Scholarlink

<p>Chronic renal failure (CKD) is a significant load on the systems involved in healthcare due to its growing frequency, risk of evolution to final phase renal sickness, deprived prognosis and mortality, and quickly became a global epidemic. becomes a serious health crisis. Poor diet and not drinking enough water are the main causes of this disease. Machine learning (ML) techniques are well suited for IRC prediction. The present study provides a method to predict a person’s CKD status from clinical data, including data preprocessing, missing value processing techniques, data aggregation, and feature extraction. In this study, we analyzed three different trained models using machine learning methods such as logic regression (LR), classification using decision tree (DT), KNearest Neighbors (ANN) and multiple variables. physiologic. The LR classifier is believed to be the most precise in this part, yielding approximately 99% precision in this study. The dataset used to create this method is a publicly available CKD dataset. Compared with previous studies, the accuracy of the model used in this study is significantly higher, indicating that it is also more reliable than the model used in previous studies. Many model comparisons have proven its sustainability and the diagram can be drawn from the research results. The proposed work can be used to guess the outcome of multiple techniques and the appropriate method that can be castoff depending on the requirements.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Chronic Kidney Disease Classification Using Machine Learning Methods

  • 期刊论文

  • 发表日期：

    2026年5月2日

查看全文
  • A. Kishore Kumar,
  • A. Murugarajan,
  • A. Udhayakumar

摘要

Chronic renal failure (CKD) is a significant load on the systems involved in healthcare due to its growing frequency, risk of evolution to final phase renal sickness, deprived prognosis and mortality, and quickly became a global epidemic. becomes a serious health crisis. Poor diet and not drinking enough water are the main causes of this disease. Machine learning (ML) techniques are well suited for IRC prediction. The present study provides a method to predict a person’s CKD status from clinical data, including data preprocessing, missing value processing techniques, data aggregation, and feature extraction. In this study, we analyzed three different trained models using machine learning methods such as logic regression (LR), classification using decision tree (DT), KNearest Neighbors (ANN) and multiple variables. physiologic. The LR classifier is believed to be the most precise in this part, yielding approximately 99% precision in this study. The dataset used to create this method is a publicly available CKD dataset. Compared with previous studies, the accuracy of the model used in this study is significantly higher, indicating that it is also more reliable than the model used in previous studies. Many model comparisons have proven its sustainability and the diagram can be drawn from the research results. The proposed work can be used to guess the outcome of multiple techniques and the appropriate method that can be castoff depending on the requirements.