A novel hybrid machine learning based prediction of chronic kidney disease

Chronic kidney disease, sometimes called chronic renal disease, is characterised by a typical kidney function or the incremental progression of renal failure over months or years. Due to an increasing patient population, a growing possibility of kidney disorders entering the death phase, and a poor prognosis for morbidity and mortality, chronic kidney disease (CKD) indicates a high burden on the healthcare system. Different complex conditions include developed stages in blood, anemia (low blood count), weak bones, and nerve damage. Early identification and medication prevents chronic uropathy is getting the worse situation. It is significant to have potential techniques during the initial analysis of CKD. In recent times, the Machine Learning (ML) methods had gain more attention due to its accurate and effective results. The primary objective of this task is to determine the presence of CKD. Hence in this paper A novel Hybrid Machine Learning based prediction of CKD is presented. For obtaining better and accurate results, two of the most popular ML classifiers SVM (Support Vector Machine) and Decision tree are combined as a hybrid model. This approach can give accurate and reliable outputs in form of accuracy, prediction time.