RESUMEN
BACKGROUND: Cardiovascular disease (CVD) is the leading cause of death in the United States, affecting a significant proportion of adults. Digital health lifestyle change programs have emerged as a promising method of CVD prevention, offering benefits such as on-demand support, lower cost, and increased scalability. Prior research has shown the effectiveness of digital health interventions in reducing negative CVD outcomes. This pilot study focuses on the Lark Heart Health program, a fully digital artificial intelligence (AI)-powered smartphone app, providing synchronous CVD risk counseling, educational content, and personalized coaching. OBJECTIVE: This pilot study evaluated the feasibility and acceptability of a fully digital AI-powered lifestyle change program called Lark Heart Health. Primary analyses assessed (1) participant satisfaction, (2) engagement with the program, and (3) the submission of health screeners. Secondary analyses were conducted to evaluate weight loss outcomes, given that a major focus of the Heart Health program is weight management. METHODS: This study enrolled 509 participants in the 90-day real-world single-arm pilot study of the Heart Health app. Participants engaged with the app by participating in coaching conversations, logging meals, tracking weight, and completing educational lessons. The study outcomes included participant satisfaction, app engagement, the completion of screeners, and weight loss. RESULTS: On average, Heart Health study participants were aged 60.9 (SD 10.3; range 40-75) years, with average BMI indicating class I obesity. Of the 509 participants, 489 (96.1%) stayed enrolled until the end of the study (dropout rate: 3.9%). Study retention, based on providing a weight measurement during month 3, was 80% (407/509; 95% CI 76.2%-83.4%). Participant satisfaction scores indicated high satisfaction with the overall app experience, with an average score of ≥4 out of 5 for all satisfaction indicators. Participants also showed high engagement with the app, with 83.4% (408/489; 95% CI 80.1%-86.7%) of the sample engaging in ≥5 coaching conversations in month 3. The results indicated that participants were successfully able to submit health screeners within the app, with 90% (440/489; 95% CI 87%-92.5%) submitting all 3 screeners measured in the study. Finally, secondary analyses showed that participants lost weight during the program, with analyses showing an average weight nadir of 3.8% (SD 2.9%; 95% CI 3.5%-4.1%). CONCLUSIONS: The study results indicate that participants in this study were satisfied with their experience using the Heart Health app, highly engaged with the app features, and willing and able to complete health screening surveys in the app. These acceptability and feasibility results provide a key first step in the process of evidence generation for a new AI-powered digital program for heart health. Future work can expand these results to test outcomes with a commercial version of the Heart Health app in a diverse real-world sample.
RESUMEN
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.
