Title :
A new approach to medical diagnosis
Author :
Schizas, C.N. ; Pattichis, C.S. ; Middleton, L.T.
Author_Institution :
Dept. of Comput Sci., Cyprus Univ., Nicosia, Cyprus
Abstract :
The diagnostic usefulness of artificial neural networks (ANNs) is explored by means of an integrated system for medical diagnosis. The models were developed by using the unsupervized self organizing feature maps algorithm. Clinical and laboratory data for training and testing the ANNs was collected from 71 subjects by applying examination protocols that were developed by experts in the appropriate fields. The diagnostic yield obtained by the examined models was in the region of 80 to 90%
Keywords :
medical diagnostic computing; medical expert systems; neural nets; self-organising feature maps; artificial neural networks; integrated system; medical diagnosis; unsupervized self organizing feature maps algorithm; Artificial neural networks; Diseases; Genetics; Laboratories; Medical diagnosis; Muscles; Neuromuscular; Protocols; Spinal cord; Testing;
Conference_Titel :
Biomedical Engineering Days, 1992., Proceedings of the 1992 International
Conference_Location :
Istanbul
Print_ISBN :
0-7803-0743-7
DOI :
10.1109/IBED.1992.247114
