The purpose of this study was to estimate the hearing levels, at the mid-fr
equencies, of 233 ears with sensorineural hearing loss by classifying the c
orresponding transiently evoked otoacoustic emissions (TEOAE) recordings in
to three threshold groups. A classification algorithm was based upon a disc
riminant analysis of fast Fourier transform (FFT) data, evoked by non-linea
r click stimuli of SO (+/-2) dB SPL per ear. To validate the efficiency of
the proposed methodology TEOAE recordings were initially grouped by mean he
aring level values of the 1 kHz and 2 kHz octaves into three threshold rang
es according to two strategy schemes: in the first, TEOAE data were assigne
d into 10-19 dB HL, 20-39 dB HL or greater than or equal to 40 dB HL groups
. In the second, TEOAE data were assigned into 10-29>dB H>, 30-39 dB HL or
greater than or equal to 40 dB HL groups. The most accurate prediction esti
mates were obtained from the second strategy scheme with a 90.9% accuracy i
n the 10-29 dB HL group, 82% in the 30-39 dB HL group and 71.4% in the grea
ter than or equal to 40 dB HL group.