Hierarchical Federated Learning on Healthcare Data: An Application to Parkinson's Disease

Author

Brandon J. Harvill

Date of Award

3-2023

Document Type

Thesis

Degree Name

Master of Science

Department

Department of Operational Sciences

First Advisor

Chancellor A. Johnstone, PhD

Abstract

Federated learning (FL) is a budding machine learning (ML) technique that seeks to keep sensitive data private, while overcoming the difficulties of Big Data. Specifically, FL trains machine learning models over a distributed network of devices, while keeping the data local to each device. We apply FL to a Parkinson’s Disease (PD) telemonitoring dataset where physiological data is gathered from various modalities to determine the PD severity level in patients. We seek to optimally combine the information across multiple modalities to assess the accuracy of our FL approach, and compare to traditional ”centralized” statistical and deep learning models.

AFIT Designator

AFIT-ENS-MS-23-M-124

Comments

A 12-month embargo was observed.

Approved for public release. Case number on file.

Recommended Citation

Harvill, Brandon J., "Hierarchical Federated Learning on Healthcare Data: An Application to Parkinson's Disease" (2023). Theses and Dissertations. 6995.
https://scholar.afit.edu/etd/6995