Computational audiology

Computational audiology is a branch of audiology that employs techniques from mathematics and computer science to improve clinical treatments and scientific understanding of the auditory system. Computational audiology is closely related to computational medicine, which uses quantitative models to develop improved methods for general disease diagnosis and treatment.[1]

Overview

In contrast to traditional methods in audiology and hearing science research, computational audiology emphasizes predictive modeling and large-scale analytics ("big data") rather than inferential statistics and small-cohort hypothesis testing. The aim of computational audiology is to translate advances in hearing science, data science, information technology, and machine learning to clinical audiological care. Research to understand hearing function and auditory processing in humans as well as relevant animal species represents translatable work that supports this aim. Research and development to implement more effective diagnostics and treatments represent translational work that supports this aim.[2]

For people with hearing difficulties, tinnitus, hyperacusis, or balance problems, these advances might lead to more precise diagnoses, novel therapies, and advanced rehabilitation options including smart prostheses and e-Health/mHealth apps. For care providers, it can provide actionable knowledge and tools for automating part of the clinical pathway.[3]

The field is interdisciplinary and includes foundations in audiology, auditory neuroscience, computer science, data science, machine learning, psychology, signal processing, natural language processing, otology and vestibulology.

Applications

In computational audiology, models and algorithms are used to understand the principles that govern the auditory system, to screen for hearing loss, to diagnose hearing disorders, to provide rehabilitation, and to generate simulations for patient education, among others.

Computational models of hearing, speech and auditory perception

For decades, phenomenological & biophysical (computational) models have been developed to simulate characteristics of the human auditory system. Examples include models of the mechanical properties of the basilar membrane,[4] the electrically stimulated cochlea,[5][6] middle ear mechanics,[7] bone conduction,[8] and the central auditory pathway.[9] Saremi et al. (2016) compared 7 contemporary models including parallel filterbanks, cascaded filterbanks, transmission lines and biophysical models.[10] More recently, convolutional neural networks (CNNs) have been constructed and trained that can replicate human auditory function[11] or complex cochlear mechanics with high accuracy.[12] Although inspired by the interconnectivity of biological neural networks, the architecture of CNNs is distinct from the organization of the natural auditory system.

e-Health / mHealth (connected hearing healthcare, wireless- and internet-based services)

Online pure-tone threshold audiometry (or screening) tests, electrophysiological measures, for example distortion-product otoacoustic emissions (DPOAEs) and speech-in-noise screening tests are becoming increasingly available as a tools to promote awareness and enable accurate early identification of hearing loss across ages, monitor the effects of ototoxicity and/or noise, and guide ear and hearing care decisions and provide support to clinicians.[13][14] Smartphone-based tests have been proposed to detect middle ear fluid using acoustic reflectometry and machine learning.[15] Smartphone attachments have also been designed to perform tympanometry for acoustic evaluation of the middle ear eardrum.[16][17] Low-cost earphones attached to smartphones have also been prototyped to help detect the faint otoacoustic emissions from the cochlea and perform neonatal hearing screening.[18][19]

Big data and AI in audiology and hearing healthcare

Collecting large numbers of audiograms (e.g. from databases from the National Institute for Occupational Safety and Health or NIOSH[20] or National Health and Nutrition Examination Survey or NHANES) provides researchers with opportunities to find patterns of hearing status in the population[21][22] or to train AI systems that can classify audiograms.[23] Machine learning can be used to predict the relationship between multiple factors e.g. predict depression based on self-reported hearing loss[24] or the relationship between genetic profile and self-reported hearing loss.[25] Hearing aids and wearables provide the option to monitor the soundscape of the user or log the usage patterns which can be used to automatically recommend settings that are expected to benefit the user.[26]

Computational approaches to improving hearing devices and auditory implants

Methods to improve rehabilitation by auditory implants include improving music perception,[27] models of the electrode-neuron interface,[28] and an AI based Cochlear Implant fitting assistant.[29]

