Classification and Association Rule Mining Technique for Predicting Chronic Kidney Disease

Abstract

Background and objective: Chronic kidney disease (CKD) is one of the deadly diseases that can affect a lot of vital organs in the human body such as heart, liver, and lungs. Many individuals might be at early stage of kidney disease and not have any signs, which might lead to a sudden death. Previous research showed that early prediction of CKD is very important in the medical field for physicians’ decision-making and patients’ health and life. To this end, constructing an efficient prediction system for CKD, which is the goal of this paper, often reduces medical errors and overall healthcare cost. Methods: Classification and association rule mining techniques were integrated and utilised to construct an efficient system for predicting and diagnosing CKD and its causes using weka and SPSS as platform environments. In particular, five classification algorithms, namely, naive Bayes, decision tree, support vector machine, K-nearest neighbour, and JRip were used to achieve the research goal. In addition, Apriori algorithm was used to discover strong relationship rules between attributes. The experiments were conducted on real medical dataset collected from hospitals and patient monitoring systems. Results: The experiments achieved high accuracy of 98.50% for K-nearest neighbour (KNN) classifier and achieved 96.00% when using classier based on association rule (JRip). Conclusions: We conclude by showing that applying integrative approach by combining classification algorithms and association rule mining can significantly improve the classification accuracy and be more useful for CKD prediction. This research has also several theoretical and practical implications for the medical field and healthcare industry.

Association rule mining for prediction of COVID-19

“…Thus, for this example, the following association rules are developed: S5→(S2,S1); (S1,S5)→S2 and (S2,S5)→S1. It has been noticed that the apriori algorithm of association rule mining has already been successfully deployed for prediction/diagnosis of heart diseases (Said et al, 2015;Domadiya & Rao, 2018;Jamsheela, 2021), dengue (Jahangir et al, 2018), brain tumor (Sengupta et al, 2013), chronic kidney disease (Alaiad et al, 2020), infectious diseases (Brossette et al, 1998), pandemic diseases (Burvin & Dhanalakshmi, 2018;Aiswarya et al, 2020), COVID-19 (Çelik, 2020;Shawkat et al, 2021;Tandan et al, 2021), pediatric primary care (Downs & Wallace, 2000), treatment of patients in an emergency department (Sarıyer & Taşar, 2020) etc. In this paper, based on a huge dataset of COVID-19 patients and using the FP growth algorithm of association rule mining, an attempt is put forward to discover COVID-19 symptom patterns and rules which would support the initial identification of severe COVID-19 cases for early treatment and isolation.…”

An improved feature selection approach for chronic heart disease detection

“…A current literature review in [13], [14], related to the dimensionality reduction problem in medical dataset classification showed that the issue of irrelevant feature on the accuracy of classification model is still an ongoing and open research issue. Developing classification model with higher accuracy on medical ISSN: 2302-9285  An improved feature selection approach for chronic heart disease … (S. J. Sushma)…”

A novel enhanced decision tree model for detecting chronic kidney disease

“…Creatinine levels in the blood increase with reduced kidney activities. Researches (Levey et al 1999(Levey et al , 2009Alaiad et al 2020;Elhoseny et al 2019;Qin et al 2019) show that the most commonly used prediction factors for CKD diagnosis are serum creatinine, age, serum urea, and specific gravity. From different research studies performed in different random samples, it has been observed that close associations are present between enhanced albuminuria (presence of albumin in the urine) and kidney failure (Chronic Kidney Disease Prognosis Consortium, 2010).…”