Chronic Kidney Disease Classification Using ML Algorithms | ||||
| Kafrelsheikh Journal of Information Sciences | ||||
| Volume 4, Issue 2, November 2023 PDF (462.87 K) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/kjis.2023.220954.1015 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
Sara A shehab  1; Eman Shehab2; aya morsi3
| ||||
| 1Computer Science Dep, Faculty of Computer and Artificial Intelligence, Sadat city, Egypt | ||||
| 2Department of computer science, faculty of computers and artificial intellgence, sadat city | ||||
| 3student bioinformatic, faculty of computers and artificial intellgence, sadat city | ||||
| Abstract | ||||
| Chronic kidney failure is one of the most common diseases that threaten the lives of many people and cause death for many. By using artificial intelligence, we predict the disease and classify people into infected and non-infected people. One of the goals is to reduce non-communicable disease-related premature death by a third by 2030. 10-15% of the world's population may have chronic kidney disease (CKD), which is one of the major causes of non-communicable disease morbidity and mortality. In order to reduce the effects of patient health complications like hypertension, anaemia (low blood count), mineral bone disorder, poor nutritional health, acid base abnormalities, and neurological complications with timely intervention through appropriate medications, early and accurate detection of the stages of CKD is thought to be essential. Several studies on the early identification of CKD have been conducted utilising machine learning approaches. They weren't primarily concerned with predicting the exact stages. In this work classification methods are used like support vector classifier, random forest, logistic regression, and decision tree. The results detect that Linear SVC Support Vector Machine achieved high accuracy and Random Forest and Decision tree (100%) and logistic regression achieved (96.8%). A data set with 24 feature and 401 records are used for testing the algorithms. 20% of data set will be used in testing and 80% for training. The proposed work achieves high accuracy when compared with the previous works. | ||||
| Keywords | ||||
| Chronic kidney; Machine Learning; Support Vector Machine; Random Forest | ||||
|
Statistics Article View: 228 PDF Download: 240 |
||||
