Cochlear Mechanisms and Otoacoustic Emission Test Performance

Detection of mild sensory hearing loss using a joint reflection-distortion otoacoustic emission profile

Measuring and analyzing both nonlinear-distortion and linear-reflection otoacoustic emissions (OAEs) combined creates what we have termed a "joint-OAE profile." Here, we test whether these two classes of emissions have different sensitivities to hearing loss and whether our joint-OAE profile can detect mild-moderate hearing loss better than conventional OAE protocols have. 2f1-f2 distortion-product OAEs and stimulus-frequency OAEs were evoked with rapidly sweeping tones in 300 normal and impaired ears. Metrics included OAE amplitude for fixed-level stimuli as well as slope and compression features derived from OAE input/output functions. Results show that mild-moderate hearing loss impacts distortion and reflection emissions differently. Clinical decision theory was applied using OAE metrics to classify all ears as either normal-hearing or hearing-impaired. Our best OAE classifiers achieved 90% or better hit rates (with false positive rates of 5%-10%) for mild hearing loss, across a nearly five-octave range. In summary, results suggest that distortion and reflection emissions have distinct sensitivities to hearing loss, which supports the use of a joint-OAE approach for diagnosis. Results also indicate that analyzing both reflection and distortion OAEs together to detect mild hearing loss produces outstanding accuracy across the frequency range, exceeding that achieved by conventional OAE protocols.

Reliable Long-Term Serial Evaluation of Cochlear Function Using Pulsed Distortion-Product Otoacoustic Emissions: Analyzing Levels and Pressure Time Courses

OBJECTIVES

To date, there is no international standard on how to use distortion-product otoacoustic emissions (DPOAEs) in serial measurements to accurately detect changes in the function of the cochlear amplifier due, for example, to ototoxic therapies, occupational noise, or the development of regenerative therapies. The use of clinically established standard DPOAE protocols for serial monitoring programs appears to be hampered by multiple factors, including probe placement and calibration effects, signal-processing complexities associated with multiple sites of emission generation as well as suboptimal selection of stimulus parameters.

DESIGN

Pulsed DPOAEs were measured seven times within 3 months for f2 = 1 to 14 kHz and L2 = 25 to 80 dB SPL in 20 ears of 10 healthy participants with normal hearing (mean age = 32.1 ± 9.7 years). L1 values were computed from individual optimal-path parameters derived from the corresponding individual DPOAE level map in the first test session. Three different DPOAE metrics for evaluating the functional state of the cochlear amplifier were investigated with respect to their test-retest reliability: (1) the interference-free, nonlinear-distortion component level ( LOD ), (2) the time course of the DPOAE-envelope levels, LDP ( t ), and (3) the squared, zero-lag correlation coefficient ( ) between the time courses of the DPOAE-envelope pressures, pDP ( t ), measured in two sessions. The latter two metrics include the two main DPOAE components and their state of interference.

RESULTS

Collated over all sessions and frequencies, the median absolute difference for LOD was 1.93 dB and for LDP ( t ) was 2.52 dB; the median of was 0.988. For the low ( f2 = 1 to 3 kHz), mid ( f2 = 4 to 9 kHz), and high ( f2 = 10 to 14 kHz) frequency ranges, the test-retest reliability of LOD increased with increasing signal to noise ratio (SNR).

CONCLUSIONS

On the basis of the knowledge gained from this study on the test-retest reliability of pulsed DPOAE signals and the current literature, we propose a DPOAE protocol for future serial monitoring applications that takes into account the following factors: (1) separation of DPOAE components, (2) use of individually optimal stimulus parameters, (3) SNR of at least 15 dB, (4) accurate pressure calibration, (5) consideration of frequency- and level-dependent test-retest reliabilities and corresponding reference ranges, and (6) stimulus levels L2 that are as low as possible with sufficient SNR to capture the nonlinear functional state of the cochlear amplifier operating at its highest gain.

Deep Learning Models for Predicting Hearing Thresholds Based on Swept-Tone Stimulus-Frequency Otoacoustic Emissions

OBJECTIVES

This study aims to develop deep learning (DL) models for the quantitative prediction of hearing thresholds based on stimulus-frequency otoacoustic emissions (SFOAEs) evoked by swept tones.

DESIGN

A total of 174 ears with normal hearing and 388 ears with sensorineural hearing loss were studied. SFOAEs in the 0.3 to 4.3 kHz frequency range were recorded using linearly swept tones at a rate of 2 Hz/msec, with stimulus level changing from 40 to 60 dB SPL in 10 dB steps. Four DL models were used to predict hearing thresholds at octave frequencies from 0.5 to 4 kHz. The models-a conventional convolutional neural network (CNN), a hybrid CNN-k-nearest neighbor (KNN), a hybrid CNN-support vector machine (SVM), and a hybrid CNN-random forest (RF)-were individually built for each frequency. The input to the DL models was the measured raw SFOAE amplitude spectra and their corresponding signal to noise ratio spectra. All DL models shared a CNN-based feature self-extractor. They differed in that the conventional CNN utilized a fully connected layer to make the final regression decision, whereas the hybrid CNN-KNN, CNN-SVM, and CNN-RF models were designed by replacing the last fully connected layer of CNN model with a traditional machine learning (ML) regressor, that is, KNN, SVM, and RF, respectively. The model performance was evaluated using mean absolute error and SE averaged over 20 repetitions of 5 × 5 fold nested cross-validation. The performance of the proposed DL models was compared with two types of traditional ML models.

