Evaluating a New Digital App–Based Program for Heart Health: Feasibility and Acceptability Pilot Study
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.011 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".