Detection of Chronic Kidney Disease Using Machine Learning Algorithms

Everyone is aware that the kidneys play a significant part in the body, providing critical functions such as osmoregulation and excretion, amongst other things. To put it another way, the kidneys and the excretion system are responsible for collecting any harmful or unneeded compounds and then flushing them out of the body. Chronic renal disease is the result of an issue originating in the kidneys. Chronic kidney disease (CKD), a non-communicable disorder that has a substantial effect on patient morbidity, mortality, and hospital admission rates worldwide, affects 10-15% of the world’s population. It is believed that making an accurate and early diagnosis of the phases of CKD is essential for reducing the negative effects that the patient’s health problems have. Chronic kidney disease, often known as CKD, is a disorder that is characterised by a continuous decline in kidney function over time. It is indicative of a condition that is harmful to one’s kidneys and has an impact on their overall health. Incorrect diagnosis and management of an illness might potentially result in end-stage renal failure and the death of the patient. Several studies focusing on the early detection of CKD have made use of tools from the field of machine learning. The objective of this study is to design a method based on machine learning that is capable of accurately predicting Chronic Kidney Disease (CKD). The Artificial Neural Network (ANN) is the method that is used in the proposed strategy for the purpose of making a prediction about CKD. Both the training and the testing of the models made use of the Chronic Kidney Disease dataset that was available in the UCI Machine Learning Repository. People will be able to ascertain whether or not they have CKD by inputting information into a web application that was built using the Flask framework. This component of the proposed system is also included. Because of this function, the system is both less complicated and more accessible to all users. The research contributes to the field of medical diagnostics and highlights the ways in which machine learning techniques might be used to improve CKD prediction.