الفهرس 
Title :An approach for estimation transition stage for chronic kidney disease using hidden markov models
AbstractOnly 14 pages are availabe for public view
 |  | from | 124 |  |  |
| | | from | 124 | | |
Abstract
Early detection of kidney diseases considered to be one of the most critical factors in managing and controlling chronic kidney disease. Therefore, the current study has concerned with using Hidden Markov Model (HMM) and the most efficient data mining techniques to reveal and extract the hidden information from the clinical/ laboratory patient{u2019}s data to help physicians to maximize the accuracy of identify the disease severity stage and estimating transition rates between the chronic kidney disease Stages. The results of Probabilistic Neural Networks (PNN), Multilayer Perceptron (MLP), Support Vector Machine (SVM) and Radial Basis Function (RBF) algorithms have been compared, the results showed that Using the Probabilistic Neural Network algorithm with the HMM gives better classification and prediction performance for the severity stage of patients{u2019} chronic kidney disease. There are two published papers extracted from this thesis {u2022} Rady, El-Houssainy A., and Ayman S. Anwar. 2Prediction of kidney disease stages using data mining algorithms.3 Informatics in Medicine Unlocked (2019): 100178.,1-7. {u2022} Rady, El-Houssainy A., and Ayman S. Anwar. 2A note on Markov Models and chronic Diseases.3 Proceedings of the 52th Annual International Conference on Statistics, Computer Sciences and Operations Research, Institute of Statistical Studies and Research, Cairo University