Earlier Forecasting of Chronic Kidney Failure: Performance of artificial intelligence in healthcare

This is the authors' abstract. We don't add key points for this paper.

The fast paced growth use of new information technology such as mobile application, big data analytics impacted all sectors. The healthcare trade is mostly an “information and document rich industry”, and manual handling is not feasible in practical life. These huge volumes of data have been key to the arena of data-mining to generate associations among the attributes and extract knowledge. Many research shows that combating Kidney diseases is a complex assignment that involves considerable knowledge and experience because kidney diseases have become a silent threat, without symptoms, and develop into an acute stage quickly. Unfortunately, the majority of patients discover this disease in its advanced stages where hemodialysis or transplant becomes a necessity.Various data mining procedures are available for forecasting diseases such as clustering, classification, association rules, regression, and summarizations. All these technics proved a great success in information and knowledge discovery from medical big data to help in decision making and saving human lives. In this paper, the key objective of this study is to analyze a real datasets collected and forecasting kidney failure which will make controlling the progression of the disease possible and can even stabilize the state of patients. We will present and discuss many researches about Chronic Kidney Disease Forecasting (CKD) and we will show that the best method to predict and forecasting kidney failure progression is by predicting Glomerular Filtration Rate variation (GFR), our results show that linear regression is the most accurate and suitable method that could be used in the field of bioinformatics, for further data analysis and predictions. particularly chronic kidney disease. This paper will be useful for many medical institutions and work-related bioinformatics in pursuance to understand the prediction and how can data mining technics help to forecast failure kidney progression, and even intervene to control it.

May support GFR forecasting models in CKD research; leaves open prospective validation before clinical use.