Neuroanatomical-Based Machine Learning Prediction of Alzheimer's Disease Across Sex and Age
Public DepositedAlzheimer's Disease (AD) is a progressive neurodegenerative disorder characterized by cognitive decline and memory loss. In 2024, in the US alone, it affects approximately 1 in 9 people aged 65 and older, representing 10.9% of this population. This amounts to 6.9 million individuals, with women (4.2 million) constituting more than men (2.7 million). Magnetic resonance imaging (MRI) has emerged as a valuable tool for examining brain structure and identifying potential AD biomarkers. Early detection and accurate AD diagnosis are crucial for timely intervention and management. Moreover, monitoring disease progression and evaluating treatment effectiveness heavily rely on identifying reliable biomarkers. While sex contributes to Alzheimer's prevalence, age remains the primary risk factor, with incidence increasing significantly with each decade. However, the reasons for the variation of biomarkers with age remain unclear. This study performs predictive analyses by employing machine learning techniques to identify key brain regions associated with AD using numerical data derived from anatomical MRI scans, going beyond standard statistical methods. Additionally, subgroup analyses identified key brain regions that strongly predicted AD across three age groups: younger (69-76 years), older (77-84 years), and unified (69-84 years). Using the Random Forest Algorithm, we achieved 92.87% accuracy in detecting AD from Mild Cognitive Impairment, and Cognitive Normals. The hippocampus, amygdala, and entorhinal cortex consistently showed volume decreases across sexes and age groups despite varying prevalence rates between males and females. For instance, the right amygdala exhibited decreased volume in younger males (aged 69-76), while in females, this decline was observed in the older group (aged 77-84). Both younger males and females (aged 69-76) exhibited volume decreases in the right hippocampus, suggesting its importance in the early stages of AD. Older males (aged 77-84) showed substantial volume decreases in the left inferior temporal cortex. Additionally, the left middle temporal cortex showed decreased volume in females, suggesting a potential female-specific influence, while the right entorhinal cortex may have a male-specific impact. These age-specific sex differences could inform clinical research and treatment strategies, aiding in identifying neuroanatomical markers and therapeutic targets for future research and clinical interventions.
- Creator
- Contributors
- Degree
- Unit
- Publisher
- Identifier
- etd-123372
- Keyword
- Advisor
- Orcid
- Committee
- Defense date
- Year
- 2024
- Date created
- 2024-07-18
- Resource type
- Source
- etd-123372
- Rights statement
- Last modified
- 2024-08-26
Relations
- In Collection:
Items
Items
Thumbnail | Title | Visibility | Embargo Release Date | Actions |
---|---|---|---|---|
|
Bhaavin_MS_Thesis.pdf | Public | Download | |
|
Bhaavin_MS_Thesis_ppt_slides.pdf | Public | Download |
Permanent link to this page: https://digital.wpi.edu/show/sq87c015j