ABSTRACT
A recent study shows that covid-19 infected patients are having more probability of developing acute kidney injury that may leads to loss of kidney functionality. Hemodialysis is a process of removing the waste and excess fluids from the blood. Nowadays, because of covid-19, people prefer for home dialysis rather than taking dialysis in the hospitals. Generally, in the patients starting dialysis, almost, 23 percent of patients died in first month due to improper monitoring during the process of dialysis. Here, we have proposed an approach for real-time monitoring and health prediction. Our aim is to predict the probability of success, by analyzing the data using the popular classification techniques of machine learning which gives the maximum rate of accuracy to predict the outcome of dialysis. The system designed will collect the patient’s parameters such as temperature, blood pressure, and pulse rate during home dialysis. The stored data are then processed to check for any air bubbles or blood leakage occurrences. In such occurrences, the patient’s family is immediately alerted through an SMS to take the patient to hospital. This system helps to reduce the mortality rate after the dialysis treatment. Results prove that the KNN algorithm shows improvement in prediction accuracy of about 14%, 8%, and 5% when compared with logistic regression, SVM, and Naïve Bayes algorithms. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.