Objective This study defines a screening procedure for cochlear implant (CI) candidacy in hearing aid users by using simple audiometric measures. Methods Within this retrospective study, hearing aid performance and audiometric measures in 185 subjects (318 ears) were analyzed. By means of a linear Naive Bayes classifier, the pure-tone average and the maximum monosyllabic score (PB_max) were used to predict the aided monosyllabic word score and CI candidacy. Results The two parameters PB_max and four-frequency hearing threshold average can be used to predict speech perception with hearing aids with reasonable accuracy for screening purposes. The classification has a sensitivity of 87% and a specificity of 91%. The classification can be represented by a simple linear formula. Conclusion CI candidacy can be predicted based on commonly used audiometric measures. Cochlear implant candidacy may be considered if the difference between the average pure-tone threshold (in decibels) and PBmax (in percent) exceeds 8.

Objectives/Hypothesis: To determine the improvement in word recognition score (WRS₆₅) after cochlear implant (CI) surgery in hearing aid (HA) users with preoperative hearing threshold ≤80 dB HL and inadequate speech recognition scores with HA. Secondarily, to identify predictive factors for WRS₆₅ with a CI (WRS₆₅[CI]) 6 months after surgery, derived from the standard German CI preoperative assessment.Study Design: Retrospective chart review.Methods: Retrospective review of all adult patients who received a Nucleus cochlear implant in the ear, nose, and throat department of the University Hospital of Erlangen between January 2010 and April 2019. The inclusion criteria were a preoperative hearing threshold ≤80 dB HL in the ear to receive the implantation, German as the native language, and at least 6 months postimplantation care at our center.Results: The inclusion criteria were met by 128 patients. All but two patients (98.4%) showed a significant improvement, WRS₆₅(CI) versus WRS₆₅ with an (HA) (WRS₆₅[HA]), of at least 15 percentage points (pp). The median improvement was 55 pp with a median WRS₆₅(CI) of 70%. Three preoperative audiometric measures, the maximum word recognition score, age at implantation, and WRS₆₅(HA) were identified as predictive factors for WRS₆₅(CI). For three‐quarters of the CI recipients, the score was not poorer than 12 pp below the predicted WRS₆₅(CI).Conclusions: For patients with a hearing loss ≤80 dB HL, cochlear implantation should be considered when speech perception with an HA is insufficient. The prediction model can support counseling in this patient group.Level of Evidence: 4 Laryngoscope, 131:E940–E945, 2021

This study investigated the speech perception of cochlear implant (CI) recipients with measurable preoperative ipsilateral speech perception. These data sh

Human brain performs remarkably well in segregating a particular speaker from interfering ones in a multispeaker scenario. We can quantitatively evaluate the segregation capability by modeling a relationship between the speech signals present in an auditory scene, and the listener's cortical signals measured using electroencephalography (EEG). This has opened up avenues to integrate neuro-feedback into hearing aids where the device can infer user's attention and enhance the attended speaker. Commonly used algorithms to infer the auditory attention are based on linear systems theory where cues such as speech envelopes are mapped on to the EEG signals. Here, we present a joint convolutional neural network (CNN)—long short-term memory (LSTM) model to infer the auditory attention. Our joint CNN-LSTM model takes the EEG signals and the spectrogram of the multiple speakers as inputs and classifies the attention to one of the speakers. We evaluated the reliability of our network using three different datasets comprising of 61 subjects, where each subject undertook a dual-speaker experiment. The three datasets analyzed corresponded to speech stimuli presented in three different languages namely German, Danish, and Dutch. Using the proposed joint CNN-LSTM model, we obtained a median decoding accuracy of 77.2% at a trial duration of 3 s. Furthermore, we evaluated the amount of sparsity that the model can tolerate by means of magnitude pruning and found a tolerance of up to 50% sparsity without substantial loss of decoding accuracy.

Objective: To determine speech perception in quiet and noise of adult cochlear implant listeners retaining a hearing aid contralaterally. Second, to investigate the influence of contralateral hearing thresholds and speech perception on bimodal hearing. Patients and methods: Sentence recognition with hearing aid alone, cochlear implant alone and bimodally at 6 months after cochlear implantation were assessed in 148 postlingually deafened adults. Data were analyzed for bimodal summation using measures of speech perception in quiet and in noise. Results: Most of the subjects showed improved sentence recognition in quiet and in noise in the bimodal condition compared to the hearing aid-only or cochlear implant-only mode. The large variability of bimodal benefit in quiet can be partially explained by the degree of pure tone loss. Also, subjects with better hearing on the acoustic side experience significant benefit from the additional electrical input. Conclusions: Bimodal summation shows different characteristics in quiet and noise. Bimodal benefit in quiet depends on hearing thresholds at higher frequencies as well as in the lower- and middle-frequency ranges. For the bimodal benefit in noise, no correlation with hearing threshold in any frequency range was found.