Online Machine Learning Audiometry

Objectives: A confluence of recent developments in cloud computing, real-time web audio and machine learning psychometric function estimation has made wide dissemination of sophisticated turn-key audiometric assessments possible. The authors have combined these capabilities into an online (i.e., web-based) pure-tone audiogram estimator intended to empower researchers and clinicians with advanced hearing tests without the need for custom programming or special hardware. The objective of this study was to assess the accuracy and reliability of this new online machine learning audiogram method relative to a commonly used hearing threshold estimation technique also implemented online for the first time in the same platform. Design: The authors performed air conduction pure-tone audiometry on 21 participants between the ages of 19 and 79 years (mean 41, SD 21) exhibiting a wide range of hearing abilities. For each ear, two repetitions of online machine learning audiogram estimation and two repetitions of online modified Hughson-Westlake ascending-descending audiogram estimation were acquired by an audiologist using the online software tools. The estimated hearing thresholds of these two techniques were compared at standard audiogram frequencies (i.e., 0.25, 0.5, 1, 2, 4, 8 kHz). Results: The two threshold estimation methods delivered very similar threshold estimates at standard audiogram frequencies. Specifically, the mean absolute difference between threshold estimates was 3.24 ± 5.15 dB. The mean absolute differences between repeated measurements of the online machine learning procedure and between repeated measurements of the Hughson-Westlake procedure were 2.85 ± 6.57 dB and 1.88 ± 3.56 dB, respectively. The machine learning method generated estimates of both threshold and spread (i.e., the inverse of psychometric slope) continuously across the entire frequency range tested from fewer samples on average than the modified Hughson-Westlake procedure required to estimate six discrete thresholds. Conclusions: Online machine learning audiogram estimation in its current form provides all the information of conventional threshold audiometry with similar accuracy and reliability in less time. More importantly, however, this method provides additional audiogram details not provided by other methods. This standardized platform can be readily extended to bone conduction, masking, spectrotemporal modulation, speech perception, etc., unifying audiometric testing into a single comprehensive procedure efficient enough to become part of the standard audiologic workup. ACKNOWLEDGMENTS: Funding for this project was provided by NIH grants UL1 TR002345, T35 DC008765, T32 NS073547, NSF grant DGE-1745038, and the Center for Integration of Medicine and Innovative Technology (CIMIT). LLC. D. L. B. wrote the article; R. T. H. designed and conducted the experiments; N. M. helped design and conduct the experiments; X. D. S., K. A. S., J. C. D., and B. R. D. S. developed and implemented the algorithm; J. Y. C., E. A. D., J. M. B., K. L. H., and D. L. B. analyzed the data. All authors discussed the results and implications and commented on article revisions. D. L. B. has a patent pending on technology described in this article and has equity ownership in Bonauria, LLC. The authors have no other disclosures. Received December 18, 2017; accepted August 22, 2018. Address for correspondence: Dennis Barbour, Department of Biomedical Engineering, Washington University, One Brookings Dr., Campus Box 1097, Uncas Whitaker Hall Room 200E, St. Louis, MO 63130, USA. E-mail: dbarbour@wustl.edu Copyright © 2018 Wolters Kluwer Health, Inc. All rights reserved.

from #Audiology via ola Kala on Inoreader https://ift.tt/2D12MRF
via IFTTT

Benefits of Cochlear Implantation for Single-Sided Deafness: Data From the House Clinic-University of Southern California-University of California, Los Angeles Clinical Trial