RESULTS

The proposed SFOAE-based DL models resulted in an optimal mean absolute error of 5.98, 5.22, 5.51, and 6.06 dB at 0.5, 1, 2, and 4 kHz, respectively, superior to that obtained by the traditional ML models. The produced SEs were 8.55, 7.27, 7.58, and 7.95 dB at 0.5, 1, 2, and 4 kHz, respectively. All the DL models outperformed any of the traditional ML models.

CONCLUSIONS

The proposed swept-tone SFOAE-based DL models were capable of quantitatively predicting hearing thresholds with satisfactory performance. With DL techniques, the underlying relationship between SFOAEs and hearing thresholds at disparate frequencies was explored and captured, potentially improving the diagnostic value of SFOAEs.

Change to Hearing Loss-Related Risks and Screening in Preterm Infants

Hearing loss is one of the most common congenital defects in infancy; it increases speech and language delays and adversely affects academic achievement and socialemotional development. The risk of hearing loss in premature infants is higher than that in normal newborns, and because of the fragility of the auditory nervous system, it is more vulnerable to different risk factors. The hearing screening guidelines in current use were proposed by the American Academy of Pediatrics and updated in 2007, but there are no uniform guidelines for hearing screening in preterm infants. This review focuses on the risk factors related to hearing loss in premature infants, hearing screening strategies, and reasons for failure. The aim is to provide a more comprehensive understanding of hearing development in preterm infants to achieve early detection and early intervention. At the same time, attention should be paid to delayed auditory maturation in preterm infants to avoid excessive intervention. KEY POINTS: · Hearing loss is very common in infancy, especially in premature infants.. · Genetic factors, infection, hyperbilirubinemia, drugs, and noise are the main causes.. · We should pay attention to the delayed hearing maturity of premature infants and avoid excessive intervention..

Objective Assessment System for Hearing Prediction Based on Stimulus-Frequency Otoacoustic Emissions

Stimulus-frequency otoacoustic emissions (SFOAEs) can be useful tools for assessing cochlear function noninvasively. However, there is a lack of reports describing their utility in predicting hearing capabilities. Data for model training were collected from 245 and 839 ears with normal hearing and sensorineural hearing loss, respectively. Based on SFOAEs, this study developed an objective assessment system consisting of three mutually independent modules, with the routine test module and the fast test module used for threshold prediction and the hearing screening module for identifying hearing loss. Results evaluated via cross-validation show that the routine test module and the fast test module predict hearing thresholds with similar performance from 0.5 to 8 kHz, with mean absolute errors of 7.06–11.61 dB for the routine module and of 7.40–12.60 dB for the fast module. However, the fast module involves less test time than is needed in the routine module. The hearing screening module identifies hearing status with a large area under the receiver operating characteristic curve (0.912–0.985), high accuracy (88.4–95.9%), and low false negative rate (2.9–7.0%) at 0.5–8 kHz. The three modules are further validated on unknown data, and the results are similar to those obtained through cross-validation, indicating these modules can be well generalized to new data. Both the routine module and fast module are potential tools for predicting hearing thresholds. However, their prediction performance in ears with hearing loss requires further improvement to facilitate their clinical utility. The hearing screening module shows promise as a clinical tool for identifying hearing loss.

Assessment of Hearing Screening Combined With Limited and Expanded Genetic Screening for Newborns in Nantong, China

IMPORTANCE

Early identification and intervention for newborns with hearing loss (HL) may lead to improved physiological and social-emotional outcomes. The current newborn hearing screening is generally beneficial but improvements can be made.

OBJECTIVE

To assess feasibility and evaluate utility of a modified genetic and hearing screening program for newborn infants.

DESIGN, SETTING, AND PARTICIPANTS

This population-based cohort study used a 4-stage genetic and hearing screening program at 6 local hospitals in Nantong city, China. Participants were newborn infants born between January 2016 and June 2020 from the Han population. Statistical analysis was performed from April 1 to May 1, 2021.

EXPOSURES

Limited genetic screening for 15 variants in 4 common HL-associated genes and newborn hearing screening (NHS) were offered concurrently to all newborns. Hearing rescreening and/or diagnostic tests were provided for infants with evidence of HL on NHS or genetic variants on screening. Expanded genetic tests for a broader range of genes were targeted to infants with HL with negative results of limited genetic tests.

