A neural network approach to the prediction of pure tone thresholds with distortion product emissions

Distortion Product Emission (DPE) growth functions, demographic data, and pure tone thresholds were recorded in 229 normal-hearing and hearing-impaired ears. Half of the data set (115 ears) was used to train a set of neural networks to map DPE and demographic features to pure tone thresholds at six frequencies in the audiometric range. The six networks developed from this training process were then used to predict pure tone thresholds in the remaining 114-ear data set. When normal pure tone threshold was defined as a threshold less than 20 dB HL, frequency-specific prediction accuracy varied from 57% (correct classification of hearing impairment at 1025 Hz) to 100% (correct classification of hearing impairment at 2050 Hz). Overall prediction accuracy was 90% for impaired pure tone thresholds and 80% for normal pure tone thresholds. This neural network approach was found to be more accurate than discriminant analysis in the prediction of pure tone thresholds. It is concluded that a general strategy exists whereby DPE measures can accurately categorize pure tone thresholds as normal or impaired in large populations of ears with purely cochlear hearing dysfunction.