Objectives: Cochlear implants (CIs) have been shown to benefit patients with single-sided deafness (SSD) in terms of tinnitus reduction, localization, speech understanding, and quality of life (QoL). While previous studies have shown cochlear implantation may benefit SSD patients, it is unclear which point of comparison is most relevant: baseline performance before implantation versus performance with normal-hearing (NH) ear after implantation. In this study, CI outcomes were assessed in SSD patients before and up to 6 mo postactivation. Benefits of cochlear implantation were assessed relative to binaural performance before implantation or relative to performance with the NH ear alone after implantation. Design: Here, we report data for 10 patients who completed a longitudinal, prospective, Food and Drug Administration–approved study of cochlear implantation for SSD patients. All subjects had severe to profound unilateral hearing loss in one ear and normal hearing in the other ear. All patients were implanted with the MED-EL CONCERTO Flex 28 device. Speech understanding in quiet and in noise, localization, and tinnitus severity (with the CI on or off) were measured before implantation (baseline) and at 1, 3, 6 mo postactivation of the CI processor. Performance was measured with both ears (binaural), the CI ear alone, and the NH ear alone (the CI ear was plugged and muffed). Tinnitus severity, dizziness severity, and QoL were measured using questionnaires administered before implantation and 6 mo postactivation. Results: Significant CI benefits were observed for tinnitus severity, localization, speech understanding, and QoL. The degree and time course of CI benefit depended on the outcome measure and the reference point. Relative to binaural baseline performance, significant and immediate (1 mo postactivation) CI benefits were observed for tinnitus severity and speech performance in noise, but localization did not significantly improve until 6 mo postactivation; questionnaire data showed significant improvement in QoL 6 mo postactivation. Relative to NH-only performance after implantation, significant and immediate benefits were observed for tinnitus severity and localization; binaural speech understanding in noise did not significantly improve during the 6-mo study period, due to variability in NH-only performance. There were no correlations between behavioral and questionnaire data, except between tinnitus visual analog scale scores at 6 mo postactivation and Tinnitus Functional Index scores at 6 mo postactivation. Conclusions: The present behavioral and subjective data suggest that SSD patients greatly benefit from cochlear implantation. However, to fully understand the degree and time course of CI benefit, the outcome measure and point of comparison should be considered. From a clinical perspective, binaural baseline performance is a relevant point of comparison. The lack of correlation between behavioral and questionnaire data suggest that represent independent measures of CI benefit for SSD patients. This is an open access article distributed under the Creative Commons Attribution License 4.0 (CCBY), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. ACKNOWLEDGEMENTS: The authors thank all the SSD patients who participated in this study. The authors thank Justin Aronoff and David Landsberger for their help with the initial design of this study, and Suzanne Gutierrez for coordination support during the study. The authors also thank three anonymous reviewers for helpful comments. MED-EL provided the cochlear implants and speech processors for the study, as well as support for research and publication costs. The authors have no conflicts of interest to declare. Received April 26, 2018; accepted September 5, 2018. Address for correspondence: John Galvin, House Ear Institute, 2100 West Third Street, Suite 100, Los Angeles, CA, USA 90057. E-mail: jgalvin@hei.org Copyright © 2018 Wolters Kluwer Health, Inc. All rights reserved.

from #Audiology via ola Kala on Inoreader https://ift.tt/2CxkYRE
via IFTTT

Online Machine Learning Audiometry

Objectives: A confluence of recent developments in cloud computing, real-time web audio and machine learning psychometric function estimation has made wide dissemination of sophisticated turn-key audiometric assessments possible. The authors have combined these capabilities into an online (i.e., web-based) pure-tone audiogram estimator intended to empower researchers and clinicians with advanced hearing tests without the need for custom programming or special hardware. The objective of this study was to assess the accuracy and reliability of this new online machine learning audiogram method relative to a commonly used hearing threshold estimation technique also implemented online for the first time in the same platform. Design: The authors performed air conduction pure-tone audiometry on 21 participants between the ages of 19 and 79 years (mean 41, SD 21) exhibiting a wide range of hearing abilities. For each ear, two repetitions of online machine learning audiogram estimation and two repetitions of online modified Hughson-Westlake ascending-descending audiogram estimation were acquired by an audiologist using the online software tools. The estimated hearing thresholds of these two techniques were compared at standard audiogram frequencies (i.e., 0.25, 0.5, 1, 2, 4, 8 kHz). Results: The two threshold estimation methods delivered very similar threshold estimates at standard audiogram frequencies. Specifically, the mean absolute difference between threshold estimates was 3.24 ± 5.15 dB. The mean absolute differences between repeated measurements of the online machine learning procedure and between repeated measurements of the Hughson-Westlake procedure were 2.85 ± 6.57 dB and 1.88 ± 3.56 dB, respectively. The machine learning method generated estimates of both threshold and spread (i.e., the inverse of psychometric slope) continuously across the entire frequency range tested from fewer samples on average than the modified Hughson-Westlake procedure required to estimate six discrete thresholds. Conclusions: Online machine learning audiogram estimation in its current form provides all the information of conventional threshold audiometry with similar accuracy and reliability in less time. More importantly, however, this method provides additional audiogram details not provided by other methods. This standardized platform can be readily extended to bone conduction, masking, spectrotemporal modulation, speech perception, etc., unifying audiometric testing into a single comprehensive procedure efficient enough to become part of the standard audiologic workup. ACKNOWLEDGMENTS: Funding for this project was provided by NIH grants UL1 TR002345, T35 DC008765, T32 NS073547, NSF grant DGE-1745038, and the Center for Integration of Medicine and Innovative Technology (CIMIT). LLC. D. L. B. wrote the article; R. T. H. designed and conducted the experiments; N. M. helped design and conduct the experiments; X. D. S., K. A. S., J. C. D., and B. R. D. S. developed and implemented the algorithm; J. Y. C., E. A. D., J. M. B., K. L. H., and D. L. B. analyzed the data. All authors discussed the results and implications and commented on article revisions. D. L. B. has a patent pending on technology described in this article and has equity ownership in Bonauria, LLC. The authors have no other disclosures. Received December 18, 2017; accepted August 22, 2018. Address for correspondence: Dennis Barbour, Department of Biomedical Engineering, Washington University, One Brookings Dr., Campus Box 1097, Uncas Whitaker Hall Room 200E, St. Louis, MO 63130, USA. E-mail: dbarbour@wustl.edu Copyright © 2018 Wolters Kluwer Health, Inc. All rights reserved.

