A Predictive Model for Cochlear Implant Outcome in Children with Cochlear Nerve Deficiency

Machine learning-based prediction of the outcomes of cochlear implantation in patients with inner ear malformation

OBJECTIVE

The objectives of this study are twofold: first, to visualize the structure of malformed cochleae through image reconstruction; and second, to develop a predictive model for postoperative outcomes of cochlear implantation (CI) in patients diagnosed with cochlear hypoplasia (CH) and incomplete partition (IP) malformation.

METHODS

The clinical data from patients diagnosed with cochlear hypoplasia (CH) and incomplete partition (IP) malformation who underwent cochlear implantation (CI) at Beijing Tongren Hospital between January 2016 and August 2020 were collected. Radiological features were analyzed through 3D segmentation of the cochlea. Postoperative auditory speech rehabilitation outcomes were evaluated using the Categories of Auditory Performance (CAP) and the Speech Intelligibility Rating (SIR). This study aimed to investigate the relationship between cochlear parameters and postoperative outcomes. Additionally, a predictive model for postoperative outcomes was developed using the K-nearest neighbors (KNN) algorithm.

RESULTS

In our study, we conducted feature selection by using patients' imaging and audiological attributes. This process involved methods such as the removal of missing values, correlation analysis, and chi-square tests. The findings indicated that two specific features, cochlear volume (V) and cochlear canal length (CDL), significantly contributed to predicting the outcomes of hearing and speech rehabilitation for patients with inner ear malformations. In terms of hearing rehabilitation, the KNN classification achieved an accuracy of 93.3%. Likewise, for speech rehabilitation, the KNN classification demonstrated an accuracy of 86.7%.

CONCLUSION

The measurements obtained from the 3D reconstruction model hold significant clinical relevance. Despite the considerable variability in cochlear morphology across individuals, radiological features remain effective in predicting cochlear implantation (CI) prognosis for patients with inner ear malformations. The utilization of 3D segmentation techniques and the developed predictive model can assist surgeons in conducting preoperative cochlear structural measurements for patients with inner ear malformations. This, in turn, can offer a more informed perspective on the anticipated outcomes of cochlear implantation.

Can Cochlear Nerve Size Assessment With Magnetic Resonance Enhance the Understanding of Idiopathic Sudden Sensorineural Hearing Loss?

BACKGROUND AND OBJECTIVES

Idiopathic sudden sensorineural hearing loss (ISSHL) is a rapid loss of hearing, exceeding 30 dB in at least 3 consecutive frequencies within 3 days, without any identifiable cause despite thorough investigations. Currently, the etiology and pathogenesis of ISSHL have not been fully elucidated. This study aimed to assess the size of the cochlear nerve in patients with ISSHL and explore its relationship with pretreatment audiograms and treatment response. Subjects and.

METHODS

A total of 125 patients (59 [47.2%] women; mean age 47.7±13.8 years [minimum-maximum: 21-76]) and 60 healthy participants (27 [45%] women; mean age 45.7±16.8 years [minimum-maximum: 20-76]) as a control group were included in this study. The size of the cochlear nerve was assessed on the affected side, compared to the control group, as well as on the unaffected side. Pretreatment and posttreatment audiological values were also analyzed.

RESULTS

The cross-sectional area (CSA), vertical diameter (VD), and horizontal diameter (HD) of the CN were found to be smaller on the affected side of ISSHL patients compared to the control group (p<0.01; p=0.04; p=0.02, respectively). In the study group (affected side of ISSHL patients), there were no significant differences in VD, HD, and CSA values between pretreatment audiogram types (p=0.23; p=0.53; p=0.39, respectively), and initial hearing levels (p=0.16; p=0.22; p=0.23, respectively). Furthermore, there were no significant differences in VD, HD, and CSA values between the recovery groups according to Furuhashi criteria (p=0.18; p=0.37; p=0.27, respectively).

CONCLUSIONS

The size of the CN may be a risk factor for ISSHL, but it does not affect the type of audiogram curves and was not prognostic in terms of treatment response.

The Relationship Between Cochlear Implant Speech Perception Outcomes and Electrophysiological Measures of the Electrically Evoked Compound Action Potential

OBJECTIVE

This study assessed the relationship between electrophysiological measures of the electrically evoked compound action potential (eCAP) and speech perception scores measured in quiet and in noise in postlingually deafened adult cochlear implant (CI) users. It tested the hypothesis that how well the auditory nerve (AN) responds to electrical stimulation is important for speech perception with a CI in challenging listening conditions.

