Clinical and demographic predictors of heart failure outcomes: A machine learning perspective

Abstract

Heart failure (HF) is a multifaceted clinical condition associated with high morbidity and mortality rates. It is an increasing public health concern, impacting millions globally and placing considerable strain on healthcare systems. In recent decades, there has been a growing interest in using machine learning techniques to predict HF outcomes. Hence, this study aims to explore the clinical and demographic characteristics associated with HF outcomes using a comprehensive dataset obtained from Kaggle. The dataset, “Heart Failure Clinical Records.csv,” was preprocessed to address missing values and prepared for analysis. Feature importance analysis and correlation matrix computations were conducted to identify significant predictors of death events among HF patients, including age, serum creatinine, and ejection fraction. Various machine learning models, such as logistic regression, random forest, support vector machine, and gradient boosting machine, were employed to predict death events. The results revealed varying levels of performance among the models, with some demonstrating promising accuracy and predictive power. However, further refinement of these predictive models is warranted to enhance clinical decision-making and patient care in HF management. Overall, this study underscores the value of data-driven approaches in understanding HF outcomes and highlights the necessity for ongoing research in this field.

Keywords

Heart failure / Machine learning models / Logistic regression / Random forest / Support vector machine / Gradient boosting machine / Data-driven approaches

Funding

None.

Conflict of interest

The authors declare that they have no competing interests.

References

[1] Tromp J, Paniagua SM, Lau ES, et al. Age dependent associations of risk factors with heart failure: Pooled population based cohort study. BMJ. 2021; 372:n461. doi: 10.1136/bmj.n461

[2] Veenis JF, Brunner-La Rocca HP, Linssen GC, et al. Age differences in contemporary treatment of patients with chronic heart failure and reduced ejection fraction. Eur J Prev Cardiol. 2019; 26(13):1399-1407. doi: 10.1177/2047487319835042

[3] Mortazavi BJ, Downing NS, Bucholz EM, et al. Analysis of machine learning techniques for heart failure readmissions. Circ Cardiovasc Qual Outcomes. 2016; 9(6):629-640. doi: 10.1161/CIRCOUTCOMES.116.003039

[4] Olsen CR, Mentz RJ, Anstrom KJ, Page D, Patel PA. Clinical applications of machine learning in the diagnosis, classification, and prediction of heart failure. Am Heart J. 2020; 229:1-17. doi: 10.1016/j.ahj.2020.07.009

[5] Katarya R, Srinivas P. Predicting Heart Disease at Early Stages using Machine Learning: A Survey. In: 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC). IEEE; 2020. p. 302-305. doi: 10.1109/ICESC48915.2020.9155586

[6] Saqib M, Perswani P, Muneem A, et al. Machine learning in heart failure diagnosis, prediction, and prognosis: Review. Ann Med Surg (Lond). 2024; 86(6):3615-3623. doi: 10.1097/MS9.0000000000002138

[7] Prudvi PS, Sharifahmadian E. Applying machine learning techniques to find important attributes for heart failure severity assessment. Int J Comput Sci Eng Appl. 2017; 7(5):1-9. doi: 10.5121/ijcsea.2017.7501

[8] Available froAQ3 m: https://www.kaggle.com/datasets/whenamancodes/heart-failure-clinical-records/data. [Last accessed on 2024 May 30].

[9] Chicco D, Jurman G. Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone. BMC Med Inform Decis Mak. 2020; 20(1):16. doi: 10.1186/s12911-020-1023-5

[10] McMurray JJ, Adamopoulos S, Anker SD, et al. ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure 2012: The Task Force for the Diagnosis and Treatment of Acute and Chronic Heart Failure 2012 of the European Society of Cardiology. Developed in collaboration with the Heart Failure Association (HFA) of the ESC. Eur Heart J. 2012; 33(14):1787-1847. doi: 10.1093/eurheartj/ehs104

[11] Filippos T, Andrew X, Javed B. Cardiovascular aging and heart failure: JACC review topic of the week. J Am Coll Cardiol. 2019; 74(6):804-813. doi: 10.1016/j.jacc.2019.06.053

[12] Shah SJ, Katz DH, Selvaraj S, et al. Phenomapping for novel classification of heart failure with preserved ejection fraction. Circulation. 2015; 131(3):269-279. doi: 10.1161/CIRCULATIONAHA.114.010637

[13] Fonarow GC, Adams KF Jr., Abraham WT, et al. Risk stratification for in-hospital mortality in acutely decompensated heart failure: Classification and regression tree analysis. JAMA. 2005; 293(5):572-580. doi: 10.1001/jama.293.5.572

[14] Damman K, Valente MAE, Voors AA, O’Connor CM, van Veldhuisen DJ, Hillege HL. Renal impairment, worsening renal function, and outcome in patients with heart failure: An updated meta-analysis. Eur Heart J. 2014; 35(7): 455-469. doi: 10.1093/eurheartj/eht386

[15] Angraal S, Mortazavi BJ, Gupta A, et al. Machine learning prediction of mortality and hospitalization in heart failure with preserved ejection fraction. JACC Hear Fail. 2020; 8(1):12-21. doi: 10.1016/j.jchf.2019.06.013

[16] Nithya B, Ilango V. Predictive Analytics in Health Care Using Machine Learning Tools and Techniques. In: 2017 International Conference on Intelligent Computing and Control Systems (ICICCS). IEEE; 2017. p. 492-499. doi: 10.1109/ICCONS.2017.8250771

[17] Obermeyer Z, Emanuel EJ. Predicting the future-big data, machine learning, and clinical medicine. N Engl J Med. 2024; 375(13):1216-1219. doi: 10.1056/NEJMp1606181

[18] Choi E, Schuetz A, Stewart WF, Sun J. Using recurrent neural network models for early detection of heart failure onset. J Am Med Inform Assoc. 2017; 24(2):361-370.doi: 10.1093/jamia/ocw112

[19] Miotto R, Wang F, Wang S, Jiang X, Dudley JT. Deep learning for healthcare: Review, opportunities and challenges. Brief Bioinform. 2018; 19(6):1236-1246. doi: 10.1093/bib/bbx044

[20] Solares JR, Raimondi FE, Zhu Y, et al. Deep learning for electronic health records: A comparative review of multiple deep neural architectures. J Biomed Inform. 2020; 101:103337. doi: 10.1016/j.jbi.2019.103337

[21] Suresh H, Guttag J. A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle. In: The ACM International Conference Proceeding Series (ICPS). New York; 2021. doi: 10.1145/3465416.3483305