from #Audiology via ola Kala on Inoreader https://ift.tt/2D12MRF
via IFTTT

Benefits of Cochlear Implantation for Single-Sided Deafness: Data From the House Clinic-University of Southern California-University of California, Los Angeles Clinical Trial

Objectives: Cochlear implants (CIs) have been shown to benefit patients with single-sided deafness (SSD) in terms of tinnitus reduction, localization, speech understanding, and quality of life (QoL). While previous studies have shown cochlear implantation may benefit SSD patients, it is unclear which point of comparison is most relevant: baseline performance before implantation versus performance with normal-hearing (NH) ear after implantation. In this study, CI outcomes were assessed in SSD patients before and up to 6 mo postactivation. Benefits of cochlear implantation were assessed relative to binaural performance before implantation or relative to performance with the NH ear alone after implantation. Design: Here, we report data for 10 patients who completed a longitudinal, prospective, Food and Drug Administration–approved study of cochlear implantation for SSD patients. All subjects had severe to profound unilateral hearing loss in one ear and normal hearing in the other ear. All patients were implanted with the MED-EL CONCERTO Flex 28 device. Speech understanding in quiet and in noise, localization, and tinnitus severity (with the CI on or off) were measured before implantation (baseline) and at 1, 3, 6 mo postactivation of the CI processor. Performance was measured with both ears (binaural), the CI ear alone, and the NH ear alone (the CI ear was plugged and muffed). Tinnitus severity, dizziness severity, and QoL were measured using questionnaires administered before implantation and 6 mo postactivation. Results: Significant CI benefits were observed for tinnitus severity, localization, speech understanding, and QoL. The degree and time course of CI benefit depended on the outcome measure and the reference point. Relative to binaural baseline performance, significant and immediate (1 mo postactivation) CI benefits were observed for tinnitus severity and speech performance in noise, but localization did not significantly improve until 6 mo postactivation; questionnaire data showed significant improvement in QoL 6 mo postactivation. Relative to NH-only performance after implantation, significant and immediate benefits were observed for tinnitus severity and localization; binaural speech understanding in noise did not significantly improve during the 6-mo study period, due to variability in NH-only performance. There were no correlations between behavioral and questionnaire data, except between tinnitus visual analog scale scores at 6 mo postactivation and Tinnitus Functional Index scores at 6 mo postactivation. Conclusions: The present behavioral and subjective data suggest that SSD patients greatly benefit from cochlear implantation. However, to fully understand the degree and time course of CI benefit, the outcome measure and point of comparison should be considered. From a clinical perspective, binaural baseline performance is a relevant point of comparison. The lack of correlation between behavioral and questionnaire data suggest that represent independent measures of CI benefit for SSD patients. This is an open access article distributed under the Creative Commons Attribution License 4.0 (CCBY), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. ACKNOWLEDGEMENTS: The authors thank all the SSD patients who participated in this study. The authors thank Justin Aronoff and David Landsberger for their help with the initial design of this study, and Suzanne Gutierrez for coordination support during the study. The authors also thank three anonymous reviewers for helpful comments. MED-EL provided the cochlear implants and speech processors for the study, as well as support for research and publication costs. The authors have no conflicts of interest to declare. Received April 26, 2018; accepted September 5, 2018. Address for correspondence: John Galvin, House Ear Institute, 2100 West Third Street, Suite 100, Los Angeles, CA, USA 90057. E-mail: jgalvin@hei.org Copyright © 2018 Wolters Kluwer Health, Inc. All rights reserved.

