2026-05-21T01:07:24Zhttps://keep.lib.asu.edu/oai/request

oai:keep.lib.asu.edu:node-2006602025-06-02T23:52:30Zoai_pmh:alloai_pmh:repo_items

200660 https://hdl.handle.net/2286/R.2.N.200660 http://rightsstatements.org/vocab/InC/1.0/ http://creativecommons.org/licenses/by-nc-sa/4.0 2025-05 32 pages Limaye, Anushka Wu, Teresa Forzani, Erica Al-Hindawi, Firas Barrett, The Honors College Harrington Bioengineering Program School of Biological & Health Systems Engineering School of Mathematical and Statistical Sciences Alzheimer's disease is a rapidly growing public health crisis. This challenging neurodegenerative disease starts with a prolonged pre-clinical phase, known as Mild Cognitive Impairment. (MCI) Researchers advocate for the importance in diagnosing individuals with MCI to prevent further disease progression. Current diagnostic approaches are not sufficient because they don't capture the fluctuant behavior expected with MCI symptoms; consequently, researchers have been exploring how studying lifestyle and routine data of individuals can improve diagnosis accuracy. The goal of this thesis was to contribute towards a working-effort in creating a machine learning model that can supplement the clinical diagnosis of MCI using naturalistic driving data. By implementing a state-of-the-art algorithm known ROCKET with classical machine learning classifiers, my work aims to help design a model that can accurately diagnose individuals with MCI. Alzheimer's Mild Cognitive Impairment Ad MCI rocket Machine learning ML Diagnostic tool Machine learning models Driving data Naturalistic data Feature Engineering Employing ROCKET and Machine Learning on Naturalistic Driving Data to Predict Mild Cognitive Impairment