Digital health technology provides opportunities to leverage artificial intelligence and other digital applications to promote cardiovascular health. Digital health technologies include artificial intelligence (such as machine learning [ML], neural networks),1 analytic systems, mobile apps, wearables, email, text messaging, and telemedicine.2 In this article, we review the role of digital technology in cardiovascular health and a selection of recent studies to evaluate the evidence of its effectiveness.

Artificial intelligence is broadly defined as the capability of computer systems to perform tasks similar to humans.3 Examples include vision, speech, pattern recognition, and decision making. Machine learning is the ability of the computer program to learn from experience. This typically occurs from analysis of large sets of data processed through human-derived algorithms to enhance, predict, and explain outcomes.4 An example of the use of ML in clinical care is cardiovascular disease (CVD) prediction and electrocardiographic interpretation. Neural networks, named after the human nervous system, are nonlinear statistic models that control where signals are sent. Neural networks can be used for decision making such as cardiovascular diagnosis confirmation.

Digital Technology Use in Cardiovascular Risk Assessment

Several studies have demonstrated improved CVD risk factor identification using ML compared with traditional risk assessment tools. Researchers developed an ML risk calculator and compared it with the American College of Cardiology/American Heart Association CVD risk calculator in 6459 participants from the Multi-Ethnic Study of Atherosclerosis.5 Study participants were free of CVD at baseline and followed for 13 years. Results revealed that the American College of Cardiology/American Heart Association risk calculator was less precise: statin therapy was recommended to 46% of the sample, with 23.8% of CVD events occurring in those not recommended a statin. In comparison, the ML risk calculator recommended a statin to 11% of the sample, with 14.4% of CVD events occurring in those not recommended a statin.5 Similarly in 3 cohorts from Australia, 4 ML models were developed and compared with the 2008 Framingham model. The ML models provided 2.7% to 5.2% better predictions across all 3 cohorts.6 Taken together, the authors of these studies suggest ML provides promise in providing more precise estimates of CVD risk.

Digital Health Interventions for Cardiovascular Disease Prevention

Digital health interventions have the potential to provide a personalized approach to promote cardiovascular health. Behavior change theory is a key component of digital interventions and includes theoretical frameworks such as supportive accountability,7 self-efficacy theory,8 social cognitive theory, and the health belief model.9 Precision healthcare has been promoted for decades. Many of the challenges in operationalizing precision healthcare are healthcare accessibility, scheduling, care continuity, and inadequate knowledge exchange between provides and patients.10 Thus, promotion of healthy lifestyles and lifestyle risk factor reduction remain inadequately addressed in patients with CVD.11 To achieve sustainable change, individual-level personalized strategies may be leveraged through digital health interventions.

Evidence of the effectiveness of digital health interventions has varied but is promising overall. Text messaging has been successfully used to provide information regarding healthy diet and physical activity recommendations, monitoring, and individual feedback. Text messaging has resulted in improvements in diet and activity in many (TextMe,12 Mobile MyPlate,13 MyQuest,14 Text-To-Move15), but not all studies.16

Smartphone/mobile apps have been designed to improve dietary and physical activity behavior. Examples include apps that track dietary patterns and activity through user input of text or visual images.17,18 Users can set their own goals and receive feedback on progress toward goals. Reviews of smartphone apps have had variable results with many demonstrating short-term improvement. Villinger et al19 conducted a systematic review and meta-analysis of the effectiveness of mobile app interventions on nutrition behaviors (41 studies, 27 randomized controlled trials [RCTs]). Findings revealed significantly improved nutrition behaviors and nutrition-related outcomes (P = .004 and P = .043, respectively). A second systematic review of 27, primarily RCTs, found significant between-group improvements in 19 of the 27 studies.20 A meta-analysis of 6 RCTs in adults using a smartphone app as the primary component of the intervention revealed a trend for more steps per day in the intervention compared with the control groups, with programs lasting less than 3 months more effective than longer programs.21 Taken together, text messaging and smartphone/mobile apps have the potential to improve lifestyle behaviors associated with cardiovascular health. The addition of strategies to increase sustainability of the effects needs to be assessed.

