For expert systems intended to aid diagnosis, a structure with five levels
is proposed. These levels are the original area, the parameter and a reduce
d parameter layer, the classification and the final-decision layer. On the
basis of this structures, an expert system was developed specifically for n
eonatal hearing screening with transitory evoked otoacoustic emissions (TEO
AE). In a second step, this system was investigated for its suitability to
classify emissions, regardless of patient age. For the comparison measureme
nts in 252 mainly adult patients, some with an acquired hearing impairment,
were used. To adapt the pass/fail decision to the extended evaluation crit
eria, the false classifications from a first run with the new data were use
d for training. Thereafter the expert system, working with a wider data bas
is, classified the new data with a sensitivity that was increased by 4.8 %
to 97.2 %, and a 2.0 % improvement in specificity to 95.5 % when classifyin
g new data. These results, together with those of 97.3 % and 94.3 % achieve
d with exclusively neonatal TEOAE: classification, clearly show the advanta
ge of the expert system structures chosen, and document evidence of the pra
ctical applicability of the method.