Objectives: Big data refers to a large and diverse set of structured and unstructured data that grows exponentially over time. Artificial Intelligence and Machine Learning (AI/ML) tools have made it possible to generate and analyze big data, especially those generated from the internet quickly and meaningfully. This talk presents some examples of how big data is being used in healthcare to generate new theories and draw inferences. Challenges and limitations of using big data will also be discussed.

Design: A literature review was performed to examine the type of big data used within the field of hearing science and the AI/ML methods used to analyze them. Examples of studies with big data (i.e., structured, semi-structured, and unstructured) and the type of AI/ML methods used will be presented to illustrate the applications within hearing healthcare.

Results: The use of big data and AI/ML models within hearing healthcare is still in its infancy. In the past, the use unstructured and semi-structured publicly available data was common. However, more structured big data is being generated through hearing device manufactures, through ongoing panel studies as well as within the healthcare systems. In general, earlier big data studies within hearing healthcare were exploratory and hypothesis-generating. However, current and future studies are likely to enhance hypothesis testing and experimentation, complementing the traditional research methods.

Conclusions: AI/ML methods will continue to improve and expand as well as impact the future of hearing healthcare. It is likely that the generative AI will be used more and more in the future both by the researchers as well as the industry to be able to improve efficacy. However, efforts are needed to develop good quality big data within hearing healthcare to train the AI/ML models effectively.