|
|
 |
| |
|
|
|
Comparative Study on Multivariate Methods Using Chronic Kidney Disease |
|
|
|
PP: 1-13 |
|
|
|
doi:10.18576/jsap/130101
|
|
|
|
Author(s) |
|
|
|
K. Senthamarari Kannan,
S. Anitha,
|
|
|
|
Abstract |
|
|
| The human being is currently one of the most serious illnesses in the modern world, and accurate diagnosis is necessary as soon as possible. In this modern world, there are numerous diseases that exist. Chronic kidney disease is regarded as the most serious of these disorders in humans. There are several methods in the medical area for disease diagnosis, and the prediction criterion is also significant in the medical field for determining the consequences of the study in the future. Many statistical methods are employed in order to forecast the medical dataset and provide accurate and reliable findings. A lot of models are available in multivariate methods to predict the dataset. In this paper, the computational algorithms for detecting CKD using Decision Tree (DT), Random Forest (RF), K-Nearest Neighbor (KNN), and Logistic Regression (LR) are reviewed. The first, based on the association, inference for the study. Decision tree and logistic regression approaches are used to more correctly diagnose chronic renal disease based on the results of the association. Finally, the study came to the conclusion that greatest fit for forecasting chronic renal disease.
|
|
|
|
|
|
|
|
