A Machine Learning Based Clustering Protocol for Determining Hearing Aid Initial Configurations from Pure-Tone Audiograms.
Ontology highlight
ABSTRACT:
SUBMITTER: Belitz C
PROVIDER: S-EPMC8299699 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:PurposeThis study aimed to (a) compare the Revised Hearing Handicap Inventory (RHHI) and pure-tone average (PTA) in their abilities to predict hearing aid use and (b) report the optimal cut-point values on the RHHI and PTA that predict hearing aid use.MethodParticipants were from a community-based cohort study. We evaluated the ability of the RHHI and PTA as (a) continuous variables and (b) binary variables characterized by the optimal cut point determined by the Youden Index to predict hearing aid use. RHHI scores range from 0 to 72, and PTA was defined as averaged thresholds at frequencies 0.5, 1.0, 2.0, and 4.0 kHz in the worse ear. We used logistic regression models and receiver operating characteristic curves with corresponding concordance statistics (c-statistics) and 95% confidence intervals (CIs) to determine the predictive ability of models and chi-square tests to determine whether c-statistics were significantly different.ResultsThis study included 581 participants (Mage = 72.9 [SD = 9.9] years; 59.9% female; 14.3% Minority race). The c-statistics for the RHHI (0.79, 95% CI [0.75, 0.83]) and PTA (0.81, 95% CI [0.78, 0.85]), as continuous variables, were not significantly different (p = .25). The optimal cut points for the RHHI and PTA to predict hearing aid use were 6 points and 32.5 dB HL, respectively. The c-statistics for the RHHI (0.72, 95% CI [0.68, 0.76]) and PTA (0.75, 95% CI [0.71, 0.79]), as binary variables, were not significantly different (p = .27).ConclusionThe RHHI and PTA are similar in their ability to predict hearing aid use.
| S-EPMC10950317 | biostudies-literature
Project description:ObjectiveSelecting subjects for clinical trials on hearing loss therapies relies on the patient meeting the audiological inclusion criteria. In studies on the treatment of idiopathic sudden sensorineural hearing loss, the patient's acute audiogram is usually compared with a previous audiogram, the audiogram of the non-affected ear, or a normal audiogram according to an ISO standard. Generally, many more patients are screened than actually fulfill the particular inclusion criteria. The inclusion criteria often require a calculation of pure-tone averages, selection of the most affected frequencies, and calculation of hearing loss differences.Materials and methodsA software tool was developed to simplify and accelerate this inclusion procedure for investigators to estimate the possible recruitment rate during the planning phase of a clinical trial and during the actual study. This tool is Microsoft Excel-based and easy to modify to meet the particular inclusion criteria of a specific clinical trial. The tool was retrospectively evaluated on 100 patients with acute hearing loss comparing the times for classifying automatically and manually. The study sample comprised 100 patients with idiopathic sudden sensorineural hearing loss.Results and conclusionThe age- and sex-related normative audiogram was calculated automatically by the tool and the hearing impairment was graded. The estimated recruitment rate of our sample was quickly calculated. Information about meeting the inclusion criteria was provided instantaneously. A significant reduction of 30 % in the time required for classifying (30 s per patient) was observed.