DESIGN

Study participants included 24 postlingually deafened adult CI users. All participants used Cochlear Nucleus CIs in their test ears. In each participant, eCAPs were measured at multiple electrode locations in response to single-pulse, paired-pulse, and pulse-train stimuli. Independent variables included six metrics calculated from the eCAP recordings: the electrode-neuron interface (ENI) index, the neural adaptation (NA) ratio, NA speed, the adaptation recovery (AR) ratio, AR speed, and the amplitude modulation (AM) ratio. The ENI index quantified the effectiveness of the CI electrodes in stimulating the targeted AN fibers. The NA ratio indicated the amount of NA at the AN caused by a train of constant-amplitude pulses. NA speed was defined as the speed/rate of NA. The AR ratio estimated the amount of recovery from NA at a fixed time point after the cessation of pulse-train stimulation. AR speed referred to the speed of recovery from NA caused by previous pulse-train stimulation. The AM ratio provided a measure of AN sensitivity to AM cues. Participants' speech perception scores were measured using Consonant-Nucleus-Consonant (CNC) word lists and AzBio sentences presented in quiet, as well as in noise at signal-to-noise ratios (SNRs) of +10 and +5 dB. Predictive models were created for each speech measure to identify eCAP metrics with meaningful predictive power.

RESULTS

The ENI index and AR speed individually explained at least 10% of the variance in most of the speech perception scores measured in this study, while the NA ratio, NA speed, the AR ratio, and the AM ratio did not. The ENI index was identified as the only eCAP metric that had unique predictive power for each of the speech test results. The amount of variance in speech perception scores (both CNC words and AzBio sentences) explained by the eCAP metrics increased with increased difficulty under the listening condition. Over half of the variance in speech perception scores measured in +5 dB SNR noise (both CNC words and AzBio sentences) was explained by a model with only three eCAP metrics: the ENI index, NA speed, and AR speed.

CONCLUSIONS

Of the six electrophysiological measures assessed in this study, the ENI index is the most informative predictor for speech perception performance in CI users. In agreement with the tested hypothesis, the response characteristics of the AN to electrical stimulation are more important for speech perception with a CI in noise than they are in quiet.

Cochlear implantation programming characteristics and outcomes of cochlear nerve deficiency

PURPOSE

Due to the specificity of cochlear implantation (CI) programming parameters and outcomes in cochlear nerve deficiency (CND) patients, this study aimed to investigate the correlation between programming parameters and outcomes and further compare the difference between normal and CND groups.

METHODS

Ninety (95 ears) CND patients (normal cochlea, 39; malformed cochlea, 56) and seventy-nine (81 ears) normal cochlea patients who underwent CI surgery with either Med-El or Cochlear devices were included. The programming parameters and outcomes evaluated by the questionnaires were collected and compared among the normal CND, malformed CND, and normal groups in the two device groups, and their correlation was analyzed.

RESULTS

In the CND group, a reduced stimulation rate, higher pulse width, and triphasic pulse were needed in some cases. The stimulus levels of the CND group were significantly higher than that of the normal group (p < 0.05), but the outcomes of the CND group were significantly worse than that of the normal group (p < 0.05), and the stimulus level was significantly correlated with the outcomes (p < 0.05). However, there was no difference between normal and malformed CND groups. The non-auditory response was observed in the CND group, especially the ones with malformations.

CONCLUSION

The CI programming parameters of some CND patients need to be adjusted, and a slower stimulation rate and higher pulse width are required sometimes. CND patients need a higher stimulus level than normal patients but their outcomes are poorer. Non-auditory response should be noticed in CND patients during programming.