Digital Health Interventions: Primary and Secondary Prevention

Widmer et al2 conducted a meta-analysis of 51 RCTs and cohort studies using digital health interventions for the prevention of CVD events and risk factor modification. Subgroup analyses of primary prevention studies (2 studies) did not provide evidence of a statistically significant reduction in CVD outcomes. However, evaluation of individual risk factors in primary prevention studies found a significant reduction in weight (11 studies; −3.35 lb), systolic blood pressure (23 studies; mean difference, −2.12 mm Hg), total cholesterol (13 studies; mean difference, −5.19 mg/dL), low-density lipoprotein cholesterol (8 studies; mean difference, −4.96 mg/dL), and glucose (6 studies; mean difference, −1.38 mg/dL).2 A subgroup analysis of secondary prevention studies demonstrated a significant impact of digital interventions on CVD outcomes (relative risk, 0.60; a 40% relative risk reduction), improvement in body mass index (6 studies; mean difference, −0.31 kg/m2) but no improvement in weight, systolic blood pressure, total cholesterol, low-density lipoprotein cholesterol, and glucose. Taken together, this meta-analysis suggested that digital interventions were beneficial not only in lowering CVD events in higher-risk patients but also in lowering risk factors in primary prevention approaches.2

In a second meta-analysis conducted by Akinosun et al,11 researchers analyzed 25 RCTs in patients with traditional CVD risk factors who received a digital intervention versus usual care.11 Findings revealed benefits in total cholesterol (mean difference, −0.29), high-density lipoprotein cholesterol (mean difference, −0.09), low-density lipoprotein (mean difference, 0.18), physical activity (mean difference 0.23), physical inactivity (relative risk, 0.54), and diet (relative risk, 0.79). There was no significant improvement in body mass index, systolic and diastolic blood pressure, hemoglobin A1C, alcohol intake, smoking, and medication adherence. Authors concluded that digital interventions were more effective at improving healthy behaviors than reducing unhealthy behaviors.

In patients who experienced a myocardial infarction, a digital health intervention providing medication reminders, vital sign and activity tracking, education, and outpatient care coordination resulted in a 52% lower 30-day readmission rate compared with usual care.22 Sociodemographic characteristics (age, sex, and race) did not influence use of the digital intervention, highlighting a potential role for digital interventions in the promotion of equity in social determinants of health.23

Digital Health Interventions in Cardiac Rehabilitation

Cardiac rehabilitation is an essential component of secondary prevention of CVD.24 Some patients face barriers in participation in cardiac rehabilitation due to physical accessibility, time, and travel.25 Digital health interventions have the potential to bridge these barriers and increase participation. Digital delivery of cardiac rehabilitation therapy with real-time personalized support has several advantages.26 In a systematic review of 31 studies in which authors examined digital health interventions for cardiac rehabilitation, the results revealed that cardiac rehabilitation program adherence was greater in patients using digital interventions than traditional methods alone. Secondary benefits were found in self-efficacy, weight management, diet, and quality of life. Taken together, digital cardiac rehabilitation was feasible and effective whether used alone or in combination with traditional cardiac rehabilitation.26

Conclusion

Digital health technology is an evolving field with tremendous potential to improve cardiovascular health. Cardiovascular disease remains the major cause of death in the United States. The age-adjusted mortality rate has increased in the last decade. More people died from CVD causes in 2020 (nearly 900 000 deaths) than any year since 2003.27 Opportunities to reduce CVD and CVD risk have not been fully leveraged, and digital technology interventions have the potential to meet this need. Digital health technology also has the potential to provide equitable and personalized care. Device data, electronic medical record data, and social determinants of health data provide an opportunity to combine and identify longitudinal trends and risk factors before CVD begins. In the future, large data sets can be created that can be analyzed using ML to identify patterns and structures within and among the data to provide a more robust risk assessment to promote CVD prevention.

