Chronic Kidney Disease Prediction Using Machine learning Methods

Abstract

Chronic kidney disease is caused due to various factors, Which primarily affects the health all of sudden and cause severe damage to the body and increase the early cause for death , the chronic kidney Disease includes , Tumor , cyst , Stone and other sought of kidney problems that arises because of carelessness and some other health issues over a period of long time with end stage Renal failure and requiring dialysis or kidney replanting this diseases can be easily cure when it is diagnosis early and prediction of the defects can use to treat the patient easily with  some minor complications  and may include fast recuperation with the help of doctors. This finding is not a hand- operated methods so that the process is quite easy to find for the doctors as wells as patients from anywhere at any time and it is much easier to find out the categories for the patients wellness and protect the individual from the disease  The early-stage findings show a way to make the disease eliminate to reduce the perilousness of a patient and to reduce the vulnerability  Of a disease with the susceptible by using a wireless process with only a website for uploading the patients kidney ultrasound and Kidney CT images to find out whether the patients is affected with the Normal , Tumor , Cyst , or Stone and to find out the Inner part of the Kinney through Image detecting through CNN , Finding that the kidney has a Inner with the fat or water content imminence and the outer line for the prediction of fat and water content prominently  without any delay for the patient and a giving a quick analysis for the patient and diagnosing where the patient is impacted or not for the doctor’s suggestions for the disease and to protect them from the kidney disease and to Avoid the pretend for the disease. The Aspiration of the project is to analyze the medical imaging data such as a dataset of the K – and CT images is developed and trained to distinguish between normal renal tissues and tumor lesions which involves timely inventions and a better management of the disease This helps in early prediction. By performing Evaluation reveals that the deep learning model achieves the High Accuracy, Sensitivity and specificity in differentiation between images of K. and expertise of the knowledge for the disease prediction and the difference in tissue characteristics and task requiring specialized knowledge and remains challenging.