AutoAudio: Deep Learning for Automatic Audiogram Interpretation

Crowson, Matthew G.; Lee, Jong Wook; Hamour, Amr F.; Mahmood, Rafid; Babier, Aaron; Lin, Vincent; Tucci, Debara L.; Chan, Timothy C. Y.

doi:10.1007/s10916-020-01627-1

Cited by 13 publications

(12 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additional advantages include its flexibility for expansion to bone conduction, speech perception, and masking. Crowson et al ( 72 ) utilized deep learning in the form of “Auto Audio,” a proof-of-concept model to interpret diagnostic audiograms. Audiograms consisting of various hearing loss types (e.g., conductive, sensorineural, mixed) were used to train several neural networks.…”

Section: Tele-audiology Servicesmentioning

confidence: 99%

Tele-Audiology: Current State and Future Directions

D'Onofrio

Zeng

2022

Front. Digit. Health

View full text Add to dashboard Cite

The importance of tele-audiology has been heightened by the current COVID-19 pandemic. The present article reviews the current state of tele-audiology practice while presenting its limitations and opportunities. Specifically, this review addresses: (1) barriers to hearing healthcare, (2) tele-audiology services, and (3) tele-audiology key issues, challenges, and future directions. Accumulating evidence suggests that tele-audiology is a viable service delivery model, as remote hearing screening, diagnostic testing, intervention, and rehabilitation can each be completed reliably and effectively. The benefits of tele-audiology include improved access to care, increased follow-up rates, and reduced travel time and costs. Still, significant logistical and technical challenges remain from ensuring a secure and robust internet connection to controlling ambient noise and meeting all state and federal licensure and reimbursement regulations. Future research and development, especially advancements in artificial intelligence, will continue to increase tele-audiology acceptance, expand remote care, and ultimately improve patient satisfaction.

show abstract

Section: Tele-audiology Servicesmentioning

confidence: 99%

Tele-Audiology: Current State and Future Directions

D'Onofrio

Zeng

2022

Front. Digit. Health

View full text Add to dashboard Cite

show abstract

“…Lee et al [11] leverage K-means clustering to categorize audiogram shapes into six basic types and five subtypes. Crowson et al [12] employ ResNet-101 to differentiate audiograms of individuals with conductive, sensorineural, mixed, or no hearing loss. Nonetheless, all these methods only give a rough summary of certain properties of audiograms.…”

Section: Audiogram Classificationmentioning

confidence: 99%

“…While there have been attempts to directly classify the types of hearing loss (if any) from audiogram images [10,11,12], they are only able to provide class-based qualitative descriptions of audiograms. They cannot recover the full information, specifically the precise hearing level at different frequencies, which are crucial for tuning hearing aids.…”

Section: Introductionmentioning

confidence: 99%

Interpreting Audiograms with Multi-stage Neural Networks

Li¹,

Congxi²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Audiograms are a particular type of line charts representing individuals' hearing level at various frequencies. They are used by audiologists to diagnose hearing loss, and further select and tune appropriate hearing aids for customers. There have been several projects such as Autoaudio that aim to accelerate this process through means of machine learning. But all existing models at their best can only detect audiograms in images and classify them into general categories. They are unable to extract hearing level information from detected audiograms by interpreting the marks, axis, and lines. To address this issue, we propose a Multi-stage Audiogram Interpretation Network (MAIN) that directly reads hearing level data from photos of audiograms. We also established Open Audiogram, an open dataset of audiogram images with annotations of marks and axes on which we trained and evaluated our proposed model. Experiments show that our model is feasible and reliable.

show abstract

“…88 Automation can assist clinicians and patients to interpret the measurement by data-driven automated reporting of accuracy and reliability (including signalling for suspicious outcomes) such as QUALIND ®53 or by automated classification for diagnostic purposes (including type and degree of hearing loss). Examples of automated classification include AMCLASS, 89 Autoaudio, 90 and data-driven audiogram classification. 91…”

Section: Accuracymentioning

confidence: 99%

Automated and machine learning approaches in diagnostic hearing assessment: a scoping review

Pragt¹,

Wasmann²,

Eikelboom³

et al. 2021

Preprint

View full text Add to dashboard Cite

Hearing loss affects one in five people worldwide and is estimated to affect one in four by 2050. Treatment relies on accurate diagnosis of hearing loss, but this first step is out of reach for more than 80% of those affected. Increasingly automated digital approaches are being developed for self-administered hearing assessment without professionals’ direct involvement. This scoping review provides an overview of automated approaches, based on 56 reports from 2012 until June 2021, adding to the 29 published prior to 2012. Twenty-seven automated approaches were identified. An increasing number of approaches report similar accuracy as manual hearing assessments. Machine learning approaches are more efficient and personal digital devices make assessments more affordable and accessible. Validity can be enhanced by quality surveillance including noise monitoring and detecting inconclusive results. Employed within identified limitations, automated hearing assessments can support task-shifting, self-care, and clinical care pathways.

show abstract

AutoAudio: Deep Learning for Automatic Audiogram Interpretation

Cited by 13 publications

References 25 publications

Tele-Audiology: Current State and Future Directions

Tele-Audiology: Current State and Future Directions

Interpreting Audiograms with Multi-stage Neural Networks

Automated and machine learning approaches in diagnostic hearing assessment: a scoping review

Contact Info

Product

Resources

About