Computerized classification of corpus cavernosum electromyogram signals bythe use of discriminant analysis and artificial neural networks to supportdiagnosis of erectile dysfunction
B. Kellner et al., Computerized classification of corpus cavernosum electromyogram signals bythe use of discriminant analysis and artificial neural networks to supportdiagnosis of erectile dysfunction, UROL RES, 28(1), 2000, pp. 6-13
Corpus cavernosum electromyogram (CC-EMG) provides diagnostic information o
n cavernous autonomic innervation and a measure of the degree to which the
cavernous smooth muscle cells are intact. The complicated CC-EMG is evaluat
ed and used in the diagnosis of patients suffering from erectile dysfunctio
n. The evaluation procedure has been simplified by applying digital signal
processing techniques. Since mathematically-based interpretations require q
uantitative data, spectral analysis was performed. The derived biosignals w
ere analyzed by fast Fourier transform (FFT). Besides various other spectra
l parameters, specific frequency bands were determined in the power spectru
m using factor analysis. The parameters were used for the computerized clas
sification of normal and pathological CC-EMG data and the classification wa
s performed using two independent methods: discriminant analysis (DA) and a
rtificial neural networks (ANN). A medical expert analyzed a total of 200 C
C-EMG recordings from patients with and without erectile dysfunction and se
parated these into normal (136) and pathological (64) cases. Although each
independent method had already resulted in a relatively high number of corr
ect classifications, the classification success rate could be slightly impr
oved by using a combination of both classification methods. A total of 72.7
9% and 77.94% were successfully classified using DA and ANN, respectively.
The combination of both methods increased the classification success to 80.
15%. The results of this study enabled impartial evaluation of the CC-EMC s
ignals for clinical diagnostic purposes of erectile dysfunction. This metho
d provided an objective and easy way to analyze the CC-EMG. Furthermore, th
is results in patient diagnosis becoming an easier task for less experience
d doctors, since little knowledge of the raw signal is needed.