| S-EPMC4819485 | biostudies-literature
Project description:ImportanceAge-adjusted prevalence of hearing impairment (HI) decreased across generations in the 20th century, suggesting that HI is partially preventable. It is not known whether HI incidence differs by generation.ObjectivesTo examine whether HI incidence and change in pure-tone average (PTA) differ by generation and identify factors underlying these differences.Design, setting, and participantsThis cohort study used data from the Epidemiology of Hearing Loss Study (EHLS) and Beaver Dam Offspring Study (BOSS), a pair of studies of adults in Beaver Dam, Wisconsin. Baseline examinations occurred from 1993 to 1995 in the EHLS and 2005 to 2008 in BOSS, with two 5-year follow-up examinations in each cohort. This longitudinal cohort study assessed 3651 participants without HI at baseline who had follow-up data.Main outcomes and measuresThe primary outcome was incident HI measured by pure-tone audiometry, defined as PTA greater than 25-dB hearing level (dB HL) in either ear. Associations of 5-year incidence were estimated by relative risks (RRs) and 10-year cumulative incidence with generation, as categorized by commonly used sociodemographic descriptors of year of birth, by hazard ratios (HRs). The 10-year change in PTA was investigated using a generation × time interaction term in generalized estimating equation models.ResultsAmong the 3651 participants (mean [SD] age at baseline 53.1 [10.6] years; 2255 [61.8%] female; and 3567 [97.7%] non-Hispanic White), the 5-year HI incidence was 14.1% (95% CI, 13.0%-15.3%) and the 10-year cumulative incidence was 26.0% (95% CI, 24.6%-27.6%). The incidence increased with age. The risk of 5-year incident HI decreased by generation (RR, 0.80; 95% CI, 0.66-0.97) when adjusting for multiple covariates. The decreased risk was similar in the 10-year period (HR, 0.86; 95% CI, 0.73-1.01). The PTA change rate (per 5 years of follow-up) decreased by generation, with the Greatest Generation (born 1901-1924) experiencing the highest rate (7.03 dB HL). The rates were all significantly lower for the other generations (Silent Generation [born 1925-1945], 3.30 dB HL; Baby Boom Generation [born 1946-1964], 3.36 dB HL; and Generation X [born 1965-1984], 2.33 dB HL).Conclusions and relevanceThis study suggests that the risk of HI and rate of PTA change is lower for the Silent Generation and Baby Boom Generation compared with the Greatest Generation. Part of this lower risk is likely associated with changes in modifiable factors. A potential continued benefit may exist for Generation X. Combined with the reduced risk of HI for the Silent Generation and Baby Boom Generation, this finding implies that the future HI burden may be lower than current estimates suggest.
| S-EPMC7677869 | biostudies-literature
Project description:Purpose The purpose of this study is to determine the sensitivities and specificities of different audiometric hearing screening criteria and single-item and multi-item hearing disability questionnaires among a group of Spanish-speaking adults in a rural community. Method Participants were 131 predominantly older (77% 65+ years) Hispanic/Latinx adults (98%). A structured Spanish-language interview and pure-tone threshold test data were analyzed for each participant. The sensitivities and specificities of three single questions and the Hearing Handicap Index for the Elderly-Screening (HHIE-S; Ventry & Weinstein, 1983) in Spanish, as well as three audiometric screening criteria, were evaluated in relation to the pure-tone threshold test for detecting hearing loss. Results Sensitivity and specificity of audiometric screening criteria varied, but the highest sensitivity was found for the criterion of > 25 dB HL at 1-4 kHz in either ear. The single self-perception question, "¿Cree usted que tiene pérdida de audición? (Do you think you have a hearing loss?)," was shown to be the most sensitive self-report screening compared to other single-item questions and the HHIE-S. This single question was as sensitive as an audiometric screening to detect a moderate hearing loss (> 40 dB HL in either ear). Results from the Spanish HHIE-S indicated poor performance to detect hearing loss in this population, consistent with previous research. Conclusions Among older Spanish-speaking adults, self-reported hearing status had varying sensitivities depending on the question asked. However, of the tools evaluated, the self-perception question proved to be a more sensitive and specific tool than a multi-item screen. Objective audiometric testing (> 25 dB HL) resulted in the highest sensitivity to detect a mild hearing loss.
| S-EPMC7229776 | biostudies-literature
Project description:ObjectivesWhen one ear of an individual can hear significantly better than the other ear, evaluating the worse ear with loud probe tones may require delivering masking noise to the better ear to prevent the probe tones from inadvertently being heard by the better ear. Current masking protocols are confusing, laborious, and time consuming. Adding a standardized masking protocol to an active machine learning audiogram procedure could potentially alleviate all of these drawbacks by dynamically adapting the masking as needed for each individual. The goal of this study is to determine the accuracy and efficiency of automated machine learning masking for obtaining true hearing thresholds.DesignDynamically masked automated audiograms were collected for 29 participants between the ages of 21 and 83 (mean 43, SD 20) with a wide range of hearing abilities. Normal-hearing listeners were given unmasked and masked machine learning audiogram tests. Listeners with hearing loss were given a standard audiogram test by an audiologist, with masking stimuli added as clinically determined, followed by a masked machine learning audiogram test. The hearing thresholds estimated for each pair of techniques were compared at standard audiogram frequencies (i.e., 0.25, 0.5, 1, 2, 4, 8 kHz).ResultsMasked and unmasked machine learning audiogram threshold estimates matched each other well in normal-hearing listeners, with a mean absolute difference between threshold estimates of 3.4 dB. Masked machine learning audiogram thresholds also matched well the thresholds determined by a conventional masking procedure, with a mean absolute difference between threshold estimates for listeners with low asymmetry and high asymmetry between the ears, respectively, of 4.9 and 2.6 dB. Notably, out of 6200 masked machine learning audiogram tone deliveries for this study, no instances of tones detected by the nontest ear were documented. The machine learning methods were also generally faster than the manual methods, and for some listeners, substantially so.ConclusionsDynamically masked audiograms achieve accurate true threshold estimates and reduce test time compared with current clinical masking procedures. Dynamic masking is a compelling alternative to the methods currently used to evaluate individuals with highly asymmetric hearing, yet can also be used effectively and efficiently for anyone.
