COMPARATIVE ANALYSIS OF K-NEAREST NEIGHBORS AND RANDOM FOREST ALGORITHMS IN PREDICTING HEART FAILURE DISEASE

YOGA SUWINDRA, NPM 2107100023 (2024) COMPARATIVE ANALYSIS OF K-NEAREST NEIGHBORS AND RANDOM FOREST ALGORITHMS IN PREDICTING HEART FAILURE DISEASE. Tugas_Akhir (Artikel) International Journal of Science, Technology & Management, 5 (4). ISSN 2722 - 4015 (e-ISSN)

	Text COVER.pdf Download (1MB)
	Text ARTIKEL.pdf Download (472kB)

Abstract

Heart failure is one of the cardiovascular diseases with a high mortality rate worldwide. Early detection and accurate prediction of heart failure risk are critical to improving patients' quality of life and reducing mortality. With the advancement of technology and increasingly available medical data, the use of machine learning algorithms for disease prediction has become a significant area of research. The purpose of this study is to compare the performance of the K-Nearest Neighbors and Random Forest algorithms in predicting heart failure. This study follows a systematic methodology starting with the collection of relevant medical data, followed by data preprocessing to ensure good data quality. The next stage is exploratory data analysis to understand the characteristics of the data. Next, we divide the data into training and testing sets, where we train and test the K-Nearest Neighbors and Random Forest models. We perform parameter optimization for each model to achieve optimal performance. Finally, we evaluate the model performance using accuracy metrics. The results show that Random Forest outperforms K Nearest Neighbors in terms of prediction accuracy. The training accuracy for Random Forest reaches 98.80%, while for K-Nearest Neighbors it is 93.60%. In testing, Random Forest showed an accuracy of 96.50% compared to K-Nearest Neighbors, which reached 86.00%. The smaller decrease in accuracy in Random Forest indicates better generalization ability compared to K-Nearest Neighbors. The study's results indicate that the Random Forest algorithm outperforms K-Nearest Neighbors in heart failure risk prediction. Random Forest not only has higher accuracy but also shows better stability between training and testing data. The results of this study can be a reference for medical practitioners and researchers when choosing the right algorithm for predicting heart failure. Keywords : Heart Failure, K-Nearest Neighbors, Machine Learning, Prediction, Random Forest.

Item Type:	Article
Uncontrolled Keywords:	Heart Failure, K-Nearest Neighbors, Machine Learning, Prediction, Random Forest.
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Z Bibliography. Library Science. Information Resources > ZA Information resources
Divisions:	Fakultas Sains Dan Teknologi > Informatika Komputer
Depositing User:	Unnamed user with email repository@ulb.ac.id
Date Deposited:	08 Oct 2024 09:55
Last Modified:	08 Oct 2024 09:55
URI:	http://repository.ulb.ac.id/id/eprint/1162

Actions (login required)

View Item