Kidney Failure Detection and Predictive Analytics for ckd Using Machine Learning Procedures

Kidneys are the functional units of our body. They assist in body balance by filtering the wastes, toxins, and excess water from the bloodstream and are carried out of the body through urine. If the kidney loses its functionality, then it leads to alarming health disorders in an individual. Often the symptoms of kidney disease are found very seldom. That being the case, most of the diseases are identified at the critical stages. Identifying the disease itself is inadequate for curing the disease but also the exact level of the disease parameters needs to be identified to predict and analyze the stage of the disease which is detected. Exact detection and analysis of the disease is impossible to do accurately by humans i.e., doctors. So, for accurate detection and analysis of chronic kidney disease (CKD), we take the aid of machine learning techniques that include various algorithms like classifiers K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Regression techniques like Linear Regression, Decision Trees, etc. All the machine learning replicas are trained using the dataset of CKD and their performance is compared to the best of them which gives more veracity and is considered the best classifier for the estimation and analysis of CKD. This survey analyzes and studies the diverse contributions of CKD detection models using various machine learning algorithms. This paper depicts different machine learning algorithms which contribute for the detection of CKD accurately. Moreover it is observed that the results of algorithms vary due to the variation in datasets considered for different algorithms.

Automated summary

Kidneys are essential for maintaining body balance, and machine learning techniques are valuable for accurate detection and analysis of chronic kidney disease. The performance of different algorithms varies in detecting CKD.