An Explainable Ensemble Machine Learning Framework for Early Detection of Alzheimer’s Disease Using Clinical Data
- Version
- Download 2
- File Size 604.05 KB
- File Count 1
- Create Date 20 July 2025
- Last Updated 20 July 2025
An Explainable Ensemble Machine Learning Framework for Early Detection of Alzheimer’s Disease Using Clinical Data
Kanimozhi Rajkumar1*,
Lalitha Kishore Jothi Ravikumar1,
Al Mushavir Rahman Mohamed Iliyas1,
Sowmiya Parisutha Packiyam1,
Gopal Samy Balakrishnan1
1 Department of Biotechnology, KIT - Kalaignarkarunanidhi Institute of Technology, Coimbatore, India
*Corresponding author: Kanimozhi Rajkumar,
(kanimozhi.rajkumar@gmail.com)
Abstract
Alzheimer’s Disease (AD) is a progressive neurodegenerative disorder and the leading cause of dementia, accounting for about 60–80% of cases worldwide. It is characterised by a gradual decline in cognitive functions such as memory, thinking, orientation, comprehension, and communication. The underlying pathology involves the buildup of beta-amyloid plaques and tau protein tangles in the brain, which cause neuronal damage and brain shrinkage over time. Clinically, symptoms range from mild forgetfulness to severe cognitive impairment, eventually impairing daily functioning. Globally, over 55 million people have dementia, with Alzheimer’s being the primary contributor. The societal and economic impacts are enormous, with dementia-related costs exceeding $1 trillion annually. A major challenge is that AD is often diagnosed only in later stages, after extensive neurodegeneration has occurred. Early detection is essential to slow progression, enhance quality of life, and optimise treatment options.
Keywords – Alzheimer’s Disease (AD), Machine Learning (ML), Early Detection, Explainability, Ensemble Learning, Clinical Data, Diagnostic Framework.
Download