Artificial Intelligence
74 The Use of AI In Audiology
Meghan Mahar
Introduction
Audiology is a medical field that studies the ear and hearing ability as a whole and is constantly advancing as new technology arises. Hearing loss is defined as a loss greater than 40 decibels in the better ear in adults and 30 decibels in children. Around 430 million people are affected by disabling hearing loss and this number is only predicted to increase significantly at a rapid rate. Audiology is centered around the studies of hearing impairment and the detection, diagnosis, and treatment of this problem. Artificial intelligence, also known as AI, is one of those technologies
that has been proven to significantly benefit the field as a whole. This is because it can be used to identify hearing problems early on with limited misdiagnosis, it can be used to optimize hearing aid function by adjusting to an individual’s needs, and tools using AI can help make life easier for individuals with hearing loss that is normally difficult for them. Artificial intelligence has shown early signs of having a profound impact on audiology and the lives of those with hearing loss and deafness. AI seems to have the ability to process hearing data and therefore enhance research potential in audiology. This might mean that in the near future, those with hearing loss can experience more effective treatment. As artificial intelligence continues to evolve, audiology will continue to have greater intervention advancements, which can change how healthcare is provided permanently.
Connection To STS
Artificial Intelligence advancements in the field of audiology are reflected in society in the way that it has transformed how hearing healthcare is provided to individuals with hearing impairment. Tele-audiology has broken barriers that caused difficulties in receiving hearing healthcare. It made it possible for more individuals to get the help they need and therefore improve their quality of life. Hearing aids have drastically become more advanced from AI technologies in the way that sounds are perceived. AI has also demonstrated high accuracy in diagnosis and overall efficiency in healthcare. Society benefits in the way that individuals with hearing loss can better communicate with others and their environment when hearing technologies continue to develop and become more sophisticated. So it is that the use of AI in audiology benefits healthcare drives social changes, and transforms societal functioning.
AI In Hearing Impairment Diagnosis
Artificial intelligence seems to be most promising in the area of diagnosis of hearing impairment in the field of audiology. AI technologies, such as natural language processing models like ChatGPT and machine learning, ML, are capable of analyzing large amounts of data from audiograms which are hearing tests, noise exposure histories, and genetic information. These technologies can classify audiograms, conduct automated audiometry which are sound-based hearing tests, and predict hearing loss with high accuracy, which is highly important for early detection of hearing issues and therefore intervention. By utilizing electronic health records, AI streamlines the diagnostic process, reducing the likelihood of misdiagnosis and ensuring timely intervention. This use allows for a more in-depth understanding of a patient’s hearing health, allowing audiologists to make more informed decisions. AI’s predictive abilities can identify individuals at risk of developing hearing loss in the future, allowing for proactive measures to be taken to possibly prevent the condition. For example, AI can analyze patterns in hearing data to predict future hearing loss based on current noise exposure and genetic predispositions, providing a more proactive approach to hearing care. Pure tone audiology, a hearing test that determine’s an individuals sensitivity to hearing using different frequencies of sine waves through headphones and can assess both sensioneural and conductive hearing loss. Pure tone threshold measurements can benefit from audiology technologies since AI can analyze large sets of data quickly and accurately. Within ML, there are classifiers that are used to categorize a data input with a class label. Some of these classifiers used in audiology include Support Vector Machine (SVM), k-Nearest Neighbor, and Naïve Bayes. When ML is used, feature extraction and selection are the main processes. In feature extraction, raw data is measured and identified. In feature selection, data is selected that is most meaningful for classification of hearing impairment. ML can also identify environmental risk factors for hearing loss, such as exposure to cigarette smoke and pestisides that had not been identified before and can be used for preventative measures in the diagnosis process. Genetic analysis is an important part of the diagnosis process. For example, Pendred syndrome, a common form of sensorineural hearing loss, is characterized by thyroid issues and an enlarger vestibular aqueduct. ML can identify these symptoms and make an accurate diagnosis based on what it knows (AlSamhori et al., 2024). Early detection and intervention of hearing impairment can help prevent further complications. Another form of diagnostic testing is speech audiometry. Speech audiometry assesses speech recognition to determine if intervention is necessary. Electroencephalograms, also known as EEGs, measure the brain’s activity in response to sound stimuli, called Auditory Evoked Potentials, AEPs. Electronic Records, EHRs, hold patient information and medical history. EHRs can predict diagnosis, future patient outcomes, and recommend intervention solutions. One example, “Auto-Audio,” uses databases to train neural networks for accurate and quick audiogram readings. ML classifiers and Artificial intelligence in general has thus far had a profound effect on hearing impairment diagnosis with its accuracy and sensitivity.
AI In Hearing Aid Functionality
AI-powered hearing aids have revolutionized the way individuals with hearing loss experience sound, offering a range of advanced features that significantly improve the user’s quality of life. These devices provide personalized sound adjustments, real-time environmental adaptations, and advanced voice recognition capabilities. AI algorithms can distinguish between speech and background noise, making conversations clearer even in noisy environments, which is a common challenge for those with hearing impairments. Over time, these hearing aids learn from user preferences, continuously improving their performance and adapting to the user’s specific needs. Additionally, some AI hearing aids come equipped with health tracking features, monitoring metrics such as steps taken and heart rate, contributing to overall wellness. This holistic approach not only enhances the user’s hearing experience but also supports their general health and well-being. For example, AI can adjust the hearing aid settings in real-time based on the user’s environment, ensuring optimal sound quality whether they are in a quiet room or a bustling street. AI can be used for better hearing aid fitting and functionality, adjusting to an individuals specific needs. Other AI technologies, such as Acoustic Environmental Classification, AEC, and Edge Mode adapt to the user’s environment in real time to give the best quality of sound. The Table Microphone Accessory and tinnitus preventing technologies improve speech clarity and reduce unnecessary background noises (AlSamhori et al., 2024). The effects of ChatGPT-4 on different types of hearing aids was studied based on hearing function, fitting, and maintenance (Wang et al., 2024). ChatGPT-4 was found to function well with behind the ear, in the ear, and completely in canal versions of hearing aids. This type of AI would describe the fitting process, customized specifically to the user. It also described maintenance practices such as cleaning and battery replacement. ChatGPT-4 demonstrated an impressive 72% accuracy in these tasks which dealt with different types of hearing aids. Different variations of AI can be used to improve the quality of life of hearing loss patients in unique ways that are tailored specifically to meet an individual’s needs.