Data-based investigations into hearing loss and tinnitus

Online surveys processed with ML-based classification have been used to diagnose somatosensory tinnitus.[30] Automated Natural Language Processing (NPL) techniques, including unsupervised and supervised Machine Learning have been used to analyze social posts about tinnitus and analyze the heterogeneity of symptoms.[31][32]

Diagnostics for hearing problems, acoustics to facilitate hearing

Machine learning has been applied to audiometry to create flexible, efficient estimation tools that do not require excessive testing time to determine someone's individual's auditory profile.[33][34] Similarly, machine learning based versions of other auditory tests including determining dead regions in the cochlea or equal loudness contours,[35] have been created.

e-Research (remote testing, online experiments, new tools and frameworks)

Examples of e-Research tools include including the Remote Testing Wiki,[36] the Portable Automated Rapid Testing (PART), Ecological Momentary Assessment (EMA) and the NIOSH sound level meter. A number of tools can be found online.[37]

Software and tools

Software and large datasets are important for the development and adoption of computational audiology. As with many scientific computing fields, much of the field of computational audiology existentially depends on open source software and its continual maintenance, development, and advancement.[38]

Computational biology, computational medicine, and computational pathology are all interdisciplinary approaches to the life sciences that draw from quantitative disciplines such as mathematics and information science.

See also

Wikimedia Commons has media related to Audiology.
Wikiversity has learning resources about Global Audiology

