Development of an innovative and transparent symptom checker with a focus on automatic speech recognition

Abstract

This paper presents the creation of a medical symptom checker with state-of-the-art machine and deep learning technologies. It examines the use and development of a speech to text model which is trained on medical datasets. The model is discussed, highlighting its advantages and disadvantages for the study. Moreover, the paper introduces a web application which provides a user-friendly interface, allowing users to interact with the models and showcase the results. Finally, the paper offers an outlook on the future use cases of the application and how it may improve healthcare outcomes.