| Autor: |
Salau, Ayodeji Olalekan, Assegie, Tsehay Admassu, Markus, Elisha Didam, Eneh, Joy Nnenna, Ozue, ThankGod Izuchukwu |
| Předmět: |
|
| Zdroj: |
International Journal of Electrical & Computer Engineering (2088-8708); Apr2024, Vol. 14 Issue 2, p1809-1815, 7p |
| Abstrakt: |
Heart disease (HD) accounts for more deaths every year than other illnesses. World Health Organization (WHO) assessed 17.9 million life losses caused by heart disease in 2016, demonstrating 31% of all international life losses. Three-quarters of these life losses occur in low and middle-income nations. Machine learning (ML), due to advanced precision in pattern recognition and classification, demonstrates to be in effect in complementing decision-making and threat prediction from the huge number of HD data created by the healthcare sector. Thus, this study aims to develop a logistic regression model (LRM) for predicting the risk of getting HD in ten years. The study explores the different methodologies for improving the performance of base LRM for predicting whether a person gets HD after ten years or not. The result demonstrates the capability of LRM in predicting the risks of getting HD after ten years. The LRM achieves 97.35% accuracy with the recursive feature elimination and random under-sampling. This implies that the LRM can play an important role in precautionary methods to avoid the risk of HD. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
