Title :
A neural network expert system for computer-assisted analysis of blood-pressure data
Author :
Cagnoni, S. ; Coppini, G. ; Livi, R. ; Poli, R. ; Scarpelli, P.T. ; Valli, G.
Author_Institution :
Dept. of Electron. Eng., Florence Univ., Italy
Abstract :
The expert system described, based on a neural network architecture, analyzes a subject´s anamnesis and 24-hour blood-pressure monitoring, to diagnose hypertension and give advice about choice, timing, and dosage of the most appropriate treatment. It also includes a set of explanation tools, such as the `why?´ and the `what if . . .´ functions, which emulate the ones that are typical of symbolic expert systems. Ongoing tests on 50 subjects rated both sensibility and specificity above 90%
Keywords :
computer aided analysis; expert systems; haemodynamics; medical diagnostic computing; neural nets; 24 hr; anamnesis; blood-pressure data; computer-assisted analysis; hypertension diagnosis; neural network expert system; symbolic expert systems; Biomedical monitoring; Blood pressure; Computer architecture; Computer networks; Computerized monitoring; Diagnostic expert systems; Expert systems; Hypertension; Neural networks; Timing;
Conference_Titel :
Computers in Cardiology 1991, Proceedings.
Conference_Location :
Venice
Print_ISBN :
0-8186-2485-X
DOI :
10.1109/CIC.1991.169147
