Abstract The most intensifying communal health problem is chronic kidney disease (CKD) caused by various conditions that reduce the efficiency of the kidneys which results in other health complications, that ultimately lead to the demise of the affected individual. This paper describes an experiment that uses a novel approach to fill missing values and combines related attributes based on domain knowledge and it is evaluated by 4 different Machine Learning (ML) classification algorithms – Logistic Regression, an Extended Gradient Boosting trees, Artificial Neural Networks (ANN), and Support Vector Machine (SVM). Among these four algorithms, ANN and XG-Boost provide the better result of 0.97 F1- Score. The standard related data is taken from a repository called UCI machine learning, which has 400 individual data, 250 were reported to have CKD.
Alan : Mühendislik
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|