# Detection and Classification of Alzheimer’s Disease Using Deep and Machine Learning

## TL;DR

This paper presents a machine learning and deep learning framework that combines clinical symptoms and brain imaging to accurately detect and stage Alzheimer's disease, using explainable AI to highlight relevant brain regions and features.

## Contribution

The novel contribution is a dual-modal framework integrating clinical and MRI data with interpretable AI to improve Alzheimer's detection and staging accuracy.

## Key findings

- Random Forest achieved 97% accuracy on clinical data, while CNN reached 94% accuracy in MRI-based staging.
- SHAP and Grad-CAM identified hippocampal atrophy and ventricular enlargement as key indicators of Alzheimer's disease.

## Abstract

The early identification of Alzheimer’s disease can be challenging, which limits prompt diagnosis and management options. In this study, we offer a realistic approach that combines routinely observed clinical symptoms with brain imaging to detect and stage Alzheimer’s disease. The approach increases accuracy and provides practical interpretation by identifying not just important early warning indications but also pertinent brain regions using explainable artificial intelligence approaches. The findings of this study could aid in clinical decision-making and offer a flexible framework for future research to develop more precise, clearer, and more easily accessible Alzheimer’s detection and staging techniques.

Background/Objectives: Alzheimer’s disease is the leading cause of dementia, marked by progressive cognitive decline and a severe socioeconomic burden. Early and accurate diagnosis is crucial to enhancing patient outcomes, yet traditional clinical and imaging assessments are often limited in sensitivity, particularly at early stages. This study presents a dual-modal framework that integrates symptom-based clinical data with magnetic resonance imaging (MRI) using machine learning (ML) and deep learning (DL) models, enhanced by explainable AI (XAI). Methods: Four ML classifiers—K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF)—were trained on demographic and clinical features. For stage-wise classification, five DL models—CNN, EfficientNetB3, DenseNet-121, ResNet-50, and MobileNetV2—were applied to MRI scans. Interpretability was incorporated through SHAP and Grad-CAM visualizations. Results: Random Forest achieves the highest accuracy of 97% on clinical data, while CNN achieves the best overall performance of 94% in MRI-based staging. SHAP and Grad-CAM were used to find clinically relevant characteristics and brain areas, including hippocampal atrophy and ventricular enlargement. Conclusions: Integrating clinical and imaging data and interpretable AI improves the accuracy and reliability of AD staging. The proposed model offers a valid and clear diagnostic route, which can assist clinicians in making timely diagnoses and adjusting individual treatment.