Ways AI Makes Tasks Easier For Those With Hearing Loss
AI tools extend beyond hearing aids to make life easier for individuals with hearing loss, offering a range of solutions that enhance accessibility and convenience. Enhanced diagnostics and predictive capabilities allow for the early identification of hearing loss and the suggestion of proactive measures, ensuring that individuals receive timely and effective treatment. Remote health visits facilitated by AI reduce the need for frequent in-person appointments, saving time and travel costs for patients. This is particularly beneficial for those living in remote areas or with mobility issues. Tele-audiology provides a remote option for hearing healthcare which can save travel costs, reduce travel time, and help underserved areas, making this form of healthcare more accessible. Remote screenings are shown to be just as effective as in-person clinical methods (Chen & Lin, 2024). Tele-audiology and ML can work together to provide care virtually (AlSamhori et al., 2024). Otoscopes and hearing loss diagnosis is much more accessible this way and people may be more likely to take action sooner rather than later if they have easier access to healthcare. Individuals with hearing devices can also use tele-audiology services to fine tune their hearing settings and treatment methods. Automated support through virtual assistants provides around-the-clock assistance, ensuring continuous care and support. These virtual assistants can answer common questions, offer educational resources, and even triage concerns to ensure timely care. For example, AI chatbots are able to provide immediate answers to patient questions, helping them to better manage their own hearing health. These advancements make hearing treatment more accessible and personalized, improving the overall quality of life for those with hearing impairments.
Conclusion
Artificial intelligence is transforming the field of audiology, offering significant benefits in the diagnosis and treatment of hearing impairments. AI’s ability to enhance early detection and formulate personalized treatment plans is revolutionizing patient care. AI-powered hearing aids provide personalized sound, real-time adjustments, and health tracking, while AI tools make hearing treatment more accessible and efficient. As AI technology continues to evolve, it promises to bring even greater advancements in audiology, ultimately improving the quality of life for individuals with hearing loss. The integration of AI in audiology not only enhances the effectiveness of hearing aids but also supports a more comprehensive approach to hearing health, ensuring that individuals receive the best possible care.
References
Artificial Intelligence in Plain English. (n.d.). AI revolutionizes audiology: Can you hear the difference? Artificial Intelligence in Plain English. https://ai.plainenglish.io/ai-revolutionizes-audiology-can-you-hear-the-difference-5bb743aa8ff1
Contreras, D. (2023, January 5). How AI can benefit the deaf and hard of hearing community. InnoCaption News. https://www.innocaption.com/recentnews/ai-helps-deaf-hard-of-hearing-community
D’Onofrio, K. L., & Zeng, F. G. (2022). Tele-Audiology: Current State and Future Directions. Frontiers in digital health, 3, 788103. https://doi.org/10.3389/fdgth.2021.788103
GBD 2019 Hearing Loss Collaborators (2021). Hearing loss prevalence and years lived with disability, 1990-2019: findings from the Global Burden of Disease Study 2019. Lancet (London, England), 397(10278), 996–1009. https://doi.org/10.1016/S0140-6736(21)00516-X
Lin, M.-J., & Chen, C.-K. (2024). Breaking sound barriers: Exploring tele-audiology’s impact on hearing healthcare. Diagnostics, 14(8), 856. https://doi.org/10.3390/diagnostics14080856
Salsone, B., Stein, P. S., Parsons, K. G., Kent, T., Nielsen, K., & Nitz, D. T. (2024). Technological determinism. Science Technology and Society: A Student Led Exploration, 7, 1-15. https://doi.org/10.1016/j.sts.2024.08.060
Wang, S., Mo, C., Chen, Y., Dai, X., Wang, H., & Shen, X. (2024). Exploring the performance of ChatGPT-4 in the Taiwan audiologist qualification examination: Preliminary observational study highlighting the potential of AI chatbots in hearing care. JMIR Medical Education, 10(1), e55595. https://doi.org/10.2196/55595
Wilson, B. S., Tucci, D. L., Moses, D. A., Chang, E. F., Young, N. M., Zeng, F. G., Lesica, N. A., Bur, A. M., Kavookjian, H., Mussatto, C., Penn, J., Goodwin, S., Kraft, S., Wang, G., Cohen, J. M., Ginsburg, G. S., Dawson, G., & Francis, H. W. (2022). Harnessing the Power of Artificial Intelligence in Otolaryngology and the Communication Sciences. Journal of the Association for Research in Otolaryngology : JARO, 23(3), 319–349. https://doi.org/10.1007/s10162-022-00846-2
ai use disclosure
This chapter has been authored with the assistance of Microsoft CoPilot, an artificial intelligence platform, https://copilot.cloud.microsoft/ fromcode=cmc&redirectid=74E21AC379DA4CE299398FAEE1C01430&auth=2