Assessment of cochlear electrophysiology in typically developing children and children with auditory processing disorder.

OBJECTIVE: Children with auditory processing disorder (APD) are reported to have abnormal auditory brainstem responses (ABR) but little is understood about their cochlear integrity. Poor cochlear integrity can affect neural responses. In this study, cochlear and auditory brainstem integrity was investigated in children with APD. METHOD: Twenty children with APD, sixteen typically developing children and twenty adults participated in this study. Click evoked electrocochleography (ECochG) and ABRs were recorded from all the participants. Cochlear responses were analyzed using a) latency and amplitude of summating potential; action potential, b) transmission time between summating potential and action potential, c) summating potential/action potential amplitude ratio and d) action potential latency difference to condensation and rarefaction polarity. Amplitude in the ABR components was examined. RESULTS: Children with APD showed similar cochlear function to the typically developing children. There were no significant differences in wave I amplitude between children with APD and typically developing children. However, wave V amplitude was significantly reduced in children with APD compared to typically developing children. CONCLUSION: In the absence of any functional differences in the cochlea, children with APD can show poor amplitude in the later components of the ABR. The ABR anomalies observed in children with APD arise due to poor neural processing, possibly after the first auditory synapse.

Comparison of machine learning models to classify Auditory Brainstem Responses recorded from children with Auditory Processing Disorder.

INTRODUCTION: Auditory brainstem responses (ABRs) offer a unique opportunity to assess the neural integrity of the peripheral auditory nervous system in individuals presenting with listening difficulties. ABRs are typically recorded and analyzed by an audiologist who manually measures the timing and quality of the waveforms. The interpretation of ABRs requires considerable experience and training, and inappropriate interpretation can lead to incorrect judgments about the integrity of the system. Machine learning (ML) techniques may be a suitable approach to automate ABR interpretation and reduce human error. OBJECTIVES: The main objective of this paper was to identify a suitable ML technique to automate the analysis of ABR responses recorded as a part of the electrophysiological testing in the Auditory Processing Disorder clinical test battery. METHODS: ABR responses recorded during routine clinical assessment from 136 children being evaluated for auditory processing difficulties were analyzed using several common ML algorithms: Support Vector Machines (SVM), Random Forests (RF), Decision Trees (DT), Gradient Boosting (GB), Extreme Gradient Boosting (Xgboost), and Neural Networks (NN). A variety of signal feature extraction techniques were used to extract features from the ABR waveforms as inputs to the ML algorithms. Statistical significance testing and confusion matrices were used to identify the most robust model capable of accurately identifying neurological abnormalities present in ABRs. RESULTS: Clinically significant features in the time-frequency representation of the signal were identified. The ML model trained using the Xgboost algorithm was identified as the most robust model with an accuracy of 92% compared to other models. CONCLUSION: The findings of the present study demonstrate that it is possible to develop accurate ML models to automate the process of analyzing ABR waveforms recorded at suprathreshold levels. There is currently no ML-based application to screen children with listening difficulties. Therefore, it is expected that this work will be translated into an evaluation tool that can be used by audiologists in the clinic. Furthermore, this work may aid future researchers in exploring ML paradigms to improve clinical test batteries used by audiologists in achieving accurate diagnoses.

The Medial Olivocochlear Reflex Is Unlikely to Play a Role in Listening Difficulties in Children.

The medial olivocochlear reflex (MOCR) has been implicated in several auditory processes. The putative role of the MOCR in improving speech perception in noise is particularly relevant for children who complain of listening difficulties (LiD). The hypothesis that the MOCR may be impaired in individuals with LiD or auditory processing disorder has led to several investigations but without consensus. In two related studies, we compared the MOCR functioning of children with LiD and typically developing (TD) children in the same age range (7-17 years). In Study 1, we investigated ipsilateral, contralateral, and bilateral MOCR using forward-masked click-evoked otoacoustic emissions (CEOAEs; n = 17 TD, 17 LiD). In Study 2, we employed three OAE types: CEOAEs (n = 16 TD, 21 LiD), stimulus frequency OAEs (n = 21 TD, 30 LiD), and distortion product OAEs (n = 17 TD, 22 LiD) in a contralateral noise paradigm. Results from both studies suggest that the MOCR functioning is not significantly different between the two groups. Some likely reasons for differences in findings among published studies could stem from the lack of strict data quality measures (e.g., high signal-to-noise ratio, control for the middle ear muscle reflex) that were enforced in the present study. The inherent variability of the MOCR, the subpar reliability of current MOCR methods, and the heterogeneity in auditory processing deficits that underlie auditory processing disorder make detecting clinically relevant differences in MOCR function impractical using current methods.

Crossed and uncrossed acoustic reflex growth functions in normal-hearing adults, typically developing children, and children with suspected auditory processing disorder.

OBJECTIVE: Previous data suggested that children with suspected auditory processing disorders (APD) often show elevated or absent acoustic reflex thresholds, especially in crossed conditions (e.g. Allen & Allan, 2014 ). This study further explored these effects by measuring acoustic reflex growth functions (ARGF). DESIGN: Crossed and uncrossed ARGF slopes were obtained by linear fits between reflex amplitudes and increases in activator level from threshold to 15 dB above it. STUDY SAMPLE: Normal-hearing adults, typically developing children and children with reported listening difficulties and suspected of having an APD, participated. RESULTS: The ARGF slopes were shallower in crossed than in uncrossed conditions for all groups but the magnitude of the effect was significantly greater in the children with suspected APD. There were no differences between the typically developing children and the adults. CONCLUSIONS: The results suggest shallower ARGFs in children with suspected APD. Given the role of the acoustic reflex in facilitating hearing speech in noise these findings may begin to shed light on physiologic explanations for some of the difficulties that are reported by children with suspected APD.

Contralateral inhibition of distortion product otoacoustic emissions in children with auditory processing disorders.

OBJECTIVE: The purpose of this study was to evaluate changes in distortion product otoacoustic emission (DPOAE) level elicited by contralateral noise in children with normal hearing, and those with auditory processing disorders (APD) whose audiometric thresholds were normal. It was hypothesized that children with APD would demonstrate smaller changes. DESIGN: Levels of DPOAEs were recorded for f(2) stimulus tones fixed at 2, 3, and 4 kHz while the f(1) tone was ramped around nominal stimulus frequency ratios of f(2)/f(1) = 1.22 and 1.10. Mean and maximum absolute changes resulting from contralateral broadband noise presented at 60 dB SPL were evaluated across the DPOAE frequency bands for each individual and for both groups of subjects. STUDY SAMPLE: Eight normal-hearing children and eight children with APD whose audiometric thresholds were normal participated. RESULTS: There were no significant differences in DPOAE inhibition between normal hearing and APD groups, or previously recorded adult data. Mean absolute changes were typically near 1 dB, except for f(2) = 4 kHz and the stimulus frequency ratio 1.22 where inhibition was only 0.5 dB. However, there were individual children in both groups who demonstrated larger DPOAE changes for some stimulus parameters. CONCLUSIONS: The inhibition of otoacoustic emissions requires further study in APD children.