Outcome of cochlear implantation in a case of cochlear aplasia with cochlear nerve deficiency

Cochlear nerve deficiency in cochlear aplasia is a contraindication for cochlear implantation (CI) anticipating poor auditory response. Few authors have reported auditory outcomes even without nerves following CI. This study outlines the audiological outcomes of a patient in early childhood with cochlear aplasia and cochlear nerve deficiency who underwent CI. Auditory and speech-language development were assessed using the Categories of Auditory Performance (CAP) scale, Speech Intelligibility Rating (SIR) scale and Ling-6 sound test; at the time of switch-on, after 6 and 12 months of auditory verbal therapy. Significant differences across CAP, SIR and Ling-6 sound detection scores were noted, with the highest mean scores at the 12th-month postimplantation, indicating substantial improvement in auditory and speech-language skills. In cochlear aplasia cases, residual cochlear elements and nerve fibres cannot be ruled out. Our report emphasises the need for research, as this has the potential to impact the existing guidelines for CI candidacy.

Molecular Genetic Etiology and Revisiting the Middle Ear Surgery Outcomes of Branchio-Oto-Renal Syndrome: Experience in a Tertiary Referral Center

OBJECTIVES

To explore the phenotypes and genotypes of patients with branchio-oto-renal (BOR) and branchio-otic (BO) syndrome, and to analyze the middle ear surgery outcomes qualitatively and quantitatively, proposing a factor usefully prognostic of surgical outcomes.

STUDY DESIGN

Retrospective cohort study.

SETTING

Tertiary referral center.

PATIENTS

Eighteen patients with BOR/BO syndrome in 12 unrelated Korean families.

INTERVENTION

Middle ear surgery, including either stapes surgery or ossicular reconstruction.

MAIN OUTCOME MEASURE

Clinical phenotypes, genotypes, and middle ear surgery outcomes.

RESULTS

Eight probands (66.7%) were confirmed genetically; the condition segregated as a dominant or de novo trait. Six EYA1 heterozygous variants were identified by exome sequencing and multiplex ligation-dependent probe amplification. All variants were pathogenic or likely pathogenic based on the ACMG/AMP guidelines. Two novel EYA1 frameshift variants (p.His373Phefs*4 and p.Gln543Asnfs*90) truncating a highly conserved C-terminal Eya domain were identified, expanding the genotypic spectrum of EYA1 in BOR/BO syndrome. Remarkably, middle ear surgery was individualized to ensure optimal audiological outcomes and afforded significant audiological improvements, especially in BOR/BO patients without enlarged vestibular aqueducts (EVAs). A significant difference in air-bone gap closure after middle ear surgery was noted between the two groups even after adjusting for confounders: -20.5 dB in ears without EVAs (improvement) but 0.8 dB in ears with EVAs (no change or deterioration). Furthermore, the success rate was significantly associated with the absence of EVA.

CONCLUSIONS

The results of this study were against the notion that middle ear surgery is always contraindicated in patients with BOR/BO syndrome, and an EVA could be a negative prognostic indicator of middle ear surgery in BOR/BO patients. This may aid to determine the strategy of audiological rehabilitation in patients with BOR/BO syndrome.

A 3-Year Follow-Up and Radiological Analysis of Cochlear Implantation Patients with Cochlear Nerve Deficiency and Modiolar Deficiency-Type Malformations

OBJECTIVE

Cochlear nerve deficiency (CND) is often combined with modiolar deficiency-type inner ear malformations, which cause variable cochlear implantation (CI) outcomes. We aimed to assess the postoperative development of auditory and speech perception in CND patients with modiolar deficiency-type malformations after 3 years of follow-up to determine the factors correlated with CI outcomes.

METHODS

Sixty-seven CND patients with modiolar deficiency-type malformations who underwent CI surgery were retrospectively reviewed. Modiolar deficiency-type malformations included common cavity (CC), cochlear hypoplasia (CH) (including CH-I and CH-II) and incomplete partition-I (IP-I). Categorical auditory performance (CAP) and the infant-toddler meaningful auditory integration scale (MAIS) were used to assess auditory ability. The speech intelligibility rating (SIR) and meaningful use of speech scale (MUSS) were used to assess the speech intelligibility of these CI patients. The CI outcomes were evaluated at 0, 12, 24 and 36 months after implant activation.

RESULTS

All patients demonstrated improvements in auditory ability and speech intelligibility after CI. There were no significant differences in CI outcomes at any time point according to the malformation type. The number of nerve bundles within the internal auditory canal (IAC) showed significant differences at 12, 24 and 36 months after CI ( p < 0.05). Patients with one nerve bundle had relatively poor CI outcomes.

