Classification of hearing based on pupillometry (Lebiecka-Johansen et al., 2025)

Purpose: Speech understanding in noise can be effortful, especially for people with hearing impairment. To compensate for reduced acuity, hearing-impaired (HI) listeners may be allocating listening effort differently than normal-hearing (NH) peers. We expected that this might influence measures derived from the pupil dilation response. To investigate this in more detail, we assessed the sensitivity of pupil measures to hearing-related changes in effort allocation. We used a machine learning–based classification framework capable of combining and ranking measures to examine hearing-related, stimulus-related (signal-to-noise ratio [SNR]), and task response–related changes in pupil measures.

Method: Pupil data from 32 NH (40–70 years old, M = 51.3 years, six males) and 32 HI (31–76 years old, M = 59 years, 13 males) listeners were recorded during an adaptive speech reception threshold test. Peak pupil dilation (PPD), mean pupil dilation (MPD), principal pupil components (rotated principal components [RPCs]), and baseline pupil size (BPS) were calculated. As a precondition for ranking pupil measures, the ability to classify hearing status (NH/HI), SNR (high/low), and task response (correct/incorrect) above random prediction level was assessed. This precondition was met when classifying hearing status in subsets of data with varying SNR and task response, SNR in the NH group, and task response in the HI group.

Results: A combination of pupil measures was necessary to classify the dependent factors. Hearing status, SNR, and task response were predicted primarily by the established measures—PPD (maximum effort), RPC2 (speech processing), and BPS (task anticipation)—and by the novel measures RPC1 (listening) and RPC3 (response preparation) in tasks involving SNR as an outcome or sometimes difficulty criterion.

Conclusions: A machine learning–based classification framework can assess sensitivity of, and rank the importance of, pupil measures in relation to three effort modulators (factors) during speech perception in noise. This indicates that the effects of these factors on the pupil measures allow for reasonable classification performance. Moreover, the varying contributions of each measure to the classification models suggest they are not equally affected by these factors. Thus, this study enhances our understanding of pupil responses and their sensitivity to relevant factors.

Supplemental Material S1. Overview of the correlations between pupil measures.

Supplemental Material S2. Descriptive statistics of pupil measures used for each of the classification models.

Supplemental Material S3. Distributions of pupil measures across three selected SNRs (-13 dB that was used in the model NH SNR; -7 dB from the range of overlapping SNRs; -1 dB with the largest median misclassification percentage) within the NH group.

Supplemental Material S4. Distributions of pupil measures across three selected SNRs (+7 dB; -6 dB from the range of overlapping SNRs; -1 dB with the largest median misclassification percentage) within the HI group.

Supplemental Material S5. Averaged pupil responses relative to baseline in the data subsets included across classification models.

Supplemental Materials 6-8. Markdown R scripts for reproduction of the analyses’ steps.

Lebiecka-Johansen, P., Zekveld, A. A., Wendt, D., Koelewijn, T., Muhammad, A. I., & Kramer, S. E. (2025). Classification of hearing status based on pupil measures during sentence perception. Journal of Speech, Language, and Hearing Research, 68(3), 1188–1208. https://doi.org/10.1044/2024_JSLHR-24-00005