References

  1. ^ Winslow, Raimond L.; Trayanova, Natalia; Geman, Donald; Miller, Michael I. (31 October 2012). "Computational Medicine: Translating Models to Clinical Care". Science Translational Medicine. 4 (158): 158rv11. doi:10.1126/scitranslmed.3003528. PMC 3618897. PMID 23115356.
  2. ^ Gannon, Frank (November 2014). "The steps from translatable to translational research". EMBO Reports. 15 (11): 1107–1108. doi:10.15252/embr.201439587. ISSN 1469-221X. PMC 4253482. PMID 25296643.
  3. ^ Wasmann, Jan-Willem A.; Lanting, Cris P.; Huinck, Wendy J.; Mylanus, Emmanuel A. M.; van der Laak, Jeroen W. M.; Govaerts, Paul J.; Swanepoel, De Wet; Moore, David R.; Barbour, Dennis L. (November–December 2021). "Computational Audiology: New Approaches to Advance Hearing Health Care in the Digital Age". Ear and Hearing. 42 (6): 1499–1507. doi:10.1097/AUD.0000000000001041. PMC 8417156. PMID 33675587.
  4. ^ De Boer, Egbert (1996), Dallos, Peter; Popper, Arthur N.; Fay, Richard R. (eds.), "Mechanics of the Cochlea: Modeling Efforts", The Cochlea, Springer Handbook of Auditory Research, vol. 8, New York, NY: Springer New York, pp. 258–317, doi:10.1007/978-1-4612-0757-3_5, ISBN 978-1-4612-6891-8, retrieved 2022-01-18
  5. ^ Frijns, J. H. M.; de Snoo, S. L.; Schoonhoven, R. (1995-07-01). "Potential distributions and neural excitation patterns in a rotationally symmetric model of the electrically stimulated cochlea". Hearing Research. 87 (1): 170–186. doi:10.1016/0378-5955(95)00090-Q. ISSN 0378-5955. PMID 8567435. S2CID 4762235.
  6. ^ Rubinstein, Jay T.; Hong, Robert (September 2003). "Signal Coding in Cochlear Implants: Exploiting Stochastic Effects of Electrical Stimulation". Annals of Otology, Rhinology & Laryngology. 112 (9_suppl): 14–19. doi:10.1177/00034894031120s904. ISSN 0003-4894. PMID 14533839. S2CID 32157848.
  7. ^ Sun, Q.; Gan, R. Z.; Chang, K.-H.; Dormer, K. J. (2002-10-01). "Computer-integrated finite element modeling of human middle ear". Biomechanics and Modeling in Mechanobiology. 1 (2): 109–122. doi:10.1007/s10237-002-0014-z. ISSN 1617-7959. PMID 14595544. S2CID 8781577.
  8. ^ Stenfelt, Stefan (2016-10-01). "Model predictions for bone conduction perception in the human". Hearing Research. MEMRO 2015 – Basic Science meets Clinical Otology. 340: 135–143. doi:10.1016/j.heares.2015.10.014. ISSN 0378-5955. PMID 26657096. S2CID 4862153.
  9. ^ Meddis, Ray; Lopez-Poveda, Enrique A.; Fay, Richard R.; Popper, Arthur N., eds. (2010). "Computational Models of the Auditory System". Springer Handbook of Auditory Research. 35. doi:10.1007/978-1-4419-5934-8. ISBN 978-1-4419-1370-8. ISSN 0947-2657.
  10. ^ Saremi, Amin; Beutelmann, Rainer; Dietz, Mathias; Ashida, Go; Kretzberg, Jutta; Verhulst, Sarah (September 2016). "A comparative study of seven human cochlear filter models". The Journal of the Acoustical Society of America. 140 (3): 1618–1634. Bibcode:2016ASAJ..140.1618S. doi:10.1121/1.4960486. ISSN 0001-4966. PMID 27914400.
  11. ^ Kell, Alexander J. E.; Yamins, Daniel L. K.; Shook, Erica N.; Norman-Haignere, Sam V.; McDermott, Josh H. (2018-05-02). "A Task-Optimized Neural Network Replicates Human Auditory Behavior, Predicts Brain Responses, and Reveals a Cortical Processing Hierarchy". Neuron. 98 (3): 630–644.e16. doi:10.1016/j.neuron.2018.03.044. ISSN 0896-6273. PMID 29681533. S2CID 5084719.
  12. ^ Baby, Deepak; Van Den Broucke, Arthur; Verhulst, Sarah (February 2021). "A convolutional neural-network model of human cochlear mechanics and filter tuning for real-time applications". Nature Machine Intelligence. 3 (2): 134–143. doi:10.1038/s42256-020-00286-8. ISSN 2522-5839. PMC 7116797. PMID 33629031.
