.1 (95% CI 53.8-70.5) g, and 1 week of app use was associated with 21.7 (95% CI 20.5-22.9) g of weight loss from the day of the first input to that of the final input to the app. Furthermore, the average number of times that a member used the gym weekly was also shown to be statistically significantly associated with weight loss: 1 use per week was associated with 255.5 (95% CI 228.5-282.6) g of weight loss.

CONCLUSIONS

This empirical study demonstrated a significant association between weight loss among gym members and not only the frequency of weekly gym use but also the use of a health and fitness self-tracking app. However, further work is needed to examine the mechanisms through which mobile apps affect health behaviors and to identify the specific app features that are most effective in promoting weight loss.

Predictors of program interest in a digital health pilot study for heart health

Digital health programs can play a key role in supporting lifestyle changes to prevent and reduce cardiovascular disease (CVD) risk. A key concern for new programs is understanding who is interested in participating. Thus, the primary objective of this study was to utilize electronic health records (EHR) to predict interest in a digital health app called Lark Heart Health. Because prior studies indicate that males are less likely to utilize prevention-focused digital health programs, secondary analyses assessed sex differences in recruitment and enrollment. Data were drawn from an ongoing pilot study of the Heart Health program, which provides digital health behavior coaching and surveys for CVD prevention. EHR data were used to predict whether potential program participants who received a study recruitment email showed interest in the program by "clicking through" on the email to learn more. Primary objective analyses used backward elimination regression and eXtreme Gradient Boost modeling. Recruitment emails were sent to 8,649 patients with available EHR data; 1,092 showed interest (i.e., clicked through) and 345 chose to participate in the study. EHR variables that predicted higher odds of showing interest were higher body mass index (BMI), fewer elevated lab values, lower HbA1c, non-smoking status, and identifying as White. Secondary objective analyses showed that, males and females showed similar program interest and were equally represented throughout recruitment and enrollment. In summary, BMI, elevated lab values, HbA1c, smoking status, and race emerged as key predictors of program interest; conversely, sex, age, CVD history, history of chronic health issues, and medication use did not predict program interest. We also found no sex differences in the recruitment and enrollment process for this program. These insights can aid in refining digital health tools to best serve those interested, as well as highlight groups who may benefit from behavioral intervention tools promoted by additional recruitment efforts tailored to their interest.

Mapping digital health ecosystems in Africa in the context of endemic infectious and non-communicable diseases

Investments in digital health technologies such as artificial intelligence, wearable devices, and telemedicine may support Africa achieve United Nations (UN) Sustainable Development Goal for Health by 2030. We aimed to characterize and map digital health ecosystems of all 54 countries in Africa in the context of endemic infectious and non-communicable diseases (ID and NCD). We performed a cross-national ecological analysis of digital health ecosystems using 20-year data from the World Bank, UN Economic Commission for Africa, World Health Organization, and Joint UN Programme on HIV/AIDS. Spearman's rank correlation coefficients were used to characterize ecological correlations between exposure (technology characteristics) and outcome (IDs and NCDs incidence/mortality) variables. Weighted linear combination model was used as the decision rule, combining disease burden, technology access, and economy, to explain, rank, and map digital health ecosystems of a given country. The perspective of our analysis was to support government decision-making. The 20-year trend showed that technology characteristics have been steadily growing in Africa, including internet access, mobile cellular and fixed broadband subscriptions, high-technology manufacturing, GDP per capita, and adult literacy, while many countries have been overwhelmed by a double burden of IDs and NCDs. Inverse correlations exist between technology characteristics and ID burdens, such as fixed broadband subscription and incidence of tuberculosis and malaria, or GDP per capita and incidence of tuberculosis and malaria. Based on our models, countries that should prioritize digital health investments were South Africa, Nigeria, and Tanzania for HIV; Nigeria, South Africa, and Democratic Republic of the Congo (DROC) for tuberculosis; DROC, Nigeria, and Uganda for malaria; and Egypt, Nigeria, and Ethiopia for endemic NCDs including diabetes, cardiovascular disease, respiratory diseases, and malignancies. Countries such as Kenya, Ethiopia, Zambia, Zimbabwe, Angola, and Mozambique were also highly affected by endemic IDs. By mapping digital health ecosystems in Africa, this study provides strategic guidance about where governments should prioritize digital health technology investments that require preliminary analysis of country-specific contexts to bring about sustainable health and economic returns. Building digital infrastructure should be a key part of economic development programs in countries with high disease burdens to ensure more equitable health outcomes. Though infrastructure developments alongside digital health technologies are the responsibility of governments, global health initiatives can cultivate digital health interventions substantially by bridging knowledge and investment gaps, both through technology transfer for local production and negotiation of prices for large-scale deployment of the most impactful digital health technologies.