REFERENCES 1. Robert N. How artificial intelligence is changing nursing. Nurs Manage. 2019;50(9):30–39. 2. Widmer RJ, Collins NM, Collins CS, West CP, Lerman LO, Lerman A. Digital health interventions for the prevention of cardiovascular disease: a systematic review and meta-analysis. Mayo Clin Proc. 2015;90(4):469–480. 3. Oxford English Dictionary. Oxford, England: Oxford University Press; 2023. 4. Mintz Y, Brodie R. Introduction to artificial intelligence in medicine. Minim Invasive Ther Allied Technol. 2019;28(2):73–81. 5. Kakadiaris IA, Vrigkas M, Yen AA, Kuznetsova T, Budoff M, Naghavi M. Machine learning outperforms ACC/AHA CVD risk calculator in MESA. J Am Heart Assoc. 2018;7(22):e009476. 6. Sajeev S, Champion S, Beleigoli A, et al. Predicting Australian adults at high risk of cardiovascular disease mortality using standard risk factors and machine learning. Int J Environ Res Public Health. 2021;18(6):3187. 7. Mohr DC, Cuijpers P, Lehman K. Supportive accountability: a model for providing human support to enhance adherence to eHealth interventions. J Med Internet Res. 2011;13(1):e30. 8. Hong PC, Chen KJ, Chang YC, Cheng SM, Chiang HH. Effectiveness of theory-based health information technology interventions on coronary artery disease self-management behavior: a clinical randomized waitlist-controlled trial. J Nurs Scholarsh. 2021;53(4):418–427. 9. Brewer LC, Hayes SN, Caron AR, et al. Promoting cardiovascular health and wellness among African-Americans: community participatory approach to design an innovative mobile-health intervention. PloS One. 2019;14(8):e0218724. 10. Brunner-La Rocca HP, Fleischhacker L, Golubnitschaja O, et al. Challenges in personalised management of chronic diseases—heart failure as prominent example to advance the care process. EPMA J. 2015;7:2. doi:10.1186/s13167-016-0051-9. Accessed 2015. 11. Akinosun AS, Polson R, Diaz-Skeete Y, et al. Digital technology interventions for risk factor modification in patients with cardiovascular disease: systematic review and Meta-analysis. JMIR Mhealth Uhealth. 2021;9(3):e21061. 12. Santo K, Hyun K, de Keizer L, et al. The effects of a lifestyle-focused text-messaging intervention on adherence to dietary guideline recommendations in patients with coronary heart disease: an analysis of the TEXT ME study. Int J Behav Nutr Phys Act. 2018;15(1):45. 13. Brown ON, O'Connor LE, Savaiano D. Mobile MyPlate: a pilot study using text messaging to provide nutrition education and promote better dietary choices in college students. J Am Coll Health. 2014;62(5):320–327. 14. Griffin JB, Struempler B, Funderburk K, Parmer SM, Tran C, Wadsworth DD. My Quest, an intervention using text messaging to improve dietary and physical activity behaviors and promote weight loss in low-income women. J Nutr Educ Behav. 2018;50(1):11–18.e11. 15. Agboola S, Jethwani K, Lopez L, Searl M, O'Keefe S, Kvedar J. Text to move: a randomized controlled trial of a text-messaging program to improve physical activity behaviors in patients with type 2 diabetes mellitus. J Med Internet Res. 2016;18(11):e307. 16. Klimis H, Thiagalingam A, McIntyre D, Marschner S, Von Huben A, Chow CK. Text messages for primary prevention of cardiovascular disease: the TextMe2 randomized clinical trial. Am Heart J. 2021;242:33–44. 17. Ferrara G, Kim J, Lin S, Hua J, Seto E. A focused review of smartphone diet-tracking apps: usability, functionality, coherence with behavior change theory, and comparative validity of nutrient intake and energy estimates. JMIR Mhealth Uhealth. 2019;7(5):e9232. 18. Liu YC, Chen CH, Lee CW, et al. Design and usability evaluation of user-centered and visual-based aids for dietary food measurement on mobile devices in a randomized controlled trial. J Biomed Inform. 2016;64:122–130. 19. Villinger K, Wahl DR, Boeing H, Schupp HT, Renner B. The effectiveness of app-based mobile interventions on nutrition behaviours and nutrition-related health outcomes: a systematic review and meta-analysis. Obes Rev. 2019;20(10):1465–1484. 20. Schoeppe S, Alley S, Van Lippevelde W, et al. Efficacy of interventions that use apps to improve diet, physical activity and sedentary behaviour: a systematic review. Int J Behav Nutr Phys Act. 2016;13(1):127. 21. Romeo A, Edney S, Plotnikoff R, et al. Can smartphone apps increase physical activity? Systematic review and meta-analysis. J Med Internet Res. 2019;21(3):e12053. 22. Marvel FA, Spaulding EM, Lee MA, et al. Digital health intervention in acute myocardial infarction. Circ Cardiovasc Qual Outcomes. 2021;14(7):e007741. 23. Shah LM, Ding J, Spaulding EM, et al. Sociodemographic characteristics predicting digital health intervention use after acute myocardial infarction. J Cardiovasc Transl Res. 2021;14(5):951–961. 24. Yuan G, Shi J, Jia Q, et al. Cardiac rehabilitation: a bibliometric review from 2001 to 2020. Front Cardiovasc Med. 2021;8:672913. 25. Vanzella LM, Oh P, Pakosh M, Ghisi GLM. Barriers to cardiac rehabilitation in ethnic minority groups: a scoping review. J Immigr Minor Health. 2021;23(4):824–839. 26. Wongvibulsin S, Habeos EE, Huynh PP, et al. Digital health interventions for cardiac rehabilitation: systematic literature review. J Med Internet Res. 2021;23(2):e18773. 27. Tsao CW, Aday AW, Almarzooq ZI, et al. Heart disease and stroke statistics—2023 update: a report from the American Heart Association. Circulation. 2023;147(8):e93–e621.