A data-driven approach to identify a rapid screener for auditory processing disorder testing referrals in adults

Abstract

Hearing thresholds form the gold standard assessment in Audiology clinics. However, ~ 10% of adult patients seeking audiological care for self-perceived hearing deficits have thresholds that are normal. Currently, a diagnostic assessment for auditory processing disorder (APD) remains one of the few viable avenues of further care for this patient population, yet there are no standard guidelines for referrals. Here, we identified tests within the APD testing battery that could provide a rapid screener to inform APD referrals in adults. We first analyzed records from the University of Pittsburgh Medical Center (UPMC) Audiology database to identify adult patients with self-perceived hearing difficulties despite normal audiometric thresholds. We then looked at the patients who were referred for APD testing. We examined test performances, correlational relationships, and classification accuracies. Patients experienced most difficulties within the dichotic domain of testing. Additionally, accuracies calculated from sensitivities and specificities revealed the words-in-noise (WIN), the Random Dichotic Digits Task (RDDT) and Quick Speech in Noise (QuickSIN) tests had the highest classification accuracies. The addition of these tests have the greatest promise as a quick screener during routine audiological assessments to help identify adult patients who may be referred for APD assessment and resulting treatment plans.

Figure 1

A normal audiogram does not guarantee robust hearing in everyday conditions. (A) Most recent patient records from UPMC audiology between 2015 and 2020 were analyzed to identify patients with bilateral normal audiograms based on the inclusion criteria listed, resulting in 7212 patients further analyzed. (B) Averaged hearing thresholds were better than 20 dB HL for left (blue, solid) and right (red, dashed) ears in these patients. (C) The median age distribution of these patients skewed towards young and middle age, with a median age of 35 years. (D) The primary presenting complaint for these patients was hearing loss or hearing in noise difficulties, followed by tinnitus, pressure/fullness, dizziness and otalgia. (E) Only 47 adult patients were further referred for APD testing. These patients also had normal or near normal bilateral audiograms (F), and a median age of 30 years (G). The primary presenting complaints in decreasing frequency were hearing loss/hearing in noise difficulties, tinnitus, dizziness, noise exposure, otalgia, fullness and hyperacusis (H).

Figure 2

The screening version of the Hearing Handicap Inventory for Adults identifies self-reported hearing difficulties in adult patients who underwent an APD assessment. Patient self-reports on the HHIA-S classified APD patients into various degrees of hearing handicap, with most patients reporting mild to moderate hearing handicap.

Figure 3

Deficits were concentrated in the binaural integration and speech-in-noise domains. Individual test data on various domains of testing are shown for the left (blue) and right (red) ears of patients assessed for APD. Shaded areas represent normal ranges for respective tests. Pie charts identify proportion of patients who tested within normal limits for each test. Tests cover the three domains of APD testing—binaural integration (A–D), speech in noise (E,F), and temporal processing (G,H).

Figure 4

Development of a rapid screener for APD referrals. (A) Across domains, only performance on the RDDT 3-pair test and the words-in-noise test were significantly correlated in patients assessed for APD. (B) Stepwise selection revealed the shortest path for capturing the greatest number of deficits in patients assessed for APD (red, solid) compared to all other combinations of tests (gray, dashed). The cumulative increase in hit rate with each successive addition of a test is shown on the y axis. RDDT random dichotic digits test, GIN gaps in noise test, FP frequency patterns test, QuickSIN quick speech in noise, DW Dichotic words test, WIN words-in-noise test. (C) Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and Accuracy for the top three tests identified via stepwise selection (RDDT, WIN, QuickSIN) contrasted with the lowest test (FP). Error bars indicate 95% confidence intervals.