Abstract: People now commonly suffer from chronic kidney disease (CKD). By detecting and treating those who are at risk for this condition as soon as feasible, a variety of serious problems, such as end-stage renal disease, elevated risk, and cardiovascular disease, may be prevented. Medical researchers can get a lot of help from the machine learning algorithm in accurately diagnosing the disease at the very beginning. Algorithms for machine learning and Big Data platforms have recently been combined to improve healthcare. This work presents hybrid machine learning methods that integrate extraction of the feature strategies and various algorithms of machine learning under classification technique related to massive data platforms to identify chronic kidney disease (CKD). In this study, logistic regression (LR), random forest (RF), decision tree (DT), support vector machine (SVM), Naive Bayes (NB), and gradient boosted trees were employed as six ensemble learning strategies for machine learning classification tasks (GBT Classifier). The results were validated using four evaluation techniques: accuracy, precision, recall, and F1-measure. The results demonstrated that the chosen features had helped SVM, DT, and GBT Classifiers operate at their peak levels.
Keywords: Chronic kidney, Naive Bayes (NB), decision tree (DT), logistic regression (LR), Gradient- Boosted Trees (GBT Classifier) and Random Forest (RF).
|
DOI:
10.17148/IJARCCE.2023.12206
