Factors affecting open-set word recognition in adults with cochlear implants

Abstract

Objective: A great deal of variability exists in the speech-recognition abilities of postlingually deaf adult cochlear implant (CI) recipients. A number of previous studies have shown that duration of deafness is a primary factor affecting CI outcomes; however, there is little agreement regarding other factors that may affect performance. The objective of the present study was to determine the source of variability in CI outcomes by examining three main factors, biographic/audiologic information, electrode position within the cochlea, and cognitive abilities in a group of newly implanted CI recipients.

Design: Participants were 114 postlingually deaf adults with either the Cochlear or Advanced Bionics CI systems. Biographic/audiologic information, aided sentence-recognition scores, a high resolution temporal bone CT scan and cognitive measures were obtained before implantation. Monosyllabic word recognition scores were obtained during numerous test intervals from 2 weeks to 2 years after initial activation of the CI. Electrode position within the cochlea was determined by three-dimensional reconstruction of pre- and postimplant CT scans. Participants' word scores over 2 years were fit with a logistic curve to predict word score as a function of time and to highlight 4-word recognition metrics (CNC initial score, CNC final score, rise time to 90% of CNC final score, and CNC difference score).

Results: Participants were divided into six outcome groups based on the percentile ranking of their CNC final score, that is, participants in the bottom 10% were in group 1; those in the top 10% were in group 6. Across outcome groups, significant relationships from low to high performance were identified. Biographic/audiologic factors of age at implantation, duration of hearing loss, duration of hearing aid use, and duration of severe-to-profound hearing loss were significantly and inversely related to performance as were frequency modulated tone, sound-field threshold levels obtained with the CI. That is, the higher-performing outcome groups were younger in age at the time of implantation, had shorter duration of severe-to-profound hearing loss, and had lower CI sound-field threshold levels. Significant inverse relationships across outcome groups were also observed for electrode position, specifically the percentage of electrodes in scala vestibuli as opposed to scala tympani and depth of insertion of the electrode array. In addition, positioning of electrode arrays closer to the modiolar wall was positively correlated with outcome. Cognitive ability was significantly and positively related to outcome; however, age at implantation and cognition were highly correlated. After controlling for age, cognition was no longer a factor affecting outcomes.

Conclusion: There are a number of factors that limit CI outcomes. They can act singularly or collectively to restrict an individual's performance and to varying degrees. The highest performing CI recipients are those with the least number of limiting factors. Knowledge of when and how these factors affect performance can favorably influence counseling, device fitting, and rehabilitation for individual patients and can contribute to improved device design and application.

Figure 1

CT derived image of a participant’s electrode array (Contour Advance) and corresponding markers used to measure array position. See text for description.

Figure 2

Examples of tightly-wrapped, loosely-wrapped and deeply-inserted electrode arrays positioned in ST for the Nucleus Contour, Nucleus Contour Advance, and AB HiFocus I. See text for description.

Figure 3

A participant’s CNC word scores over time (open circles), the corresponding logistic curve fit (dotted line), and the four post-implant word recognition metrics. CNC Initial Score for this participant was 13.2%. CNC Final Score was 67%; CNC Rise Time (RT) to 90% of the CNC Final Score was 6.9 months, and CNC Diff Score was 53.8%.

Figure 4

The logistic curves for each of the participants and their assigned outcome group. The box plot shows the upper and lower quartiles about the median. The upper whisker represents the 90^th rank-order percentile of all data. The lower whisker represents the 10^th rank-order percentile of all data, and the filled circles represent individuals beyond those limits. The panel on the far right indicates the range of rank-order percentages defined for each group.

Figure 5

CNC Final Score for each participant rank ordered from lowest to highest score and each participant’s corresponding outcome group.

Figure 6

Histograms in panels (a–c) display the non-normal distribution of CNC Initial Score, CNC Final Score, and CNC RT, respectively. Panel (d) displays the normal distribution of CNC Diff Score.

Figure 7

Scatter plots of select biographic/audiologic factors plotted in relation to the six outcome groups, Group 1 (poorest performers) and Group 6 (highest performers) (panels a–d, f). Panel (e) is a scatter plot of Pre-Implant Sentence Recognition vs. CNC Final Score for all participants. The different symbols represent the six outcome groups.

Figure 8

Scatter plots of select electrode position factors in relation to the six outcome groups.

Figure 9

A scatter plot of Wrapping Factor vs. CNC Final Score for 59 participants with electrode arrays positioned in ST.

Figure 10

Scatter plots of the 1^st PC of Cognitive Factors (raw data) and 1^st PC of Cognitive Factors (standardized data) in relation to the six outcome groups.

Figure 11

Scatter plot of 1^st PC of Cognitive Factors (raw data) vs. Age at CI for all 114 participants. The different symbols represent the six outcome groups. Participants to the left of the dashed vertical line are < 65 years old and those to the right are ≥ to 65 years.

Figure 12

A mid-modiolar cochlear cross section showing a hypothetical ST electrode array placment (filled circles) compared to placement of an electrode array translocated to SV (open circles).