Algorithms to diagnose NIHL
Reviewed by Joanna Lemanska

Finding an efficient diagnostic tool for noise-induced hearing loss (NIHL) has been of research interest for a long time. There are several algorithms that compare expected age-related deterioration of hearing with the actual audiogram. This study aimed to compare a new algorithm, Adjusted Notch Depth (AND), that uses the deepest notch depth to diagnose NIHL with other existing algorithms. Additionally, this algorithm did not use preliminary criteria and did not estimate age adjustments based on normalised data but on a regression equation. The association of self-reported noise exposure for 10 algorithms in total was compared, including four algorithms developed in this study. The audiograms were retrieved from three cycles of National Health and Nutritional Examination surveys in the US and divided into two groups, for participants without the noise exposure in the past and for participants with the noise exposure in the past. Each group consisted of 615 participants. Receiver operating characteristic (ROC) curves were used to estimate the diagnostic ability of all investigated algorithms. Only the AND algorithm, that did not include 6kHz thresholds in calculations and was based on single frequencies anchors, allowed for a statistically significant identification of the audiograms of participants that reported noise exposure in the past. Although these results are promising, the authors indicated that the true ability of the algorithm to diagnose NIHL was difficult to investigate as noise exposure does not necessarily lead to the noise-induced hearing loss, and can be only treated as a predictor of it.

Association of self-reported noise exposure and audiograms processed with algorithms proposed to quantify noise-induced hearing loss.
Pudrith C, Phillips S, Labban J.
INT J AUDIOL
2021:1-9.
Online ahead of print.