Weight Loss in a Digital Diabetes Prevention Program for People in Health Professional Shortage and Rural Areas

Individuals with prediabetes living in hard-to-reach and underserved areas experience barriers to accessing traditional in-person preventive health services. The National Diabetes Prevention Program (DPP) is a preventive health care program designed to reduce the risk of developing type 2 diabetes. Although there have been increasing numbers of remote DPPs accessible, there are little data on the clinical outcomes of digital DPPs for members living in hard-to-reach and underserved areas. This study assessed whether living in a designated Health Professional Shortage Area (HPSA) and a rural versus urban area impacted the weight loss of N = 7266 members of a fully digital program called Lark DPP. Secondary analyses included between-group comparisons of program retention and member characteristics, demographics, and socioeconomics. Percent weight loss did not differ by HPSA (P = 0.16) or rural/urban status (P = 0.15), despite greater potential barriers for members residing in HPSAs (eg, highest starting body mass index, lowest income, lowest education). Mean percent weight loss for members residing in an HPSA and rural area was mean (M) = 4.75%, standard error (SE) = 0.09; for members in a non-HPSA, rural area M = 4.96%, SE = 0.16; for members in an HPSA, urban area M = 4.55%, SE = 0.13; and for members in a non-HPSA, urban area M = 4.77%, SE = 0.13. Members of a fully digital DPP achieved weight loss that did not differ by HPSA or urban/rural designation. Fully digital programs offer a solution to reduce the risk of type 2 diabetes in areas where residents may not otherwise have access to diabetes prevention services.

Facilitating engagement of universal school-based digital mental health solutions through user experience: A qualitative exploration

Digital mental health intervention (DMHI) programs offered in schools present a readily-accessible and flexible means for educating, empowering, and supporting adolescents in maintaining a balanced mental health, especially during uncertain and stressful times such as the COVID-19 pandemic. Recent studies indicate that the effectiveness of DMHI programs in improving students' mental well-being and in preventing from their mental health complications depends on the users' engagement. This study focuses on identifying the user experience factors that can facilitate user engagement with universal school-based DMHI programs (i.e., the DMHI programs delivered to the students regardless of their mental health risks or conditions). To identify said factors, we sought to gain a deeper understanding of perceptions, opinions, and preferences of actual end-users (i.e., the adolescents) regarding their experiences with both digital and non-digital mental health resources. Specifically, interviews were conducted with two participant groups to uncover the reasons that could lead the adolescents to better engage with school-based DMHI programs, as well as the shortcomings that could prevent that from happening: (a) adolescent users who had either a high or a low level of engagement with universal DMHI programs of a specific school-based digital mental health solution; and (b) adolescents who had voluntarily used non-digital or non-school-based digital mental health resources for purposes other than treatment. Through a thematic analysis of interview data, the most important (or primary) and the additionally desirable (or secondary) factors that could lead to a higher engagement level for school-based DMHI programs were identified. Lastly, using the evidence gathered from our interviews, specific recommendations are proposed that could help in targeting each identified engagement factor and in increasing the likelihood that school-based DMHI programs achieve their desired outcome for high school students.

Behavioral Patterns of Supply and Demand Sides of Health Services for the Elderly in Sustainable Digital Transformation: A Mixed Methods Study

The aging transformation of digital health services faces issues of how to distinguish influencing factors, redesign services, and effectively promote measures and policies. In this study, in-depth interviews were conducted, and grounded theory applied to open coding, main axis coding, and selective coding to form concepts and categories. Trajectory equifinality modeling clarified the evolution logic of digital transformation. Based on the theory of service ecology, a digital health service aging model was constructed from the “macro–medium–micro” stages and includes governance, service, and technology transformation paths. The macro stage relies on organizational elements to promote the institutionalization of management and guide the transformation of governance for value realization, including the construction of three categories: mechanism, indemnification, and decision-making. The meso stage relies on service elements to promote service design and realize service transformation that is suitable for aging design, including the construction of three categories: organization, resources, and processes. The micro stage relies on technical elements to practice experiencing humanization, including the construction of three categories: target, methods, and evaluation. These results deepen the understanding of the main behaviors and roles of macro-organizational, meso-service, and micro-technical elements in digital transformation practice and have positive significance for health administrative agencies to implement action strategies.