  13. ^ Paglialonga, Alessia; Cleveland Nielsen, Annette; Ingo, Elisabeth; Barr, Caitlin; Laplante-Lévesque, Ariane (2018-07-31). "eHealth and the hearing aid adult patient journey: a state-of-the-art review". BioMedical Engineering OnLine. 17 (1): 101. doi:10.1186/s12938-018-0531-3. ISSN 1475-925X. PMC 6069792. PMID 30064497.
  14. ^ Frisby, Caitlin; Eikelboom, Robert; Mahomed-Asmail, Faheema; Kuper, Hannah; Swanepoel, De Wet (2021-12-30). "MHealth Applications for Hearing Loss: A Scoping Review". Telemedicine and e-Health. 28 (8): 1090–1099. doi:10.1089/tmj.2021.0460. hdl:2263/84486. ISSN 1530-5627. PMID 34967683. S2CID 245567480.
  15. ^ Chan, Justin; Raju, Sharat; Nandakumar, Rajalakshmi; Bly, Randall; Gollakota, Shyamnath (2019-05-15). "Detecting middle ear fluid using smartphones". Science Translational Medicine. 11 (492): eaav1102. doi:10.1126/scitranslmed.aav1102. ISSN 1946-6234. PMID 31092691. S2CID 155102882.
  16. ^ Chan, Justin; Najafi, Ali; Baker, Mallory; Kinsman, Julie; Mancl, Lisa R.; Norton, Susan; Bly, Randall; Gollakota, Shyamnath (2022-06-16). "Performing tympanometry using smartphones". Communications Medicine. 2 (1): 57. doi:10.1038/s43856-022-00120-9. ISSN 2730-664X. PMC 9203539. PMID 35721828. S2CID 249811632.
  17. ^ Community, Nature Portfolio Bioengineering (2022-06-15). "Computing for Audiology: Smartphone tympanometer for diagnosing middle ear disorders". Nature Portfolio Bioengineering Community. Retrieved 2022-06-21.
  18. ^ Goodman, Shawn S. (2022-10-31). "Affordable hearing screening". Nature Biomedical Engineering. 6 (11): 1199–1200. doi:10.1038/s41551-022-00959-2. ISSN 2157-846X. PMID 36316370. S2CID 253246312.
  19. ^ Chan, Justin; Ali, Nada; Najafi, Ali; Meehan, Anna; Mancl, Lisa R.; Gallagher, Emily; Bly, Randall; Gollakota, Shyamnath (2022-10-31). "An off-the-shelf otoacoustic-emission probe for hearing screening via a smartphone". Nature Biomedical Engineering. 6 (11): 1203–1213. doi:10.1038/s41551-022-00947-6. ISSN 2157-846X. PMC 9717525. PMID 36316369.
  20. ^ Masterson, Elizabeth A.; Tak, SangWoo; Themann, Christa L.; Wall, David K.; Groenewold, Matthew R.; Deddens, James A.; Calvert, Geoffrey M. (June 2013). "Prevalence of hearing loss in the United States by industry". American Journal of Industrial Medicine. 56 (6): 670–681. doi:10.1002/ajim.22082. PMID 22767358.
  21. ^ Charih, François; Bromwich, Matthew; Mark, Amy E.; Lefrançois, Renée; Green, James R. (December 2020). "Data-Driven Audiogram Classification for Mobile Audiometry". Scientific Reports. 10 (1): 3962. Bibcode:2020NatSR..10.3962C. doi:10.1038/s41598-020-60898-3. ISSN 2045-2322. PMC 7054524. PMID 32127604.
  22. ^ Cox, Marco; de Vries, Bert (2021). "Bayesian Pure-Tone Audiometry Through Active Learning Under Informed Priors". Frontiers in Digital Health. 3: 723348. doi:10.3389/fdgth.2021.723348. ISSN 2673-253X. PMC 8521968. PMID 34713188.
  23. ^ Crowson, Matthew G.; Lee, Jong Wook; Hamour, Amr; Mahmood, Rafid; Babier, Aaron; Lin, Vincent; Tucci, Debara L.; Chan, Timothy C. Y. (2020-08-07). "AutoAudio: Deep Learning for Automatic Audiogram Interpretation". Journal of Medical Systems. 44 (9): 163. doi:10.1007/s10916-020-01627-1. ISSN 1573-689X. PMID 32770269. S2CID 221035573.
  24. ^ Crowson, Matthew G.; Franck, Kevin H.; Rosella, Laura C.; Chan, Timothy C. Y. (July–August 2021). "Predicting Depression From Hearing Loss Using Machine Learning". Ear and Hearing. 42 (4): 982–989. doi:10.1097/AUD.0000000000000993. ISSN 1538-4667. PMID 33577219. S2CID 231901726.
  25. ^ Wells, Helena Rr.; Freidin, Maxim B.; Zainul Abidin, Fatin N.; Payton, Antony; Dawes, Piers; Munro, Kevin J.; Morton, Cynthia C.; Moore, David R.; Dawson, Sally J; Williams, Frances Mk. (2019-02-14), Genome-wide association study identifies 44 independent genomic loci for self-reported adult hearing difficulty in the UK Biobank cohort, doi:10.1101/549071, S2CID 92606662, retrieved 2022-01-20