CONCLUSIONS

CND patients with modiolar deficiency-type malformations showed continuous improvement in auditory and speech abilities after CI. Compared with malformations, the number of nerve bundles should be given more attention when selecting the side for CI.

Audiological characteristics and cochlear implant outcome in children with cochlear nerve deficiency

Objectives

This study aimed to examine the audiological characteristics and validity of predicting outcomes of cochlear implants (CIs) in children with cochlear nerve deficiency (CND) based on the internal auditory meatus (IAM) nerve grading system.

Methods

The audiological characteristics of 188 ears in 105 children diagnosed with CND were analyzed based on the IAM nerve grading system. In addition, 42 children with CND who underwent CI were also divided into four groups based on the system, and their auditory and speech performance at baseline (preoperative) and 6, 12, and 24 months after CI were analyzed and compared with those of the control group (n = 24) with a normal cochlear nerve (CN) and CI.

Results

The audiological test results showed no significant differences among the four CND groups in terms of elicited rates of distortion product otoacoustic emission (DPOAE) (p = 1.000), auditory brainstem response (ABR) (p = 0.611), and cochlear microphonic (CM) (p = 0.167). Hearing in the CND IV group was significantly better than that in the CND I group (p < 0.05). In children with CI, the auditory and speech performance of the control group was significantly higher than all CND groups from 6 to 24 months (p < 0.05) and 12 to 24 months (p < 0.05), respectively. Meanwhile, there were no significant differences between each pair group in the four CND groups (p > 0.05).

Conclusion

Children with CND, including those in whom the CN was not visualized by MRI, can benefit from CI. Additionally, the IAM nerve grading system could not predict the outcomes of CI in children with CND.

Functional Outcomes of Cochlear Implantation in Children with Bilateral Cochlear Nerve Aplasia

Background and Objectives: Many otologists face a dilemma in the decision-making process of surgical management of patients with cochlear nerve (CN) aplasia. The goal of this study is to provide fresh evidence on cochlear implantation (CI) results in patients with CN aplasia. Materials and Methods: We scrutinized functional outcomes in 37 ears of 21 children with bilateral CN aplasia who underwent unilateral or bilateral CI based on cross-sectional and longitudinal assessments. Results: The Categories of Auditory Performance (CAP) scores gradually improved throughout the 3-year follow-up; however, variable outcomes existed between individuals. Specifically, 90% of recipients with a 1-year postoperative CAP score ≤1 could not achieve a CAP score over 1 even at 3-year postoperative evaluation, while the recipients with a 1-year postoperative CAP score >1 had improved auditory performance, and 72.7% of them were able to achieve a CAP score of 4 or higher. Meanwhile, intraoperative electrically evoked compound action potential was not correlated with postoperative CAP score. Conclusions: Our results further refine previous studies on the clinical feasibility of CI as the first treatment modality to elicit favorable auditory performance in children with CN aplasia. However, special attention should be paid to pediatric patients with an early postoperative CAP score ≤1 for identification of unsuccessful cochlear implants and switching to auditory brainstem implants.

Cochlear Implantation Outcomes in Patients with Auditory Neuropathy Spectrum Disorder of Genetic and Non-Genetic Etiologies: A Multicenter Study

With diverse etiologies and clinical features, the management of pediatric auditory neuropathy spectrum disorder (ANSD) is often challenging, and the outcomes of cochlear implants (CIs) are variable. This study aimed to investigate CI outcomes in pediatric patients with ANSD of different etiologies. Thirty-six children with ANSD who underwent cochlear implantation between 2001 and 2021 were included. Comprehensive etiological analyses were conducted, including a history review, next-generation sequencing-based genetic examinations, and imaging studies using high-resolution computed tomography and magnetic resonance imaging. Serial behavioral and speech audiometry were performed before and after surgery, and the outcomes with CI were evaluated using the Categories of Auditory Performance (CAP) and Speech Intelligibility Rating (SIR) scores. By etiology, 18, 1, 1, and 10 patients had OTOF-related, WFS1-related, OPA1-related, and cochlear nerve deficiency (CND)-related ANSD, respectively. Six patients had no definite etiology. The average CI-aided behavioral threshold was 28.3 ± 7.8 dBHL, and those with CND-related ANSD were significantly worse than OTOF-related ANSD. The patients’ median CAP and SIR scores were 6 and 4, respectively. Favorable CI outcomes were observed in patients with certain etiologies of ANSD, particularly those with OTOF (CAP/SIR scores 5–7/2–5), WFS1 (CAP/SIR score 6/5), and OPA1 variants (CAP/SIR score 7/5). Patients with CND had suboptimal CI outcomes (CAP/SIR scores 2–6/1–3). Identifying the etiologies in ANSD patients is crucial before surgery and can aid in predicting prognoses.