| S-EPMC7725866 | biostudies-literature
Project description:Dissatisfaction with the sound of one's own voice is common among hearing-aid users. Little is known regarding how hearing impairment and hearing aids separately affect own-voice perception. This study examined own-voice perception and associated issues before and after a hearing-aid fitting for new hearing-aid users and refitting for experienced users to investigate whether it was possible to differentiate between the effect of (unaided) hearing impairment and hearing aids. Further aims were to investigate whether First-Time and Experienced users as well as users with dome and mold inserts differed in the severity of own-voice problems. The study had a cohort design with three groups: First-Time hearing-aid users going from unaided to aided hearing (n = 70), Experienced hearing-aid users replacing their old hearing aids (n = 70), and an unaided control group (n = 70). The control group was surveyed once and the hearing-aid users twice; once before hearing-aid fitting/refitting and once after. The results demonstrated that own-voice problems are common among both First-Time and Experienced hearing-aid users with either dome- or mold-type fittings, while people with near-normal hearing and not using hearing aids report few problems. Hearing aids increased ratings of own-voice problems among First-Time users, particularly those with mold inserts. The results suggest that altered auditory feedback through unaided hearing impairment or through hearing aids is likely both to change own-voice perception and complicate regulation of vocal intensity, but hearing aids are the primary reason for poor perceived sound quality of one's own voice.
| S-EPMC7887686 | biostudies-literature
Project description:ObjectivesChildren presenting at audiology services with caregiver-reported listening difficulties often have normal audiograms. The appropriate approach for the further assessment and clinical management of these children is currently unclear. In this Sensitive Indicators of Childhood Listening Difficulties (SICLiD) study, we assessed listening ability using a reliable and validated caregiver questionnaire (the Evaluation of Children's Listening and Processing Skills [ECLiPS]) in a large (n = 146) and heterogeneous sample of 6- to 13-year-old children with normal audiograms. Scores on the ECLiPS were related to a multifaceted laboratory assessment of the children's audiological, psycho- and physiological-acoustic, and cognitive abilities. This report is an overview of the SICLiD study and focuses on the children's behavioral performance. The overall goals of SICLiD were to understand the auditory and other neural mechanisms underlying childhood listening difficulties and translate that understanding into clinical assessment and, ultimately, intervention.DesignCross-sectional behavioral assessment of children with "listening difficulties" and an age-matched "typically developing" control group. Caregivers completed the ECLiPS, and the resulting total standardized composite score formed the basis of further descriptive statistics, univariate, and multivariate modeling of experimental data.ResultsAll scores of the ECLiPS, the SCAN-3:C, a standardized clinical test suite for auditory processing, and the National Institutes of Health (NIH) Cognition Toolbox were significantly lower for children with listening difficulties than for their typically developing peers using group comparisons via t-tests and Wilcoxon Rank-Sum tests. A similar effect was observed on the Listening in Spatialized Noise-Sentences (LiSN-S) test for speech sentence-in-noise intelligibility but only reached significance for the Low Cue and High Cue conditions and the Talker Advantage derived score. Stepwise regression to examine the factors contributing to the ECLiPS Total scaled score (pooled across groups) yielded a model that explained 42% of its variance based on the SCAN-3:C composite, LiSN-S Talker Advantage, and the NIH Toolbox Picture Vocabulary, and Dimensional Change Card Sorting scores (F[4, 95] = 17.35, p < 0.001). High correlations were observed between many test scores including the ECLiPS, SCAN-3:C, and NIH Toolbox composite measures. LiSN-S Advantage measures generally correlated weakly and nonsignificantly with non-LiSN-S measures. However, a significant interaction was found between extended high-frequency threshold and LiSN-S Talker Advantage.ConclusionsChildren with listening difficulties but normal audiograms have problems with the cognitive processing of auditory and nonauditory stimuli that include both fluid and crystallized reasoning. Analysis of poor performance on the LiSN-S Talker Advantage measure identified subclinical hearing loss as a minor contributing factor to talker segregation. Beyond auditory tests, evaluations of children with complaints of listening difficulties should include standardized caregiver observations and consideration of broad cognitive abilities.
