Explainable Deep Learning and Ensemble-Based Framework for Alzheimer’s Disease Diagnosis and Progression Prediction

View at publisher Summarise with VIRAT
Authors: Fathima Minnah A, R Srivatsan Sharath Cherian Thomas, C. R. Dhivyaa
Cited by: 0
References: 15

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Alzheimer’s Disease (AD) represents a steadily advancing neurodegenerative condition defined by progressive cognitive deterioration, where recognizing subtle onset patterns and anticipating disease trajectory remain central to therapeutic decision-making. This research outlines an interpretable hybrid ensemble learning construct that blends conventional and deep computational paradigms for multidimensional assessment of cognitive integrity and progression forecasting from Mild Cognitive Impairment (MCI) toward AD. The framework integrates Logistic Regression, XGBoost, and an Artificial Neural Network (ANN), trained on heterogeneous data derived from ADNI dataset that encompasses volumetric Magnetic Resonance Imaging (MRI) indices and neurocognitive evaluations. It integrates the strengths of each model, producing the final classification. Additionally, SHAP analysis is also performed to understand the feature contributions for the AD prediction. Experimental results prove that the proposed ensemble model achieves high predictive accuracy.

Fields of Study & Subjects

Dementia and Cognitive Impairment Research Artificial Intelligence in Healthcare Alzheimer's disease research and treatments

Publication details

Journal / source
International Conference on Computing, Communication, Control and Cyber-Physical Systems (I5CPS)
Pages
1–6
Publication date
26 February 2026
Language
EN