Computer-aided automated detection of kidney disease using supervised learning technique

In this paper, we propose an efficient home-based system for monitoring chronic kidney disease (CKD). As non-invasive disease identification approaches are gaining popularity nowadays, the proposed system is designed to detect kidney disease from saliva samples. Salivary diagnosis has advanced its popularity over the last few years due to the non-invasive sample collection technique. The use of salivary components to monitor and detect kidney disease is investigated through an experimental investigation. We measured the amount of urea in the saliva sample to detect CKD. Further, this article explains the use of predictive analysis using machine learning techniques and data analytics in remote healthcare management. The proposed health monitoring system classified the samples with an accuracy of 97.1%. With internet facilities available everywhere, this methodology can offer better healthcare services, with real-time decision support in remote monitoring platform.