Efficient datamining model for prediction of chronic kidney disease using wrapper methods

Abstract

In the present generation, majority of the people are highly affected by kidney diseases. Among them, chronic kidney is the most common life threatening disease which can be prevented by early detection. Histological grade in chronic kidney disease provides clinically important prognostic information. Therefore, machine learning techniques are applied on the information collected from previously diagnosed patients in order to discover the knowledge and patterns for making precise predictions. A large number of features exist in the raw data in which some may cause low information and error; hence feature selection techniques can be used to retrieve useful subset of features and to improve the computation performance. In this manuscript we use a set of Filter, Wrapper methods followed by Bagging and Boosting models with parameter tuning technique to classify chronic kidney disease. The capability of Bagging and Boosting classifiers are compared and the best ensemble classifier which attains high stability with better promising results is identified.

Chronic kidney disease prediction using boosting techniques based on clinical parameters

“…The authors applied the principal component analysis (PCA) method to get the optimal feature set and attained the highest accuracy rate of 99.0% using random forest (R.F.). Ramaswamyreddy et al [48] used wrapper methods along with bagging and boosting models to develop a CKD prediction model, attaining an accuracy of 99.0% with gradient boosting. However, the authors did not evaluate their model using other performance measure metrics.…”

Efficient intelligent system for diagnosis pneumonia (SARS-COVID19) in X-Ray images empowered with initial clustering

“…K-mean k-means is a clustering model partitioning data in part (clusters). Technically, it partitions data mainly based on two steps [21]: first, it finds centroids ( ) that equal number of clusters and second aggregates data points ( ) with closest centroid. In (6) finds nearest centroid for data point K…”

“…In this paper, the Wrapper model is used for feature selection. Wrapper model is a feature selection method testing different groups of features and selecting a group that satisfying the best result [21]. It has applied features selection based on randomness.…”

“…Figure 2 illustrates the principles of the wrapper model with a metaheuristic for selecting the optimum feature. 247 limited boundaries either 0 or 1 [21]. The extending search space has enhanced the performance of metaheuristic algorithms.…”

Chronic kidney disease prediction model using machine learning approach

“…The "centre for disease control and prevention" states CD can be prevented at the start stage before going to the severe condition. An early detection or prediction of CD helps to reduce the severiority of the disease also cost effective to an individual [4], [5]. This paper concentrates on two CD's namely chronic kidney disease (CKD) and diabetes mellitus (DM).…”