Prediction of Heart Failure in Respects to Death, Essay Example

Abstract

Heart failure is one of the leading causes of death for older adults. However, using the data mining technique of Weka, this proposal suggests using the data of current deaths due to the disease to allow prediction of the current disease burden. This is mainly because the disease has hurt many people and needs to be addressed through analytics prediction. Through a literature review of the existing use of data mining in healthcare research, this study will determine how data mining is going to be used to determine the future prevalence of the disease.

Introduction

Heart failure is one of the leading causes of death in the aged population. Describing the various specific causes of death regarding heart failure is important in identifying the exact mechanisms through which patients eventually die (Rahimi et al., 2015).

Explaining the various prevalence of the various causes of heart failure in causing death will allow the knowledge of existing information on predicting the disease using the various mortality prevalence of the disease.

This proposal will want to perform research that uses data mining to predict the existing cases of heart failure basing on the existing deaths caused by the disease.

A literature review will be used to analyze other studies that made use of numerical data to predict the prognosis and outcome of heart failure using parameters, such as extracellular volume fractions, and the prevalence of other pathologies, such as dilated cardiomyopathy (Vita et al., 2019). In addition to the referenced work, other existing studies will be used in the literature review.

The literature review will explore the various quantitative methodologies as regards data mining, the methodology that will be used in the proposed study (Luo et al., 2016).

This section will include a description of the data mining technique. Using the Weka data mining technique, this study will determine how the deaths caused by heart failure can be used to predict the prevalence of the disease. This is because the technique has been used successfully in another study to predict heart failure as one of the techniques that require less effort in prediction (Purusothaman and Krishnakumari, 2015).

Motivation

The main reason I decided to choose the topic of heart failure and use the proposed methodology and technique to predict the prevalence of the disease is due to the harm the disease is causing human beings. According to Fry et al. (2016), heart failure has been overlooked so far, but its chronic nature makes people’s lives very difficult, especially because other complications and conditions usually follow the disease. Therefore, the negative prognosis, which is death, motivated my course to predict the existing burden of the disease using the data collected on the already happened deaths.

Problem Domain

Prediction of heart failure using the data collected using the Weka technique is a domain that requires venturing. This is because learning analytics is part of the new goals of education systems and data mining techniques, such as Weka, provide students and the academic fraternity grounds to establish this new advanced learning area (Vahdat et al., 2015). This means predictive analytics in the field of medicine, such as in heart failure, can use existing outcomes, such as deaths, to predict the prevalence of the disease in the existing alive population.

Aim and objective

The objectives of the study to be carried out will be as follows:

To find out the death burden of heart failure in all relevant age groups.

To use the data collected on the deaths caused by the disease to predict the prevalence and disease burden of heart failure.

Future Work

The study will be used to provide data mining results through the Weka technique, which will be useful to predict future disease trends. Data analytics has been identified in healthcare systems for the use of improving the system and future healthcare outcomes while managing diseases, such as heart failure (Kankanhalli et al., 2016).

References

Fry, M., McLachlan, S., Purdy, S., Sanders, T., Kadam, U. T., & Chew-Graham, C. A. (2016). The implications of living with heart failure; the impact on everyday life, family support, co-morbidities, and access to healthcare: a secondary qualitative analysis. BMC family practice, 17(1), 1-8. https://doi.org/10.1186/s12875-016-0537-5

Kankanhalli, A., Hahn, J., Tan, S., & Gao, G. (2016). Big data and analytics in healthcare: introduction to the special section. Information Systems Frontiers, 18(2), 233-235. https://doi.org/10.1007/s10796-016-9641-2

Luo, J., Wu, M., Gopukumar, D., & Zhao, Y. (2016). Big data application in biomedical research and health care: a literature review. Biomedical informatics insights, 8, BII-S31559. https://doi.org/10.4137/BII.S31559

Purusothaman, G., & Krishnakumari, P. (2015). A survey of data mining techniques on risk prediction: Heart disease. Indian Journal of Science and Technology, 8(12), 1. https://doi.org/10.17485/ijst/2015/v8i12/58385

Rahimi, K., Duncan, M., Pitcher, A., Emdin, C. A., & Goldacre, M. J. (2015). Mortality from heart failure, acute myocardial infarction, and other ischaemic heart diseases in England and Oxford: a trend study of multiple-cause-coded death certification. J Epidemiol Community Health, 69(10), 1000-1005. https://doi.org/10.1136/jech-2015-205689

Vahdat, M., Ghio, A., Oneto, L., Anguita, D., Funk, M., & Rauterberg, M. (2015). Advances in learning analytics and educational data mining. Proc. of ESANN2015, 297-306.

Vita, T., Gräni, C., Abbasi, S. A., Neilan, T. G., Rowin, E., Kaneko, K., & Rassi, C. H. (2019). Comparing CMR mapping methods and myocardial patterns toward heart failure outcomes in nonischemic dilated cardiomyopathy. JACC: Cardiovascular Imaging, 12(8), 1659-1669. https://doi.org/10.1016/j.jcmg.2018.08.021