Early Alzheimer’s Screening with Affordable ML Approach

Abstract

Detecting Alzheimer’s disease at an early stage is essential for timely intervention and improved outcomes. This study presents a stepwise, cost-effective diagnostic framework that integrates cognitive assessments, family history, and blood biomarkers. Individual risk is estimated using logistic regression, with advanced diagnostic tests recommended only for high-risk cases. Explainable AI techniques, such as SHAP, offer trans- parent and interpretable predictions for clinicians and patients. The platform generates personalized risk reports via an intuitive digital interface, enabling scalable early screening, reducing unnecessary invasive testing, and supporting continuous cognitive health monitoring. This paper aims to present and analyze a stepwise, low-cost screening framework for early Alzheimer’s disease detection based on logistic regression and explainable AI. The framework is evaluated in terms of risk stratification design, practical deployability, and potential to reduce dependence on invasive diagnostics.