| S-EPMC8545703 | biostudies-literature
Project description:ObjectiveIf the benefits of newborn hearing screening and early intervention are to be fully realized, there is a need to understand the challenges of hearing aid management in infants. The aim was to investigate longitudinal changes in hearing aid use and hearing aid management challenges in very young infants.DesignEighty-one primarily female (99%) caregivers of infant hearing aid users completed a questionnaire about hearing aid management experiences, first when their infants were 3 to 7 months old (1 to 6 months after hearing aid fitting) and again at 7 to 21 months of age. Hearing aid data logging was compared with caregiver reports of daily use for 66 infants.ResultsThe main hearing aid management challenges reported by caregivers were performing listening checks and troubleshooting. These challenges reduced over the approximately 5-month time period but remained a problem with around a quarter of respondents still not confident or unsure about troubleshooting, and around a third not performing a daily listening check. Mean daily hearing aid use, obtained from data logging, declined significantly over time from 6.6 to 5.3 hours. Further analysis revealed reduced hearing aid use was primarily among infants with profound losses (n = 11). Caregivers overestimated daily hours of use at both time points. Caregivers reported difficulty with the infants pulling out their hearing aids, especially at the later time point.ConclusionsThe findings from this relatively large sample of caregivers of young infants, assessed at two time points, revealed significant challenges in hearing aid management, including highly variable daily hearing aid use. Interventions that use behavior change techniques may be needed to ensure intentions are consistently turned into successful actions, if the benefits of newborn hearing screening and early intervention are to be fully realized.
| S-EPMC8221722 | biostudies-literature
Project description:To clarify the possible mechanism causing binaural diplacusis with low-tone hearing loss, two psychoacoustic experiments were performed with 20 healthy subjects, using harmonic complex tones. In the first experiment, two tones were presented unilaterally, either from the right or left side. One of the tones presented was higher in frequency in terms of the fundamental component, but lower or equal in frequency in terms of the highest component, than the other tone. The subjects were asked which tone was higher in pitch after listening to both tones. They were also asked to compare tones in which low-tone components were eliminated. In the second experiment, the subjects heard these complex tones binaurally, with low-tone components eliminated in one ear. In the first experiment, most subjects perceived pitch direction, that is, higher or lower, in a reverse way when low-tone components were eliminated from the complex tones. In the second experiment, approximately half of all subjects heard the tones at different pitches in both ears. Under certain conditions, complex tone stimulation may induce binaural diplacusis when low-tone hearing is lost in one ear.
| S-EPMC6347458 | biostudies-literature
Project description:Pitch perception is known to be difficult for individuals with cochlear implant (CI), and adding a hearing aid (HA) in the non-implanted ear is potentially beneficial. The current study aimed to investigate the bimodal benefit for lexical tone recognition in Mandarin-speaking preschoolers using a CI and an HA in opposite ears. The child participants were required to complete tone identification in quiet and in noise with CI + HA in comparison with CI alone. While the bimodal listeners showed confusion between Tone 2 and Tone 3 in recognition, the additional acoustic information from the contralateral HA alleviated confusion between these two tones in quiet. Moreover, significant improvement was demonstrated in the CI + HA condition over the CI alone condition in noise. The bimodal benefit for individual subjects could be predicted by the low-frequency hearing threshold of the non-implanted ear and the duration of bimodal use. The findings support the clinical practice to fit a contralateral HA in the non-implanted ear for the potential benefit in Mandarin tone recognition in CI children. The limitations call for further studies on auditory plasticity on an individual basis to gain insights on the contributing factors to the bimodal benefit or its absence.
| S-EPMC7226140 | biostudies-literature