from #Audiology via ola Kala on Inoreader https://ift.tt/2CxkYRE
via IFTTT

The Effect of Simultaneously and Sequentially Delivered Cognitive and Aerobic Training on Mobility among Older Adults with Hearing Loss

Publication date: Available online 23 October 2018

Source: Gait & Posture

Author(s): Halina Bruce, Laurence Lai, Louis Bherer, Maxime Lussier, Nancy St.-Onge, Karen Z.H. Li

Abstract

Background

: Older adults exhibit declines in auditory and motor functioning, which are compensated for through the recruitment of cognitive resources. Cognitive or physical training alone has been shown to improve cognitive functioning and transfer to motor tasks, but results are mixed when these are combined in studies of healthy older adults, and few studies have included those with age-related hearing loss (ARHL), who are at a higher risk of falls. Research question: To examine format effects in mixed training, we used a repeated measures intervention design to compare the efficacy of Simultaneous and Sequential multimodal training formats. Methods: 42 older adults (M_age = 68.05, SD_age = 4.65, females = 26) with (ARHL) and without hearing loss (OAH) completed an intervention study consisting of 12 sessions of multimodal training (computerized cognitive dual-task and recumbent aerobic cycling). Participants were randomly assigned to either the Simultaneous (concurrent cognitive and aerobic) or Sequential training group (cognitive followed by aerobic) and completed assessments of single- and dual-task mobility concurrent with an auditory working memory task. Training gains were assessed with repeated measures ANOVAs using magnitude of improvement from pre- to post-training on primary outcome measures as the dependent variable. Results: Gains in auditory working memory were greater in the Sequential group than Simultaneous particularly among OAH. ARHL participants were unaffected by format. While all participants improved on a measure of chair rises, there was no benefit to standing balance. The results demonstrate an advantage to Sequential training, suggesting a benefit to focusing on each task in isolation. Significance: The gains noted in the ARHL indicate the potential benefit of incorporating cognitive remediation into traditional audiological rehabilitation. Moreover, it is important to consider the cost of dividing attention when combining training.

from #Audiology via ola Kala on Inoreader https://ift.tt/2PdwHfb
via IFTTT

Repeatability of electromyography recordings and muscle synergies during gait among children with cerebral palsy

Publication date: Available online 22 October 2018

Source: Gait & Posture

Author(s): Katherine M. Steele, Meghan E. Munger, Keshia M. Peters, Benjamin R. Shuman, Michael H. Schwartz

Abstract

Background

Clinical gait analysis is commonly used in the evaluation and treatment of children with cerebral palsy (CP). While the repeatability of kinematic and kinetic measures of gait has previously been evaluated, the repeatability of electromyography (EMG) recordings or measures calculated from EMG data, such as muscle synergies, remains unclear for this population.

Research question

Are EMG-based measures in clinical gait analysis repeatable between visits for children with CP?

Methods

We recruited 20 children with bilateral CP who had been referred for clinical gait analysis. The children completed two visits less than six weeks apart with EMG data collected bilaterally from five muscles (rectus femoris, medial hamstrings, vastus lateralis, anterior tibialis, and medial gastrocnemius). Variance ratio and cosine similarity were used to evaluate repeatability of EMG waveforms between visits. Nonnegative matrix factorization was used to calculate synergies from EMG data at each visit to compare synergy weights and activations.

