AutoAudio: Deep Learning for Automatic Audiogram Interpretation
- PDF / 825,205 Bytes
- 7 Pages / 595.276 x 790.866 pts Page_size
- 33 Downloads / 227 Views
MOBILE & WIRELESS HEALTH
AutoAudio: Deep Learning for Automatic Audiogram Interpretation Matthew G. Crowson 1,2 & Jong Wook Lee 1 & Amr Hamour 1 & Rafid Mahmood 2 & Aaron Babier 2 & Vincent Lin 1 & Debara L. Tucci 3 & Timothy C. Y. Chan 2 Received: 8 June 2020 / Accepted: 21 July 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Hearing loss is the leading human sensory system loss, and one of the leading causes for years lived with disability with significant effects on quality of life, social isolation, and overall health. Coupled with a forecast of increased hearing loss burden worldwide, national and international health organizations have urgently recommended that access to hearing evaluation be expanded to meet demand. The objective of this study was to develop ‘AutoAudio’ – a novel deep learning proof-of-concept model that accurately and quickly interprets diagnostic audiograms. Adult audiogram reports representing normal, conductive, mixed and sensorineural morphologies were used to train different neural network architectures. Image augmentation techniques were used to increase the training image set size. Classification accuracy on a separate test set was used to assess model performance. The architecture with the highest out-of-training set accuracy was ResNet-101 at 97.5%. Neural network training time varied between 2 to 7 h depending on the depth of the neural network architecture. Each neural network architecture produced misclassifications that arose from failures of the model to correctly label the audiogram with the appropriate hearing loss type. The most commonly misclassified hearing loss type were mixed losses. Re-engineering the process of hearing testing with a machine learning innovation may help enhance access to the growing worldwide population that is expected to require audiologist services. Our results suggest that deep learning may be a transformative technology that enables automatic and accurate audiogram interpretation. Keywords Audiogram . Automation . Deep learning . Neural networks
Introduction The National Academy of Sciences (NAS) and World Health Organization (WHO) have identified hearing loss as the
This article is part of the Topical collection on Mobile & Wireless Health Electronic supplementary material The online version of this article (https://doi.org/10.1007/s10916-020-01627-1) contains supplementary material, which is available to authorized users. * Matthew G. Crowson [email protected] 1
Department of Otolaryngology-Head & Neck Surgery, Sunnybrook Health Sciences Center, 2075 Bayview Avenue, Toronto, Ontario M4N 3M5, Canada
2
Department of Mechanical & Industrial Engineering, University of Toronto, Toronto, Canada
3
Department of Otolaryngology-Head & Neck Surgery, Duke University Medical Center, Durham, North Carolina, USA
leading human sensory system loss, and one of the leading causes for years lived with disability with significant effects on quality of life, social isolation, and overall health [1, 2]. Couple
Data Loading...
