Dissertation
Using machine learning to differentiate between healthy aging, mild cognitive impairment, & Alzheimer's disease
Doctor of Philosophy (Ph.D.), Drexel University
Sep 2018
DOI:
https://doi.org/10.17918/D8TH5X
Abstract
Alzheimer's disease (AD) is an insidious disorder in which pathology may develop decades before outward symptoms become apparent. Identification of this disease in its earliest stages would provide the greatest opportunity for successful treatment. Current recommendations place patients in groups based primarily upon CSF -amyloid (A) levels, but the procedure to gather these data is invasive. If less intrusive methods could be identified to successfully predict which individuals are especially prone to develop AD, the benefits would be invaluable. Many studies have attempted to identify these individuals using neuroimaging methods such as MRI or PET, but very few studies have incorporated EEG data, despite research indicating its relationship with AD pathology. In this analysis, multimodal classifiers incorporating EEG, MRI, and PET data were developed and used in an attempt to differentiate between AD patients and a healthy control group, as well as MCI patients with AD A pathology and those without. Additionally, repeated-measures event-related potential (ERP) data were analyzed to directly examine changes related to AD progression.
Metrics
52 File views/ downloads
56 Record Views
Details
- Title
- Using machine learning to differentiate between healthy aging, mild cognitive impairment, & Alzheimer's disease
- Creators
- Monica Truelove-Hill - DU
- Contributors
- John Kounios (Advisor) - Drexel University (1970-)
- Awarding Institution
- Drexel University
- Degree Awarded
- Doctor of Philosophy (Ph.D.)
- Publisher
- Drexel University; Philadelphia, Pennsylvania
- Resource Type
- Dissertation
- Language
- English
- Academic Unit
- Psychological and Brain Sciences (Psychology); College of Arts and Sciences; Drexel University
- Other Identifier
- 8145; 991014632252304721