Investigation of a matrix sentence test in noise: Reproducibility and discrimination function in cochlear implant patients

Objective: The aim of this study was to describe common properties (reproducibility, discrimination function, and its steepness) of matrix tests used for cochlear implant (CI) users and to obtain data for the German-language version matrix test, the Oldenburg sentence test (OLSA), presented in noise. Design: The speech reception thresholds (SRT) in noise were measured by means of an adaptive test procedure, and by measurement at various signal-to-noise ratios to determine the course of the entire discrimination function per subject. Study sample: The measurements were performed on 38 CI users fitted with a Cochlear (TM) Freedom (R) or a Cochlear (TM) Nucleus (R) 5 CI system. Results: The test-retest reproducibility showed a significant dependence on the SRT in noise. For the better performers, the test-retest difference was found to be smaller, while for the poorer performers the difference increased. For the better performers, the slope of the discrimination function at SRT (s50) was comparable to that for individuals with normal hearing, while for the poorer performers the s50 tended to be significantly reduced. Conclusions: As the CI users differed significantly in their SRT and their s50, a unified discrimination function for CI users must not be used. Further tailoring of the procedure may be required, especially for poorer CI performers.