| Autor: |
Nilashi, Mehrbakhsh, Ahmadi, Hossein, Shahmoradi, Leila, Mardani, Abbas, Ibrahim, Othman, Yadegaridehkordi, Elaheh |
| Předmět: |
|
| Zdroj: |
Journal of Soft Computing & Decision Support Systems; Oct2017, Vol. 4 Issue 5, p8-16, 9p |
| Abstrakt: |
The use of medical datasets has attracted the attention of researchers worldwide. Data mining techniques have been widely used in developing decision support systems for disease classification through a set of medical datasets. In this paper, we propose a predictive method for diseases prediction using machine learning techniques. The proposed method is developed through clustering, noise removal, and supervised machine learning techniques. Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Neural Network (NN), Adaptive Network-Based Fuzzy Inference System (ANFIS), Support Vector Regression (SVR) and Classification and Regression Trees (CART) are used for diseases prediction task. We also use the Principal Component Analysis (PCA) for dimensionality reduction and to address multi-collinearity problems in the experimental datasets. We test our proposed method on several public medical datasets. Experimental results on Wisconsin Diagnostic Breast Cancer, StatLog, Cleveland and Parkinson's telemonitoring datasets show has potential to be used as a decision support system in healthcare. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