Machine Learning-Based Prediction of the Outcomes of Cochlear Implantation in Patients With Cochlear Nerve Deficiency and Normal Cochlea: A 2-Year Follow-Up of 70 Children

Cochlear nerve deficiency (CND) is often associated with variable outcomes of cochlear implantation (CI). We assessed previous investigations aiming to identify the main factors that determine CI outcomes, which would enable us to develop predictive models. Seventy patients with CND and normal cochlea who underwent CI surgery were retrospectively examined. First, using a data-driven approach, we collected demographic information, radiographic measurements, audiological findings, and audition and speech assessments. Next, CI outcomes were evaluated based on the scores obtained after 2 years of CI from the Categories of Auditory Performance index, Speech Intelligibility Rating, Infant/Toddler Meaningful Auditory Integration Scale or Meaningful Auditory Integration Scale, and Meaningful Use of Speech Scale. Then, we measured and averaged the audiological and radiographic characteristics of the patients to form feature vectors, adopting a multivariate feature selection method, called stability selection, to select the features that were consistent within a certain range of model parameters. Stability selection analysis identified two out of six characteristics, namely the vestibulocochlear nerve (VCN) area and the number of nerve bundles, which played an important role in predicting the hearing and speech rehabilitation results of CND patients. Finally, we used a parameter-optimized support vector machine (SVM) as a classifier to study the postoperative hearing and speech rehabilitation of the patients. For hearing rehabilitation, the accuracy rate was 71% for both the SVM classification and the area under the curve (AUC), whereas for speech rehabilitation, the accuracy rate for SVM classification and AUC was 93% and 94%, respectively. Our results identified that a greater number of nerve bundles and a larger VCN area were associated with better CI outcomes. The number of nerve bundles and VCN area can predict CI outcomes in patients with CND. These findings can help surgeons in selecting the side for CI and provide reasonable expectations for the outcomes of CI surgery.

Value of Preoperative Imaging Results in Predicting Cochlear Nerve Function in Children Diagnosed With Cochlear Nerve Aplasia Based on Imaging Results

This study aimed to assess the function of the cochlear nerve using electrically evoked compound action potentials (ECAPs) for children with cochlear implants who were diagnosed with cochlear nerve aplasia and to analyze the correlation between preimplantation imaging results and ECAP responses. Thirty-five children diagnosed with cochlear nerve aplasia based on magnetic resonance imaging (MRI) were included. Preimplantation MRI and high-resolution computed tomography (HRCT) images were reconstructed, and the width of the bone cochlear nerve canal (BCNC), the diameter of the vestibulocochlear nerve (VCN), and the diameter of the facial nerve (FN) were measured. ECAP input/output (I/O) functions were measured at three electrode locations along the electrode array for each participant. The relationship between ECAP responses (including ECAP threshold, ECAP maximum amplitude, and slope of ECAP I/O function) and sizes of the BCNC and VCN was analyzed using Pearson's correlation coefficients. Our analysis revealed that ECAP responses varied greatly among individual participants. Overall, ECAP thresholds gradually increased, while maximum amplitudes and ECAP I/O function slopes gradually decreased, as the electrode location moved from the basal to the apical direction in the cochlea. ECAP responses exhibited no significant correlations with BCNC width or VCN diameter. The ratio of the VCN to FN diameters was significantly correlated with the slope of the ECAP I/O function and the maximum amplitude. BCNC width could not predict the function of the cochlear nerve. Compared with the absolute size of the VCN, the size of the VCN relative to the FN may represent an indicator for predicting the functional status of the cochlear nerve in children diagnosed with cochlear nerve aplasia based on imaging results.