MAIN OUTCOMES AND MEASURES

The detection capability for infants with hearing impairment who passed conventional hearing screening, as well as infants with normal hearing at risk of late-onset HL due to genetic susceptibility.

RESULTS

Among a total of 35 930 infants, 32 512 infants completed the follow-up and were included for analysis. Among the infants included in the analysis, all were from the Han population in China and 52.3% (16 988) were male. The modified genetic and hearing screening program revealed 142 cases of HL and 1299 cases of genetic variation. The limited genetic screening helped identify 31 infants who passed newborn hearing screening, reducing time for diagnosis and intervention; 425 infants with normal hearing with pathogenic SLC26A4 variation and 92 infants with MT-RNR1 variation were at risk for enlarged vestibular aqueduct and aminoglycoside-induced ototoxicity respectively, indicating early aversive or preventive management.

CONCLUSIONS AND RELEVANCE

This study found that performing modified genetic and hearing screening in newborns was feasible and provides evidence that the program could identify additional subgroups of infants who need early intervention. These findings suggest an advantage for universal adoption of such a practice.

A clinical comparison of DPOAE fine structure reduction methods

OBJECTIVE

To evaluate two real-time methods for reducing distortion product otoacoustic emission (DPOAE) fine structure in terms of DPOAE amplitude and fine structure depth.

DESIGN

A prospective, repeated-measures design was used to assess DPOAE characteristics in response to a conventional stimulation method (Conv.), as well as for methods implementing either a generic suppressor tone (Supp.) or frequency modulation of the f₂ primary tone (FM).

STUDY SAMPLE

Eighty-three young adults (58 females) between the ages of 20 and 34 years with normal hearing completed testing for this study.

RESULTS

Use of the Conv. and FM methods resulted in consistently higher DPOAE levels relative to the Supp. method, with average advantages of 6 and 5 dB, respectively. For all methods, increased fine structure depth was observed for stimulation with lower level (25-45 dB SPL) and lower frequency (1000-3000 Hz) primary tones. Finally, use of the Supp. and FM methods resulted in significantly decreased fine structure depth relative to the Conv. method.

CONCLUSION

Through frequency modulation of the f₂ primary tone, it was possible to reduce the depth of fine structure across a clinically meaningful range of stimulation levels and frequencies without concomitant reduction in DPOAE amplitude.

Estimating Hearing Thresholds From Stimulus-Frequency Otoacoustic Emissions

It is of clinical interest to estimate pure-tone thresholds from potentially available objective measures, such as stimulus-frequency otoacoustic emissions (SFOAEs). SFOAEs can determine hearing status (normal hearing vs. hearing loss), but few studies have explored their further potential in predicting audiometric thresholds. The current study investigates the ability of SFOAEs to predict hearing thresholds at octave frequencies from 0.5 to 8 kHz. SFOAE input/output functions and pure-tone thresholds were measured from 230 ears with normal hearing and 737 ears with sensorineural hearing loss. Two methods were used to predict hearing thresholds. Method 1 is a linear regression model; Method 2 proposed in this study is a back propagation (BP) network predictor built on the bases of a BP neural network and principal component analysis. In addition, a BP network classifier was built to identify hearing status. Both Methods 1 and 2 were able to predict hearing thresholds from 0.5 to 8 kHz, but Method 2 achieved better performance than Method 1. The BP network classifiers achieved excellent performance in determining the presence or absence of hearing loss at all test frequencies. The results show that SFOAEs are not only able to identify hearing status with great accuracy at all test frequencies but, more importantly, can predict hearing thresholds at octave frequencies from 0.5 to 8 kHz, with best performance at 0.5 to 4 kHz. The BP network predictor is a potential tool for quantitatively predicting hearing thresholds, at least at 0.5 to 4 kHz.

Maximising the ability of stimulus-frequency otoacoustic emissions to predict hearing status and thresholds using machine-learning models

OBJECTIVE

This study aimed to maximise the ability of stimulus-frequency otoacoustic emissions (SFOAEs) to predict hearing status and thresholds based on machine-learning models.

DESIGN

SFOAE data and audiometric thresholds were collected at octave frequencies from 0.5 to 8 kHz. Support vector machine, k-nearest neighbour, back propagation neural network, decision tree, and random forest algorithms were used to build classification models for status identification and to develop regression models for threshold prediction.

STUDY SAMPLE

About 230 ears with normal hearing and 737 ears with sensorineural hearing loss.

RESULTS

All classification models yielded areas under the receiver operating characteristic curve of 0.926-0.994 at 0.5-8 kHz, superior to the previous SFOAE study. The regression models produced lower standard errors (8.1-12.2 dB, mean absolute errors: 5.53-8.97 dB) as compared to those for distortion-product and transient-evoked otoacoustic emissions previously reported (8.6-19.2 dB).

CONCLUSIONS

SFOAEs using machine-learning approaches offer promising tools for the prediction of hearing capabilities, at least at 0.5-4 kHz. Future research may focus on further improvements in accuracy and reductions in test time to improve clinical utility.