Congestive heart failure is a severe chronic disease associated with high readmission risks. With nearly a million new cases reported annually, it is essential to improve the existing frameworks of identification and treatment of the problem (Ryan et al., 2019). Many experts propose new prevention methods and innovative solutions for predicting the consequent health complications. From these considerations, it is crucial to analyze the existing academic research to identify the potential knowledge gap in the study of readmission rates. Ultimately, the current paper provides a comprehensive overview of the contemporary literature on congestive heart failure and the reduction of readmission rates.
Readmission Prediction and Prevention
At present, there is an extensive list of methods used to reduce readmission rates. Some of the notable frameworks include the implementation of digital health monitoring, biomarkers, and the overall improvement of healthcare services (Ryan et al., 2019; Park et al., 2019). Furthermore, experts utilize statistical and computational methods, such as deep learning neural networks, to calculate the risk of readmission (Liu et al., 2019). Lastly, the research suggests that a person-centered treatment approach with comprehensive patient education might significantly reduce the readmission rates (Wan et al., 2019). Nevertheless, some methods demonstrate questionable effectiveness, and it is essential to analyze contemporary research to identify the knowledge gaps.
Health monitoring generally refers to telemonitoring and complex digital health monitoring, which implies the remote transmission of the patient’s vital health data to the hospital. Aronow and Shamliyan (2018) suggest that simple telemonitoring, such as patient surveys, provides the same results as the common treatment. On the other hand, Aronow and Shamliyan (2018) and Park et al. (2019) demonstrate that complex digital health monitoring is highly beneficial and might reduce readmission rates by approximately 15%. The primary advantage of the method is the immediate interpretation of health data and consequent prescription of the appropriate medications (Park et al., 2019). Ultimately, complex health monitoring is an effective method of reducing readmission rates.
Consequently, computational methods, such as neural networks, are primarily utilized to predict readmissions. Liu et al. (2019) have found that convolutional neural networks (CNN) have an approximately 10% higher prediction rate of 30-day readmissions than the existing frameworks. Furthermore, the authors report that other CNN methods might be even more productive, requiring further research (Liu et al., 2019). Therefore, it is essential to take advantage of contemporary computational technologies to improve the quality of healthcare.
Biomarkers generally refer to the measurements of the patient’s vital health data. Sudharshan et al. (2017) emphasize B-type Natriuretic Peptide (BNP), N-terminal pro BNP, and galectin-3 (Gal-3) among the biomarkers that can identify the need for future readmission. Paul and Harshaw-Ellis (2019) also demonstrate the effectiveness of cardiac biomarkers to diagnose and manage heart failure diseases. As a result, contemporary research suggests that the intelligent usage of biomarkers might significantly reduce the number of readmissions for patients with congestive heart failure.
Lastly, hospitals need to ensure the continually evolving quality of healthcare and focus on the person-centered approach. The research transparently demonstrates that the patient’s awareness of the problem, including methods of treatment and lifestyle change recommendations, is the most significant psychosocial factor for reducing readmissions (Ryan et al., 2019). Other strategies in the person-centered approach include phone calls from the hospital, the development of home-based exercise programs, post-discharge education, and dietary recommendations (Wan et al., 2019). Ultimately, the current literature review has identified four primary areas of readmission prediction and prevention: health monitoring, computational methods, biomarkers, and the person-centered approach.
Aronow, W. S., & Shamliyan, T. A. (2018). Comparative effectiveness of disease management with information communication technology for preventing hospitalization and readmission in adults with chronic congestive heart failure. Journal of the American Medical Directors Association, 19(6), 472-479. Web.
Liu, X., Chen, Y., Bae, J., Li, H., Johnston, J., & Sanger, T. (2019, November). Predicting heart failure readmission from clinical notes using deep learning. In 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 2642-2648). IEEE.
Park, C., Otobo, E., Ullman, J., Rogers, J., Fasihuddin, F., Garg, S.,… & Atreja, A. (2019). Impact on readmission reduction among heart failure patients using digital health monitoring: feasibility and adoptability study. JMIR medical informatics, 7(4), e13353. Web.
Paul, S., & Harshaw-Ellis, K. (2019). Evolving use of biomarkers in the management of heart failure. Cardiology in review, 27(3), 153-159. Web.
Ryan, C. J., Bierle, R. (Schuetz), &Vuckovic, K. M. (2019). The three Rs for preventing heart failure readmission: Review, reassess, and reeducate. Critical Care Nurse, 39(2), 85–93. Web.
Sudharshan, S., Novak, E., Hock, K., Scott, M. G., & Geltman, E. M. (2017). Use of biomarkers to predict readmission for congestive heart failure. The American journal of cardiology, 119(3), 445-451. Web.
Wan, T. T. (2018). Strategies to modify the risk for heart failure readmission: A systematic review and meta-analysis. Population Health Management for Poly Chronic Conditions, 85-112. Web.