Imaging and audiological features of children with cochlear nerve deficiency

Objective: Cochlear nerve deficiency (CND) accounts for 10-19% of hearing loss in children; this study investigated the imaging and audiological features of 25 CND children. Methods: A total of 563 children with an unpassed automatic auditory brainstem response were diagnosed with hearing loss in our department between December 2018 and December 2021, of which, the imaging and audiological features of 25 children (25/563, 4.4%) diagnosed with a CND were reviewed. Results: Twenty-one (21/25, 84.0%) CND children had unilateral deafness, and 4 cases of bilateral deafness. All deaf ears were diagnosed as severe hearing loss due to an auditory brainstem response. CM waves were recorded in 8 cases and DPOAE in 3 cases, suggesting the audiological characteristics of auditory neuropathy spectrum disorders (ANSD). MRI results indicated 23 cases had small cochlear nerves and 2 cases had absent cochlear nerves. No genetic mutations were identified in the 25 CND children. Conclusions: Most CND children had unilateral hearing loss; therefore, high-resolution MRI imaging of the internal auditory canal should be performed to detect the auditory nerve in children with severe hearing loss. Some CND children had characteristics of ANSD.

Functional Brain Connections Identify Sensorineural Hearing Loss and Predict the Outcome of Cochlear Implantation

Identification of congenital sensorineural hearing loss (SNHL) and early intervention, especially by cochlear implantation (CI), are crucial for restoring hearing in patients. However, high accuracy diagnostics of SNHL and prognostic prediction of CI are lacking to date. To diagnose SNHL and predict the outcome of CI, we propose a method combining functional connections (FCs) measured by functional magnetic resonance imaging (fMRI) and machine learning. A total of 68 children with SNHL and 34 healthy controls (HC) of matched age and gender were recruited to construct classification models for SNHL and HC. A total of 52 children with SNHL that underwent CI were selected to establish a predictive model of the outcome measured by the category of auditory performance (CAP), and their resting-state fMRI images were acquired. After the dimensional reduction of FCs by kernel principal component analysis, three machine learning methods including the support vector machine, logistic regression, and k-nearest neighbor and their voting were used as the classifiers. A multiple logistic regression method was performed to predict the CAP of CI. The classification model of voting achieves an area under the curve of 0.84, which is higher than that of three single classifiers. The multiple logistic regression model predicts CAP after CI in SNHL with an average accuracy of 82.7%. These models may improve the identification of SNHL through fMRI images and prognosis prediction of CI in SNHL.

Music perception and training for pediatric cochlear implant users

INTRODUCTION

Cochlear implants (CIs) are biomedical devices that restore sound perception for people with severe-to-profound sensorineural hearing loss. Most postlingually deafened CI users are able to achieve excellent speech recognition in quiet environments. However, current CI sound processors remain limited in their ability to deliver fine spectrotemporal information, making it difficult for CI users to perceive complex sounds. Limited access to complex acoustic cues such as music, environmental sounds, lexical tones, and voice emotion may have significant ramifications on quality of life, social development, and community interactions.

AREAS COVERED

The purpose of this review article is to summarize the literature on CIs and music perception, with an emphasis on music training in pediatric CI recipients. The findings have implications on our understanding of noninvasive, accessible methods for improving auditory processing and may help advance our ability to improve sound quality and performance for implantees.

EXPERT OPINION

Music training, particularly in the pediatric population, may be able to continue to enhance auditory processing even after performance plateaus. The effects of these training programs appear generalizable to non-trained musical tasks, speech prosody and, emotion perception. Future studies should employ rigorous control groups involving a non-musical acoustic intervention, standardized auditory stimuli, and the provision of feedback.

Flexible Real-Time Polymerase Chain Reaction-Based Platforms for Detecting Deafness Mutations in Koreans: A Proposed Guideline for the Etiologic Diagnosis of Auditory Neuropathy Spectrum Disorder

Routine application of next-generation sequencing in clinical settings is often limited by time- and cost-prohibitive complex filtering steps. Despite the previously introduced genotyping kit that allows screening of the 11 major recurring variants of sensorineural hearing loss (SNHL) genes in the Korean population, the demand for phenotype- and variant-specific screening kits still remains. Herein, we developed a new real-time PCR-based kit (U-TOP™ HL Genotyping Kit Ver2), comprising six variants from two auditory neuropathy spectrum disorder (ANSD) genes (OTOF and ATP1A3) and five variants from three SNHL genes (MPZL2, COCH, and TMC1), with a distinct auditory phenotype, making this the first genotyping kit dedicated to ANSD. The concordance rate with Sanger sequencing, sensitivity, and specificity of this genotyping kit were all 100%, suggesting reliability. The kit not only allows timely and cost-effective identification of recurring OTOF variants, but it also allows timely detection of cochlear nerve deficiency for those without OTOF variants. Herein, we provide a clinical guideline for an efficient, rapid, and cost-effective etiologic diagnosis of prelingual ANSD. Our study provides a good example of continuing to update new key genetic variants, which will continuously be revealed through NGS, as targets for the newly developed genotyping kit.