  26. ^ Christensen, Jeppe H.; Saunders, Gabrielle H.; Porsbo, Michael; Pontoppidan, Niels H. (2021). "The everyday acoustic environment and its association with human heart rate: evidence from real-world data logging with hearing aids and wearables". Royal Society Open Science. 8 (2): 201345. Bibcode:2021RSOS....801345C. doi:10.1098/rsos.201345. PMC 8074664. PMID 33972852.
  27. ^ Tahmasebi, Sina; Gajȩcki, Tom; Nogueira, Waldo (2020). "Design and Evaluation of a Real-Time Audio Source Separation Algorithm to Remix Music for Cochlear Implant Users". Frontiers in Neuroscience. 14: 434. doi:10.3389/fnins.2020.00434. ISSN 1662-453X. PMC 7248365. PMID 32508564.
  28. ^ Garcia, Charlotte; Goehring, Tobias; Cosentino, Stefano; Turner, Richard E.; Deeks, John M.; Brochier, Tim; Rughooputh, Taren; Bance, Manohar; Carlyon, Robert P. (2021-10-01). "The Panoramic ECAP Method: Estimating Patient-Specific Patterns of Current Spread and Neural Health in Cochlear Implant Users". Journal of the Association for Research in Otolaryngology. 22 (5): 567–589. doi:10.1007/s10162-021-00795-2. ISSN 1438-7573. PMC 8476702. PMID 33891218.
  29. ^ Battmer, Rolf-Dieter; Borel, Stephanie; Brendel, Martina; Buchner, Andreas; Cooper, Huw; Fielden, Claire; Gazibegovic, Dzemal; Goetze, Romy; Govaerts, Paul; Kelleher, Katherine; Lenartz, Thomas (2015-03-01). "Assessment of 'Fitting to Outcomes Expert' FOX™ with new cochlear implant users in a multi-centre study". Cochlear Implants International. 16 (2): 100–109. doi:10.1179/1754762814Y.0000000093. ISSN 1467-0100. PMID 25118042. S2CID 4674778.
  30. ^ Michiels, Sarah; Cardon, Emilie; Gilles, Annick; Goedhart, Hazel; Vesala, Markku; Schlee, Winfried (2021-07-14). "Somatosensory Tinnitus Diagnosis: Diagnostic Value of Existing Criteria". Ear & Hearing. 43 (1): 143–149. doi:10.1097/aud.0000000000001105. hdl:1942/34681. ISSN 1538-4667. PMID 34261856. S2CID 235907109.
  31. ^ Palacios, Guillaume; Noreña, Arnaud; Londero, Alain (2020). "Assessing the Heterogeneity of Complaints Related to Tinnitus and Hyperacusis from an Unsupervised Machine Learning Approach: An Exploratory Study". Audiology and Neurotology. 25 (4): 174–189. doi:10.1159/000504741. ISSN 1420-3030. PMID 32062654. S2CID 211135952.
  32. ^ "What can we learn about tinnitus from social media posts?". Computational Audiology. 2021-06-07. Retrieved 2022-01-20.
  33. ^ Barbour, Dennis L.; Howard, Rebecca T.; Song, Xinyu D.; Metzger, Nikki; Sukesan, Kiron A.; DiLorenzo, James C.; Snyder, Braham R. D.; Chen, Jeff Y.; Degen, Eleanor A.; Buchbinder, Jenna M.; Heisey, Katherine L. (July 2019). "Online Machine Learning Audiometry". Ear & Hearing. 40 (4): 918–926. doi:10.1097/AUD.0000000000000669. ISSN 0196-0202. PMC 6476703. PMID 30358656.
  34. ^ Schlittenlacher, Josef; Turner, Richard E.; Moore, Brian C. J. (2018-07-01). "Audiogram estimation using Bayesian active learning". The Journal of the Acoustical Society of America. 144 (1): 421–430. Bibcode:2018ASAJ..144..421S. doi:10.1121/1.5047436. ISSN 0001-4966. PMID 30075695. S2CID 51910371.
  35. ^ Schlittenlacher, Josef; Moore, Brian C. J. (2020). "Fast estimation of equal-loudness contours using Bayesian active learning and direct scaling". Acoustical Science and Technology. 41 (1): 358–360. doi:10.1250/ast.41.358. S2CID 214270892.
  36. ^ "PP Remote Testing Wiki | Main / RemoteTesting". www.spatialhearing.org. Retrieved 2022-01-20.
  37. ^ "Resources". Computational Audiology. Retrieved 2022-01-20.
  38. ^ Fortunato, Laura; Galassi, Mark (2021-05-17). "The case for free and open source software in research and scholarship". Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. 379 (2197): 20200079. Bibcode:2021RSPTA.37900079F. doi:10.1098/rsta.2020.0079. PMID 33775148. S2CID 232387092.