Fuzzy Neural Networks for Detection Kidney Diseases

Abstract

This study presents a learning mode-base Fuzzy Neural Networks (FNN) to detect chronic kidney disease (CKD). Combining the fuzzy set theory with the NN structure helps the proposed system to learn sensor data and adjust network parameters. The structure and algorithms of multi-input multi-output FNN are presented. The FNN algorithms implement the TSK type fuzzy rules. The learning of the system is executed by utilizing a gradient descent algorithm and c-means clustering. The presented system is trained using kidney datasets. The performance of the system is evaluated using mean accuracy, sensitivity, specificity and precision which were obtained as 99.75%, 100%, 99.34% and 99.9% correspondingly. The comparison of the results of simulation of the proposed model with the results of other existing algorithms demonstrates the efficiency of the presented FNN model. The experimental results indicate that the approach proposed offers reasonable accuracy of detection and has the potential to be applied in clinical practice.

Chronic kidney disease diagnosis using Fuzzy Knowledge Graph Pairs-based inference in the extreme case

“…On the other hand, as the electronic healthcare dataset overgrows, fuzzy techniques and fuzzy inference systems (FIS) are becoming more common for accurate and early diagnosis of common diseases in patients. For instance, some of the new proposed intelligent models can be introduced as Fuzzy inference system [5,6,7], Adaptive neuro-fuzzy inference system [8,9], Knowledge graph [10], Fuzzy knowledge graph (FKG) [11,14,21], Mamdani Complex fuzzy inference system (M-CFIS) [12,13], and so on. However, existing intelligent techniques used in these new methods have limitations when applied in decision-making support systems with limited input data.…”