Prediction of the Functional Status of the Cochlear Nerve in Individual Cochlear Implant Users Using Machine Learning and Electrophysiological Measures

OBJECTIVES

This study aimed to create an objective predictive model for assessing the functional status of the cochlear nerve (CN) in individual cochlear implant (CI) users.

DESIGN

Study participants included 23 children with cochlear nerve deficiency (CND), 29 children with normal-sized CNs (NSCNs), and 20 adults with various etiologies of hearing loss. Eight participants were bilateral CI users and were tested in both ears. As a result, a total of 80 ears were tested in this study. All participants used Cochlear Nucleus CIs in their test ears. For each participant, the CN refractory recovery function and input/output (I/O) function were measured using electrophysiological measures of the electrically evoked compound action potential (eCAP) at three electrode sites across the electrode array. Refractory recovery time constants were estimated using statistical modeling with an exponential decay function. Slopes of I/O functions were estimated using linear regression. The eCAP parameters used as input variables in the predictive model were absolute refractory recovery time estimated based on the refractory recovery function, eCAP threshold, slope of the eCAP I/O function, and negative-peak (i.e., N1) latency. The output variable of the predictive model was CN index, an indicator for the functional status of the CN. Predictive models were created by performing linear regression, support vector machine regression, and logistic regression with eCAP parameters from children with CND and the children with NSCNs. One-way analysis of variance with post hoc analysis with Tukey's honest significant difference criterion was used to compare study variables among study groups.

RESULTS

All three machine learning algorithms created two distinct distributions of CN indices for children with CND and children with NSCNs. Variations in CN index when calculated using different machine learning techniques were observed for adult CI users. Regardless of these variations, CN indices calculated using all three techniques in adult CI users were significantly correlated with Consonant-Nucleus-Consonant word and AzBio sentence scores measured in quiet. The five oldest CI users had smaller CN indices than the five youngest CI users in this study.

CONCLUSIONS

The functional status of the CN for individual CI users was estimated by our newly developed analytical models. Model predictions of CN function for individual adult CI users were positively and significantly correlated with speech perception performance. The models presented in this study may be useful for understanding and/or predicting CI outcomes for individual patients.

Therapeutic challenges and clinical characteristics of single-sided deafness in children

INTRODUCTION

The clinical implications of single-sided deafness (SSD) in children has historically been underappreciated by patients and providers alike, despite a large body of literature on the wide-ranging neurocognitive, language, scholastic, and functional impairments that occur. Conventional amplification options are marked by variable results and frequent loss of follow-up.

METHODS

Retrospective case series for pediatric SSD from 2008 to 2018.

RESULTS

88 children with congenital SSD were identified. Seventeen (N = 17/88, 23.9%) passed their newborn hearing screen. Median age at first otolaryngology evaluation was 0.65 years (range 0.1-16.9 years). Most common etiologies included cochlear nerve deficiency (N = 39, CND, 44.3%), unknown (N = 30, 35.2%), inner ear malformation (N = 7, 8.0%), and congenital cytomegalovirus (N = 6, 6.8%). 32.5% of patients elected for continued observation only, followed by bone conduction hearing aid (27.7%), contralateral routing of sound aid (20.5%), conventional hearing aid (13.3%), or cochlear implant (6%). Lack of follow-up at ≥1 year was common (39.8%). Of those with device use data (N = 39), 84.7% reported either discontinued or <6 h of daily use.

CONCLUSIONS

Despite early diagnosis and evaluation, the pediatric SSD cohort is characterized by high rates of loss of follow-up and amplification discontinuation. Cochlear nerve deficiency is commonly seen in congenital SSD. Early specialist referral is critical for habilitation evaluation. Patients and caregivers should be educated on the significant implications of unilateral hearing loss.