Development of Machine-Learning Models for Tinnitus-Related Distress Classification Using Wavelet-Transformed Auditory Evoked Potential Signals and Clinical Data.

Tinnitus is a highly prevalent condition, affecting more than 1 in 7 adults in the EU and causing negative effects on sufferers' quality of life. In this study, we utilised data collected within the "UNITI" project, the largest EU tinnitus-related research programme. Initially, we extracted characteristics from both auditory brainstem response (ABR) and auditory middle latency response (AMLR) signals, which were derived from tinnitus patients. We then combined these features with the patients' clinical data, and integrated them to build machine learning models for the classification of individuals and their ears according to their level of tinnitus-related distress. Several models were developed and tested on different datasets to determine the most relevant features and achieve high performances. Specifically, seven widely used classifiers were utilised on all generated datasets: random forest (RF), linear, radial, and polynomial support vector machines (SVM), naive bayes (NB), neural networks (NN), and linear discriminant analysis (LDA). Results showed that features extracted from the wavelet-scattering transformed AMLR signals were the most informative data. In combination with the 15 LASSO-selected clinical features, the SVM classifier achieved optimal performance with an AUC value, sensitivity, and specificity of 92.53%, 84.84%, and 83.04%, respectively, indicating high discrimination performance between the two groups.

Development and Evaluation of Automated Tools for Auditory-Brainstem and Middle-Auditory Evoked Potentials Waves Detection and Annotation.

Auditory evoked potentials (AEPs) are brain-derived electrical signals, following an auditory stimulus, utilised to examine any obstructions along the brain neural-pathways and to diagnose hearing impairment. The clinical evaluation of AEPs is based on the measurements of the latencies and amplitudes of waves of interest; hence, their identification is a prerequisite for AEP analysis. This process has proven to be complex, as it requires relevant clinical experience, and the existing software for this purpose has little practical use. The aim of this study was the development of two automated annotation tools for ABR (auditory brainstem response)- and AMLR (auditory middle latency response)-tests. After the acquisition of 1046 raw waveforms, appropriate pre-processing and implementation of a four-stage development process were performed, to define the appropriate logical conditions and steps for each algorithm. The tools' detection and annotation results, regarding the waves of interest, were then compared to the clinicians' manual annotation, achieving match rates of at least 93.86%, 98.51%, and 91.51% respectively, for the three ABR-waves of interest, and 93.21%, 92.25%, 83.35%, and 79.27%, respectively, for the four AMLR-waves. The application of such tools in AEP analysis is expected to assist towards an easier interpretation of these signals.

Binaural Interaction Component of Middle Latency Response in Children Suspected to Central Auditory Processing Disorder.

Binaural processing disorder is an important deficit in children with (C)APD so binaural processing evaluations are crucial. There are subjective and objective tests for assessing binaural processing. Subjective tests require patient attention and active so objective evaluation of binaural processing is important. The aim of present study was investigating binaural interaction component (BIC) of middle latency response (MLR) in children suspected to (C)APD. Sixty 8-12 year-old children suspected to (C)APD and sixty normal children were selected based on inclusion criteria. Both groups were matched in terms of sex (40 boys and 20 girls) and age (9.05 ± 1.25 years old). MLR test (monaural right ear, monaural left ear and binaural) was performed in all the cases and BIC was calculated by subtracting binaural response from summed monaural responses. Independent t test showed that latency of Pa and Na (ms), Pa-Na amplitude (µv), BIC latency (ms) and amplitude (µv) were significantly different from normal subjects (p value ≤0.001). Present study showed that MLR and BIC of MLR are clinically available and objective tests that can be used to determining children suspected to (C)APD. These tests might have the potential to separating normal children from children with (C)APD objectively.

A Review of the Role of Auditory Evoked Potentials in Mild Traumatic Brain Injury Assessment.

Around 75% to 90% of people who experience a traumatic brain injury (TBI) are classified as having a mild TBI (mTBI). The term mTBI is synonymous with concussion or mild head injury (MHI) and is characterized by symptoms of headache, nausea, dizziness, and blurred vision. Problems in cognitive abilities such as deficits in memory, processing speed, executive functioning, and attention are also considered symptoms of mTBI. Since these symptoms are subtle in nature and may not appear immediately following the injury, mTBI is often undetected on conventional neuropsychological tests. Current neuroimaging techniques may not be sensitive enough in identifying the array of microscopic neuroanatomical and subtle neurophysiological changes following mTBI. To this end, electrophysiological tests, such as auditory evoked potentials (AEPs), can be used as sensitive tools in tracking physiological changes underlying physical and cognitive symptoms associated with mTBI. The purpose of this review article is to examine the body of literature describing the application of AEPs in the assessment of mTBI and to explore various parameters of AEPs which may hold diagnostic value in predicting positive rehabilitative outcomes for people with mTBI.

Evaluating Auditory Pathway by Electrical Auditory Middle Latency Response and Postoperative Hearing Rehabilitation.

Objective: To establish an effective detection method to evaluate auditory pathway in patients by electrical evoked middle latency response (EMLR) before artificial cochlear implantation, and to analyze the relationship between postoperative hearing rehabilitation and auditory cortex functions. Methods: Twenty-three patients with artificial cochlear implant were recruited. EMLR was measured after adjusting the depth of anesthesia. The electrical auditory brainstem response (EABR) mode with monopolar stimulation and two-phase alternating current square waves was selected. The parameters of EMLR waveforms were recorded by the EABR measurement system. Nerve response telemetry (NRT) was examined by measuring threshold level (T value) and comfortable level (C value) 1 month after power-on, and hearing and speech development was followed up 12 months later.Results: The detection rate of EMLR was 95.65%. The waveforms of EMLR were comparable to those of auditory middle latency response (AMLR), showing decreased latency and interval but similar amplitude. The induction rate of NRT was 69.23%, which was much lower than that of EMLR. The EMLR thresholds were significantly correlated to the T and C values, and were comparable to the T values numerically. The Spearman's r value between EMLR waveforms and CAP scores after using the cochlear implant for 12 months was 0.673 (P < 0.01). Conclusion: An effective detection method to measure EMLR before artificial cochlear implant was established. The thresholds of EMLR were lower than those of NRT. The method can be useful for objective evaluation of auditory cortex functions and postoperative hearing rehabilitation.

Auditory brainstem, middle and late latency responses to short gaps in noise at different presentation rates.

OBJECTIVE: The effects of rate on auditory-evoked potentials (AEP) to short noise gaps (12 ms) recorded at high sampling rates using wide-band filters were investigated. DESIGN: Auditory brainstem (ABR), middle latency (MLR), late latency (LLR) and steady-state (ASSR) responses were simultaneously recorded in adult subjects at four gap rates (0.5, 1, 5 and 40 Hz). Major components (V, Na, Pa, Nb, Pb, N1 and P2) were identified at each rate and analysed for latency/amplitude characteristics. Gap responses at 40 Hz were recovered from Quasi-ASSRs (QASSR) using the CLAD deconvolution method. STUDY SAMPLE: Fourteen right ears of young normal hearing subjects were tested. RESULTS: All major components were present in all subjects at 1 Hz. P1 (P50) appeared as a low-pass filtered component of Pa and Pb waves. At higher rates, N1 and P2 disappeared completely while major ABR-MLR components were identified. Peak latencies were mostly determined by noise onsets slightly delayed by offset responses. CONCLUSIONS: Major AEP components can be recorded to short gaps at 1 Hz using high sampling rates and wide-band filters. At higher rates, only ABR and MLRs can be recorded. Such simultaneous recordings may provide a complete assessment of temporal resolution and processing at different levels of auditory pathways.