Page 119 - DP-2-3

Design+

ARTICLE
Machine learning strategies for predicting

Alzheimer’s disease progression

Adhinrag Kalarikkal Induchudan and Kevin Curran*
Faculty of Computing, Engineering and The Built Environment, School of Computing, Engineering,
and Intelligent Systems, Ulster University, Londonderry, Ireland

Abstract

Alzheimer’s disease (AD) represents a significant global health challenge, affecting
millions of individuals worldwide through progressive cognitive decline and behavioral
changes. The burden extends beyond patients to caregivers and healthcare systems.
While traditional diagnostic methods pose financial obstacles, emerging non-imaging
techniques show promise. Machine learning has emerged as a transformative approach
for enhancing both diagnosis and management. This study aims to develop a robust
multi-class classification model using random forest (RF) and extreme gradient boosting
algorithms on non-imaging data from the Australian AD Neuroimaging Initiative,
with emphasis on the Australian Imaging, Biomarkers, and Lifestyle Study of Aging.
Extensive data analysis was conducted, including feature importance and selection,
to improve interpretability and classification accuracy. Synthetic oversampling was
applied to address class imbalance. The findings indicate the superiority of the tuned
*Corresponding author: RF model, achieving 90% in accuracy, precision, recall, and F1 scores. In addition,
Kevin Curran cost-effective diagnostic variables were explored, with neuropsychology assessment
(kj.curran@ulster.ac.uk) variables demonstrating exceptional accuracy (90%). This research contributes to early
Citation: Induchudan AK, Curran AD detection, personalized treatment, and optimized resource allocation.
K. Machine learning strategies
for predicting Alzheimer’s
disease progression. Design+. Keywords: Alzheimer’s disease; Machine learning; Python classification model;
2025;2(3):025270031.
doi: 10.36922/DP025270031 Non-imaging data; Random Forest; Extreme gradient boosting; Australian imaging
biomarkers and lifestyle study of aging; Diagnosis
Received: July 3, 2025
Revised: July 23, 2025
Accepted: August 1, 2025
1. Introduction
Published online: August 21, 2025
Alzheimer’s disease (AD) represents a significant global health challenge, affecting
Copyright: © 2025 Author(s). millions of individuals worldwide. This condition progressively impairs memory,
This is an Open-Access article
distributed under the terms cognitive function, and behavior, ultimately leading to severe disability and death. AD
of the Creative Commons not only affects those diagnosed but also places considerable strain on caregivers and
AttributionNoncommercial License, healthcare systems, escalating the burden of care and resource allocation. Initially, AD
permitting all non-commercial use,
distribution, and reproduction in any may manifest as mild forgetfulness, but it gradually progresses to encompass a wide
medium, provided the original work range of symptoms that deteriorate over time, subjecting both patients and their families
is properly cited. to a distressing trajectory of decline and loss. The emotional toll of AD extends beyond
1
Publisher’s Note: AccScience cognitive impairment, significantly affecting the well-being of families and caregivers.
Publishing remains neutral with The continuous demands of caregiving challenge emotional resilience and endurance.
regard to jurisdictional claims in
published maps and institutional However, amidst these challenges, there is a shared commitment to confronting AD with
affiliations. resolve and innovation.

Volume 2 Issue 3 (2025) 1 doi: 10.36922/DP025270031