Improving Hearing Healthcare with Big Data Analytics of Real-Time Hearing Aid Data

Abstract

Modern hearing aids are not simple passive sound enhancers, but rather complex devices that can log (via smartphones) multivariate real-time data from the acoustic environment of a user. In the evotion project (http://h2020evotion.eu) such hearing aids are integrated with a Big Data analytics platform to bring about ecologically valid evidence to support the hearing healthcare sector. Here, we present the background of the Big Data analytics platform and demonstrate that modeling of longitudinally sampled data from hearing aids can support clinical investigations with hypotheses about hearing aid usage prognosis, and support public health decision-making within the hearing healthcare sector by simulation techniques. We found, that distinct characteristics of the acoustic environment significantly modulate how hearing impaired individuals use their hearing aids. Higher sound levels and an increased sound diversity but degraded signal quality all predicts more minutes of use per hour. By simulation, we show that a projected increase in the overall sound levels by 10dB followed by a 4dB increase in noise exposure will increase the need for hearing aid use by an additional 1 hour/day across a population of hearing impaired hearing aid users.

Fully Synthetic Longitudinal Real-World Data From Hearing Aid Wearers for Public Health Policy Modeling

“…The data-set includes information relating to patterns of real-world hearing aid usage and sound environment exposure. Undoubtedly, many such data-sources will be available for researchers and policy-makers in the future, and the data-set presented here can act as a first step of building and testing potential statistical models (Christensen et al, 2018, 2019).…”

Public health policy-making for hearing loss: stakeholders’ evaluation of a novel eHealth tool

“…2 . Our findings showed a positive correlation between HA usage and overall sound level and diversity and a negative correlation between HA usage and overall signal-to-noise ratio [ 34 ]. We also presented preliminary findings suggesting how the EVOTION HA data can be used to predict temporary threshold shifts and noise-induced hearing loss for individuals and the general public [ 35 , 36 ].…”

“…signal-to-noise ratio, describe the acoustic environment (right). Source: Christensen et al [ 34 ]. Used with permission …”

Application of Big Data to Support Evidence-Based Public Health Policy Decision-Making for Hearing

“…We have also found evidence that environmental sounds are significantly associated with hearing aid usage patterns (Christensen et al 2019a). This was done by applying a generalized linear mixed model to predict the hourly hearing aid usage (in minutes per hour) from the momentary sound environment encountered by the users.…”

“…Its ultimate objective is to enable and support more holistic management of HL at the population level (Spanoudakis et al 2018). As such, the study protocol has been published (Dritsakis et al 2018), as have papers detailing data collection processes (Pontoppidan et al 2017), the data repository architecture (Prasinos et al 2017), decision modeling (Katrakazas et al 2017) and approaches to data analysis (Christensen et al 2019a). In this article, we expand on the discussion of Gutenberg et al (2018) regarding the use of big data for developing evidence-based hearing health policies, using data collected and analyzed with a research prototype of the EVOTION decision-making platform to illustrate our points.…”