A novel enhanced decision tree model for detecting chronic kidney disease

Abstract

Prediction of diseases is sensitive as any error can result in the wrong person's treatment or not treating the right patient. Besides, some features distinguish a disease from curable to fatal or curable to chronic disease. Data mining techniques have been widely used in health-related research. The researchers, so far, could attain around 97 percent accuracy using several methods. Some researchers have demonstrated that the selection of correct features increases the prediction accuracy. This research work propose a method to distinguish between chronic and non-chronic kidney disease, identify its crucial features without reducing the accuracy of prediction, and a prediction algorithm to eliminate the possibility of under or overfitting. This study uses the recursive feature elimination (RFE) method that selects an optimal subset of features and an ensemble algorithm, the enhanced decision tree (EDT), to predict the disease. The results obtained in this paper show that the accuracy level of EDT is not changed with the removal of less significant features, thus enabling the decision-makers to concentrate on few features to reduce time and error of treatment. EDT establishes substantially high consistency in predicting, with or without feature selection, the disease.

A Hadoop‐big data analytic model to predict and classify chronic kidney diseases using improved fractional rough fuzzy K‐means clustering and extreme gradient boost rat swarm optimizer

“…The proposed method is activated in python utilizing Keras, Scikit‐learn, Opencv library on Intel Xeon processor using 128 GB of RAM through one NVIDIA GeForce GTX 1080 Ti GPU card. The performance of the proposed method is compared with existing CCKD‐RFE‐DT, 23 CCKD‐LR, 31 and CCKD‐MKC‐SVM methods.…”

“…The main contributions of this article are: A Hadoop‐big data based chronic kidney diseases prediction and classification utilizing IF‐RFKM clustering and XG boost rat swarm optimizer (IF‐RFKM‐XG‐RSO) is proposed. The proposed big data based analytical mode combines enhanced data mining technique including clustering, machine learning, optimization approaches. IF‐RFKM 20 clustering method is deemed for chronic kidney disease prediction. This disease is classified using XG boost classifier 21 for classifying the stages of chronic kidney diseases as normal and abnormal. For optimizing the parameters of the XG boost classifier, rat swarm optimization 22 algorithm is proposed. The data is generated randomly from chronic kidney disease dataset. The proposed method is activated in Python, its performance is examined with performance metrics, like accuracy, F1‐score, precision, recall. The efficiency of the proposed method is compared to the existing methods, such as CCKD‐RFE‐DT, 23 CCKD‐LR, and CCKD‐MKC‐SVM 24 …”

“…• The efficiency of the proposed method is compared to the existing methods, such as CCKD-RFE-DT, 23 CCKD-LR, and CCKD-MKC-SVM. 24 The rest of this article is designed as: Section 2 reviews the recent studies, Section 3 explains about the proposed methodology, Section 4 proves the result with discussion, Section 5 concludes this article.…”

Using machine learning methods to predict the lactate trend of sepsis patients in the ICU

“…Feature selection strategies on clinical data provide the right parameters to analyze a certain disease, treatment cost reduction, and reduce computational burden [17]. To achieve these goals, we do a further investigation on variable space.…”

“…These classi ers are Naïve Bayes (NB), J48 Decision Tree, Logistic Regression (LR), Random Forest (RF), and Logistic Model Tree (LMT). Naïve Bayes is a traditional and simple machine learning approach that contemplates dataset attributes as an independent [17]. The outputs are considered as class probabilities.…”