Results & significance

The inter-visit variance ratios of EMG data for children with CP were similar to previously reported results for typically-developing children and unimpaired adults (range: 0.39 for vastus lateralis to 0.66 for rectus femoris). The average cosine similarity of the EMG waveforms between visits was greater than 0.9 for all muscles, while synergy weights and activations also had high similarity – greater than 0.8 and 0.9 between visits, respectively. These results demonstrate that EMG repeatability between visits during clinical gait analysis for children with CP is similar to unimpaired individuals. These results provide a baseline for evaluating whether observed changes in EMG recordings between visits reflect real changes in muscle activity or are within the range of inter-visit variability.

from #Audiology via ola Kala on Inoreader https://ift.tt/2EHdH4J
via IFTTT

The Effect of Simultaneously and Sequentially Delivered Cognitive and Aerobic Training on Mobility among Older Adults with Hearing Loss

Publication date: Available online 23 October 2018

Source: Gait & Posture

Author(s): Halina Bruce, Laurence Lai, Louis Bherer, Maxime Lussier, Nancy St.-Onge, Karen Z.H. Li

Abstract

Background

: Older adults exhibit declines in auditory and motor functioning, which are compensated for through the recruitment of cognitive resources. Cognitive or physical training alone has been shown to improve cognitive functioning and transfer to motor tasks, but results are mixed when these are combined in studies of healthy older adults, and few studies have included those with age-related hearing loss (ARHL), who are at a higher risk of falls. Research question: To examine format effects in mixed training, we used a repeated measures intervention design to compare the efficacy of Simultaneous and Sequential multimodal training formats. Methods: 42 older adults (M_age = 68.05, SD_age = 4.65, females = 26) with (ARHL) and without hearing loss (OAH) completed an intervention study consisting of 12 sessions of multimodal training (computerized cognitive dual-task and recumbent aerobic cycling). Participants were randomly assigned to either the Simultaneous (concurrent cognitive and aerobic) or Sequential training group (cognitive followed by aerobic) and completed assessments of single- and dual-task mobility concurrent with an auditory working memory task. Training gains were assessed with repeated measures ANOVAs using magnitude of improvement from pre- to post-training on primary outcome measures as the dependent variable. Results: Gains in auditory working memory were greater in the Sequential group than Simultaneous particularly among OAH. ARHL participants were unaffected by format. While all participants improved on a measure of chair rises, there was no benefit to standing balance. The results demonstrate an advantage to Sequential training, suggesting a benefit to focusing on each task in isolation. Significance: The gains noted in the ARHL indicate the potential benefit of incorporating cognitive remediation into traditional audiological rehabilitation. Moreover, it is important to consider the cost of dividing attention when combining training.

from #Audiology via ola Kala on Inoreader https://ift.tt/2PdwHfb
via IFTTT

Repeatability of electromyography recordings and muscle synergies during gait among children with cerebral palsy

Publication date: Available online 22 October 2018

Source: Gait & Posture

Author(s): Katherine M. Steele, Meghan E. Munger, Keshia M. Peters, Benjamin R. Shuman, Michael H. Schwartz

Abstract

Background

Clinical gait analysis is commonly used in the evaluation and treatment of children with cerebral palsy (CP). While the repeatability of kinematic and kinetic measures of gait has previously been evaluated, the repeatability of electromyography (EMG) recordings or measures calculated from EMG data, such as muscle synergies, remains unclear for this population.

Research question

Are EMG-based measures in clinical gait analysis repeatable between visits for children with CP?

Methods

We recruited 20 children with bilateral CP who had been referred for clinical gait analysis. The children completed two visits less than six weeks apart with EMG data collected bilaterally from five muscles (rectus femoris, medial hamstrings, vastus lateralis, anterior tibialis, and medial gastrocnemius). Variance ratio and cosine similarity were used to evaluate repeatability of EMG waveforms between visits. Nonnegative matrix factorization was used to calculate synergies from EMG data at each visit to compare synergy weights and activations.

Results & significance

The inter-visit variance ratios of EMG data for children with CP were similar to previously reported results for typically-developing children and unimpaired adults (range: 0.39 for vastus lateralis to 0.66 for rectus femoris). The average cosine similarity of the EMG waveforms between visits was greater than 0.9 for all muscles, while synergy weights and activations also had high similarity – greater than 0.8 and 0.9 between visits, respectively. These results demonstrate that EMG repeatability between visits during clinical gait analysis for children with CP is similar to unimpaired individuals. These results provide a baseline for evaluating whether observed changes in EMG recordings between visits reflect real changes in muscle activity or are within the range of inter-visit variability.

from #Audiology via ola Kala on Inoreader https://ift.tt/2EHdH4J
via IFTTT