Automated detection of morphology changes in ABR waves in normal hearing using an intelligent algorithm

Introduction In daily practice, measurements of auditory brainstem responses (ABR) are used to objectively assess the hearing ability. The basic neural activity of the patient"s brain interferes with the evoked potentials resulting in a low signal-to-noise ratio. Up to 2000 stimuli are applied and the corresponding results are averaged to enable a visual annotation of the potentials. The potentials are divided into characteristic waves. At present it is not possible to automatically distinguish normal outcomes from anomalous results, as there are no clear boundaries to pathological conditions.

Material and methods Transgenic mice with a modified ionic current in the inner hair cells (IHC) and significantly reduced amplitudes in wave I in the Click-BERA were visually evaluated and described in the publication Eckrich, Hecker et al. 2019 and compared with the corresponding wild type. The two mouse lines were not significantly different in the hearing threshold. According to signal theory, the power of a signal correlates with the square of its amplitude. If Gaussian distributed values are squared and summed up, this sum has a Χ² distribution. In our new approach to analyse ABR-results, we fit a Χ² distribution to the power of single waves I.

Results The parameter analyzed in our study is the power in a single sweep of wave I in the click ABR. The frequency density distribution of wave I power displays significant differences between the two mouse lines (wild type 20.6+/- 9.4 vs. mutant 6.7+/- 2.5)

Discussion The new algorithm presented here demonstrates impressively how decreasing ionic current ratios in the IHC notably impacts the analysis parameter, which creates ample opportunities for further discussions.

Funding information BMBF Projekt 13GW0286B

Publication History

Article published online:
19 April 2024