MM304 - Harnessing the Power of Artificial Intelligence in Hearing Aids to Improve Patient Outcomes: Digital Assistants

Abstract: Artificial intelligence has been used in hearing aids for decades, however, over the past five years it's been used in several novel ways. This short course will define artificial intelligence and how it is implemented in current new generation hearing aids. Data, collected from thousands of wearers, will be used to illustrate the utility of a live neural networks in improving quality of life hearing aid outcomes.

Summary:

< ! More than 20 years ago, hearing aids evolved from a screwdriver to computer-based fitting software to make adjustments. However,
the methods used to fine-tune and adjust hearing aids in the clinic during routine follow-up appointments has not changed: Clinicians still mainly rely on wearer feedback during an in-person appointment to change and modify the acoustic parameters of the devices.

< ! Appointments for fine-tuning are common and time consuming (Tecca, 2018). Additionally, the fine tuning decision-making process of clinicians tends to vary (Anderson et al., 2018). Wearers cannot always find the language to describe sound or accurately recall situations where they had problems hearing. During follow-up appointments this means clinicians must make educated guesses about what might fix the problem—in the perfectly quiet clinic—before sending the wearer home for another trial round in real-world listening situations.

< !       < This module addresses the effect of using a wearer-controlled digital assistant, based on Artificial Intelligence (AI), to improve hearing aid fittings outside the clinic. The digital assistant uses machine learning to predict the hearing aid adjustment that best addresses a problem experienced and reported by the wearer. The module discusses how frequently different types of hearing-related problems were reported by wearers, and how effective an AI-based system was in addressing wearer problems using the wearer acceptance rate as a metric.

< !        This module addresses the effect of using a wearer-controlled digital assistant, based on Artificial Intelligence (AI), to improve hearing aid fittings outside the clinic. The digital assistant uses machine learning to predict the hearing aid adjustment that best addresses a problem experienced and reported by the wearer. The module discusses how frequently different types of hearing-related problems were reported by wearers, and how effective an AI-based system was in addressing wearer problems using the wearer acceptance rate as a metric.