Predictors of Program Interest in a Digital Health Pilot Study for Heart Health

Kimberly G. Lockwood, Viveka Pitter, Priya R. Kulkarni, Sarah A. Graham, Lisa A. Auster-Gussman, OraLee H. Branch


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.


Cardiovascular disease (CVD) is the most common health condition in the United States, with 126.9 million adults (49.2% of adults ≥20 years) living with CVD [1]. As the leading cause of death in the US and other developed nations, CVD poses substantial public health and economic burdens [1,2] making prevention and risk reduction top priorities. Importantly, CVD can be prevented or significantly reduced by maintaining a healthy lifestyle [3,4]. Behavioral interventions targeting healthy lifestyle behaviors play a critical role in preventing and managing CVD risk, as recognized by the US Preventive Services Task Force [5–7]. Traditionally, these interventions have been delivered in person [6] or via telephone [8]. However, with the rise of technology and smartphone usage, digital health programs have emerged as a convenient and accessible alternative for managing cardiovascular health [9].

Materials and method

Data for these analyses were drawn from a real-world, non-interventional, single-arm, observational pilot study of a digital health app-based program called Lark Heart Health, which provides low-risk health behavior surveys and coaching. The study is 3-months (90 days) in duration for each participant. This pilot focuses on feasibility of deploying screener surveys and user acceptability of coaching to improve knowledge and self-management of ASCVD risk. This acceptability and feasibility pilot study received approval from Advarra Institutional Review Board (protocol Pro00061694). Appropriate safeguards were taken to prevent any unauthorized use or disclosure of personal health information and to implement the administrative, physical, and technical safeguards to protect the confidentiality, integrity, and availability of protected health information. Lark is compliant with HIPAA Privacy and Security rules and all applicable regulations. Additionally, Lark is SOC2 and HITRUST certified.


Descriptive statistics for each of the EHR variables are shown in Table 2. On average, individuals in the EHR dataset were 66.1 years old (median = 68.8, range = 39.9–76.3) and approximately half of the individuals were male. The majority of the individuals identified as White (59.3%), with Hispanic/Latino individuals comprising 10% of the dataset, but nearly a quarter did not provide their race or ethnicity (24%). According to average BMI, individuals in the dataset were borderline obese (M = 30.3 kg/m2, median = 29.3 kg/m2, range = 18.0–59.8). Notably, almost two thirds of the individuals in the dataset had a diagnosis of hypertension and approximately 96% of individuals had at least one elevated lab value.


This is the first report from the ongoing Heart Health pilot study, in which we explored factors predicting interest in a digital health lifestyle change program for cardiovascular health. BMI, number of elevated lab values, HbA1c, smoking status, and race all emerged as key predictors of interest. Conversely, sex, age, history of CVD, history of diabetes, history of kidney issues, and medication use were not predictors of interest. This finding indicates that this fully digital Heart Health program may be equally appealing to both males and females, to adults across various age groups, and to individuals both with and without a history of cardiac and other chronic health issues. Taken together, these results contribute to the growing body of knowledge on the characteristics of those interested in digital health programs and provide insight into groups who could benefit from such programs but may need additional recruitment efforts.


In conclusion, our findings contribute to understanding the characteristics of individuals interested in a prevention-focused, digital health program for heart health. We found higher interest among individuals with higher BMI, those with fewer elevated lab values and lower A1c, nonsmokers, and White individuals. Additionally, we found that there was no significant difference in program interest based on sex, age, history of cardiovascular and other chronic health issues, proxy ASCVD score, number of medications, and use of different types of medications for CVD risk or diabetes.


The authors would like to thank our study participants for taking part in this important research and acknowledge contributions from the Lark Heart Health clinical study team that designed the Heart Health application, collected and processed data, and provided support to our research participants.

Citation: Lockwood KG, Pitter V, Kulkarni PR, Graham SA, Auster-Gussman LA, Branch OH (2023) Predictors of program interest in a digital health pilot study for heart health. PLOS Digit Health 2(7): e0000303.

Editor: Haleh Ayatollahi, Iran University of Medical Sciences, IRAN (ISLAMIC REPUBLIC OF)

Received: January 31, 2023; Accepted: June 19, 2023; Published: July 31, 2023

Copyright: © 2023 Lockwood et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Data Availability: The dataset referenced in this manuscript cannot be made publicly available. The data used for these analyses include sensitive, potentially identifiable information that was obtained through a collaboration between Lark Health and its healthcare partners. Please send any data-related requests to the Lark Health clinical advisory council via email to

Funding: The Heart Health pilot study was supported by funds from Roche Information Solutions and Lark Health, with OHLB as the principal investigator and KGL and SAG as co-investigators. Employees of the funding organizations were involved in study design, data collection and analysis, decision to publish, and preparation of the manuscript. KGL, VP, SAG, LAG, and OLHB received salary from Lark Health. PRK received salary from Roche Information Solutions.

Competing interests: I have read the journal’s policy and authors of this manuscript have the following competing interest: KGL, VP, SAG, LAG, and OLHB were employees of Lark Health at the time of manuscript development. PRK is an employee of Roche Information Solutions.


The GIANT Health Event 2023National Healthcare CMO Summit USANational Healthcare CNO Summit USA