Orthostatic Hypotension (OH) is a valuable biomarker for neurological diseases such as Parkinson’s Disease and Alzheimer’s. It is known that OH can be caused by autonomic dysfunction, one of the early markers of neurodegeneration. However, the current diagnosis of OH is quite tedious and infeasible in a clinical setting, therefore it is vastly underdiagnosed, despite its value. Our goal is to detect OH using machine learning transformer models using data from 1) EEG Signal, 2) Respiration Signal and 3) Wireless Signal based Respiration Signal. This would allow for a simple and accurate at-home test for OH.

I am interested in the potential of AI when applied to healthcare because of its practical uses and the large amount of data available. In particular, our research involves signal processing, transformer architecture, and data analysis, and I hope to be able to gain a pragmatic understanding of these areas. I hope that through the research process, I develop my critical thinking and awareness of the current field, while creating and exploring the application of AI in medical diagnosis.