Dear All,
There will be a Data Science and Statistics Seminar in the Math department today with AI/ human health interest.
Speaker is Dr. Jeremy Watts, who will be speaking today on how one may employ machine learning informed by brain data to understand Parkinson’s disease.
The talk will be today (Thursday 9/7) in Ayres Hall Rm 111 at 4:30PM.
For more information, please see at the end of this email, and if interested in attending the talks you may follow the calendar as I will be updating this information:
https://calendar.utk.edu/event/data_science_and_statistics_seminar_2076?utm_campaign=widget&utm_medium=widget&utm_source=University+of+Tennessee%2C+Knoxville
Thank you and looking forward to (maybe) seeing you.
Vasileios Maroulas
Speaker: Jeremy Watts
Affiliation: University of Tennessee Knoxville
Title: ML to Uncover the Role of Low Frequency Deep Brain Stimulation in Treating Parkinson's Disease
Abstract: Parkinson's disease (PD) is a progressive, neurodegenerative disorder resulting from the loss of dopaminergic neurons. PD is a chronic disease with no known cure. Over one million people in the United States are estimated to suffer from PD, with an annual national economic burden of $52 billion. Early in the disease course, dopaminergic medication can effectively manage most patients' motor symptoms. However, as the disease advances, patients may require advanced neurosurgical therapies such as deep brain stimulation (DBS), in which electrodes are implanted into the brain to help alleviate symptoms.
Predominately high frequency stimulation (180Hz) is applied to DBS; however, a growing body of literature suggests low frequency stimulation (60Hz) can alleviate gait symptoms in some PD patients. However, the interplay between medication and stimulation remains an open question. We analyzed wearable sensor measurements from a primary PD cohort collected in collaboration at Northwell Heath Hospitals (New York City, NY). In this talk, I will present our team's research using machine learning approaches to understand the interplay between medication and stimulation. This includes 1) comparing ML classifiers on wearable sensor gait measurements, 2) feature selection using SHAP values, 3) biostatistics analysis, and 4) creating a comparison aid for clinicians.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
To leave the list go here:
https://listserv.utk.edu/cgi-bin/wa?SUBED1=MATHTALK&A=1
|