Journal of Nephrology & Therapeutics

The high incidence of chronic kidney disease (CKD) and the rising number of people with end-stage renal disease (ESRD) globally highlight the importance of providing patients with options for renal-replacement therapy methods. Peritoneal dialysis (PD) has been shown in clinical studies to have many benefits as a home-based dialysis therapy, including longer preservation of residual renal function, lower hemodynamic stress, potential for better patient survival, relatively high quality of life, and greater capacity to serve more ESRD patients because of its lower cost and infrastructure needs.

Computational Collaborative Healthcare data analytics is a method of methodical data analysis that allows healthcare specialists to discovery opportunities used for development in health system management processing the various information are stored. This proposed approach entails three parts comparable to preprocessing, attribute selection, classification algorithms. The goal of this work is to plan a machine-based diagnostic approach using machine learning technique. This method is developed to mining the risk factors of chronic kidney diseases. In this work, Random forest, SVM C5.0, Decision Tree, C4.5 and ANN algorithms were used to identify an early diagnosis of CKD patients. This work comparing other algorithms the best for Random forest algorithm with good accuracy and less time complexity.

Acute kidney injury (AKI) is a major health problem, causing morbidity in 13 million people annually, among which, 85% occur in developing countries. It is therefore one of important issue in Africa where there is resource limitation at large, and appreciation of its pattern can help understand it?s causes, complications and outcome better which are determinants for its early prevention and management. The objective of the study was to evaluate Patterns and outcome of AKI patients who are admitted in Tikur Anbessa specialized hospital (TASH) Adult Emergency Unit, Addis Ababa, Ethiopia. Prospective Cross sectional study was done from August 1, 2018 to May 1, 2019. SPSS software version 25 was used for analysis.