Search

A common concern in individuals with cochlear implants (CIs) is difficulty following conversations in noisy environments and social settings. The ability to accomplish these listening tasks relies on the individual’s working memory abilities and draws upon limited cognitive resources to accomplish successful listening. For some individuals, allocating too much, can result deficits in speech perception and in long term detriments of quality of life. For this study, 31 CI users and NH controls completed a series of online behavioural tests and quality of life surveys, in order to investigate the relationship between visual and auditory working memory, clinical and behavioural measures of speech perception and quality of life and hearing. Results showed NH individuals were superior on auditory working memory and survey outcomes. In CI users, recall performance on the three working memory span tests declined from visual reading span to auditory listening in quiet and then listening in noise and speech perception was predictably worse when presented with noise maskers. Bilateral users performed better on each task compared to unilateral/HA and unilateral only users and reported better survey outcomes. Correlation analysis revealed that memory recall and speech perception ability were significantly correlated with sections of CIQOL and SSQ surveys along with clinical speech perception scores in CI users. These results confirm that hearing condition can predict working memory and speech perception and that working memory ability and speech perception, in turn, predict quality of life. Importantly, we demonstrate that online testing can be used as a tool to assess hearing, cognition, and quality of life in CI users.

There is a weak relationship between clinical and self-reported speech perception outcomes in cochlear implant (CI) listeners. Such poor correspondence may be due to differences in clinical and “real-world” listening environments and stimuli. Speech sounds in the real world are often accompanied by visual cues, background environmental noise and is generally in the context of a connected conversation. The aims of this study were to determine if brain responses to naturalistic speech could index speech perception and listening demand in CI users. Accordingly, we recorded high density EEG while CI users listened/watched a naturalistic stimulus (i.e., the television show, “The Office”). We used continuous EEG to quantify “speech neural tracking” (i.e., TRFs, temporal response functions) to the television show audio track and additionally 8–12 Hz (alpha) brain rhythms commonly related to listening effort. Background noise at three different signal-to-noise ratios (SNRs), +5, +10, and +15 dB were presented to vary the difficulty of following the television show mimicking a natural noisy environment. The task included an additional condition of audio-only (no video). After each condition, participants subjectively rated listening demand and the degree of words and conversations they felt they could understand. Fifteen CI users reported progressively higher degrees of listening demand and less words and conversation with increasing background noise. Listening demand and conversation understanding in the audio-only condition was comparable to that of the highest noise condition (+5 dB). The addition of the background noise reduced the degree of speech neural tracking. Mixed effect modeling showed that listening demand and conversation understanding were correlated to cortical speech tracking such that high demand and low conversation understanding lower associated with lower amplitude TRFs. In the high noise condition, greater listening demand was negatively correlated to parietal alpha power such that higher demand was related to lower alpha power. No significant correlations were observed between TRF/alpha and clinical speech perception scores. These results are similar to previous findings showing little relationship between speech perception and quality of life in CI users. However, the physiological responses to complex natural speech may anticipate aspects of quality-of-life measures such as self-perceived listening demand.

ImportanceThe United States Food & Drug Administration (FDA) passively monitors medical device performance and safety through submitted medical device reports (MDRs) in the Manufacturer and User Facility Device Experience (MAUDE) database. These databases can be analyzed for patterns and novel opportunities for improving patient safety and/or device design.ObjectivesThe objective of this analysis was to use supervised machine learning to explore patterns in reported adverse events involving cochlear implants.DesignThe MDRs for the top three CI manufacturers by volume from January 1st 2009 to August 30th 2019 were retained for the analysis. Natural language processing was used to measure the importance of specific words. Four supervised machine learning algorithms were used to predict which adverse event narrative description pattern corresponded with a specific cochlear implant manufacturer and adverse event type - injury, malfunction, or death.SettingU.S. government public database.ParticipantsAdult and pediatric cochlear patients.ExposureSurgical placement of a cochlear implant.Main Outcome MeasureMachine learning model classification prediction accuracy (% correct predictions).Results27,511 adverse events related to cochlear implant devices were submitted to the MAUDE database during the study period. Most adverse events involved patient injury (n = 16,736), followed by device malfunction (n = 10,760), and death (n = 16). Submissions to the database were dominated by Cochlear Corporation (n = 13,897), followed by MedEL (n = 7,125), and Advanced Bionics (n = 6,489). The random forest, linear SVC, naïve Bayes and logistic algorithms were able to predict the specific CI manufacturer based on the adverse event narrative with an average accuracy of 74.8%, 86.0%, 88.5% and 88.6%, respectively.Conclusions & RelevanceUsing supervised machine learning algorithms, our classification models were able to predict the CI manufacturer and event type with high accuracy based on patterns in adverse event text descriptions.Level of evidence3