Journal Basic Info
- Impact Factor: 1.995**
- H-Index: 8
- ISSN: 2474-1647
- DOI: 10.25107/2474-1647
Major Scope
- Obstetrics Surgery
- Plastic Surgery
- Minimally Invasive Surgery
- Robotic Surgery
- Thoracic Surgery
- Bariatric Surgery
- Orthopaedic Surgery
- Emergency Surgery
Abstract
Citation: Clin Surg. 2021;6(1):3315.Research Article | Open Access
Prediction of Cardiovascular Diseases from Risk Factor: An Application of Machine Learning
Yousaf Ali Khan1,2*
1Department of Mathematics and Statistics, Hazara University Mansehra, Pakistan
2School of Statistics, Jiangxi University of Finance and Economics, China
*Correspondance to: Yousaf Ali Khan
PDF Full Text DOI: 10.25107/2474-1647.3315
Abstract
Aims: Heart diseases are the leading cause of high mortality and incapacity across the globe. Research in recent years confirmed that, the fees of heart illnesses-associated deaths have reduced in some medically advanced countries, however still high in less and medium medically advanced countries and this need critical attention. Regardless of the seriousness of heart illnesses in lowand middle-income nations, no interest given to the prevention of Cardiovascular Disease (CVD) associated risk factors in Continent of Asia, especially in my home land. Similarly, financial and political variability is hastening the costs of heart sicknesses within these countries. On the other hand, the domain of information mining (DM), which aim at extracting excessive-stage knowledge from raw statistics, provide exciting automatic tools in lots of subject of research. Methods: This paper addressed the prediction of heart diseases from hazard elements through decision-making tree. This paper introduces data mining technique in public fitness with the aim to extract high-degree knowledge from raw data, which facilitates in prediction of heart diseases from risk factors and its prevention. The existing work intends to introduce new technique of risk elements in heart diseases using novel data mining strategies. Latest actual-international affected person’s information (e.g. smoking, area of resident, age, weight, blood stress, chest pain, Low- Density Lipoproteins (LDL), High-Density Lipoproteins (HDL), blocked arteries became accrued by way of the use of questionnaire through direct interview technique from patients. Variable decision trees are constructed for cardiovascular disease records primarily based on chance factors and ranking of risk elements. Results: The results show that there is correct prediction of Cardiovascular Disease (CVD) from risk factor, if records on chance factors are available. As direct results of this study, the use of tobacco, loss of physical exercise, and weight-reduction plan are the main factors playing vital role in the prediction of heart diseases, which is the most important reason of mortality in developing countries, especially in my country. Conclusion: We gain ranking of endangerment factors through variable decision tree, which allows improving public safety, as properly in selection regarding heart diseases remedy and prevention. It additionally facilitates in guidelines making related to prevention of cardiovascular diseases risk factors in low- and middle-income nations.
Keywords
Machine learning; Heart diseases; Prevention; Decision tree; Risk factors; Prediction; Hybrid technique; Low-Density Lipoproteins (LDL); High-Density Lipoproteins (HDL)
Cite the article
Khan YA. Prediction of Cardiovascular Diseases from Risk Factor: An Application of Machine Learning. Clin Surg. 2021; 6: 3315.