Neurofuzzy Classification of the Effect of Diabetes Mellitus on Carotid Artery

Authors:
Selami Serhatlioglu;Zulkif Bozgeyik;Yusuf Ozkan;Firat Hardalac;İ/nan Gü/ler
Affiliations:
Department of Radiology, Firat University Faculty of Medicine, Elazig, Turkey/ sserhatlioglu@firat.edu.tr;Department of Radiology, Firat University Faculty of Medicine, Elazig, Turkey;Department of Internal Medicine, Firat University Faculty of Medicine, Elazig, Turkey;Department of Biophysics, Firat University Faculty of Medicine, Elazig, Turkey;Department of Electronics and Computer Education, Gazi Ü/niversity, Ankara, Turkey
Venue:
Journal of Medical Systems
Year:
2003

Citing 5
Cited 2

Fuzzy neural networks: a survey

Fuzzy Sets and Systems
A neuro-fuzzy method to learn fuzzy classification rules from data

Fuzzy Sets and Systems - Special issue: application of neuro-fuzzy systems
NEFCLASSmdash;a neuro-fuzzy approach for the classification of data

SAC '95 Proceedings of the 1995 ACM symposium on Applied computing
Foundations of Neuro-Fuzzy Systems

Foundations of Neuro-Fuzzy Systems
Compensatory fuzzy neural networks-based intelligent detection of abnormal neonatal cerebral Doppler ultrasound waveforms

IEEE Transactions on Information Technology in Biomedicine

Soft computing in medicine

Applied Soft Computing
A survey on use of soft computing methods in medicine

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Here, we present a new clasification system for the effects of diabetes mellitus (DM) on carotid artery by using neurofuzzy system. Blood flow hemodynamics were obtained from 118 carotid arteries of 59 patients with DM by using 7.5 MHz transducer and Doppler-M unit. Vmax = peak systole, Vmin = end diastole, resistive index (RI), and pulsatile index (PI) were measured with the use of Doppler sonography. These values were applied to neurofuzzy system using NEFCLASS model. With the increase of epoch from 200 to 500 and pruning of fuzzy rules, our classification system was found to be successful in 85% of the cases. In 100 of 118 patients the classificitaion system was found to be correct. Our findings suggest that with the application of Doppler signal parameters from carotid arteries to neurofuzzy system may produce a new and reliable classification system for diagnosing diameter stenosis.