Machine learning with Internet of Things data for risk prediction: Application in ESRD

Abstract

Connected objects are the key for many intelligent systems for instance, direct access to physical and physiological values and collecting information about the human body. Our research works aim to develop non-invasive methods that predict risk for dialysis patient in End-Stage Renal Disease (ESRD) at a smart home care system based on Internet of Things (IoT). However, the IoT components pose many new challenges in collecting more fine grained information called biomarkers. In this paper, we describe our work in progress to predict dialysis biomarkers from IoT sensors. To address this problem, we present our ongoing research to develop a modern data analytics environment using machine learning techniques. This paper gives also an overview about literature review and discusses open issues.