Advancing Early Alzheimer's Disease Detection in Underdeveloped Areas with Fair Explainable AI Methods

Abstract

Artificial intelligence (AI)-based telemedicine systems for early Alzheimer's detection using low-cost modalities are vital for rural or underdeveloped areas where travelling distance and high-cost devices like MRI are drawbacks. These systems require eXplainable AI (XAI) for reliable outcomes and intuitive explanations. Current XAI evaluations lack input from medical professionals and overlook stakeholder diversity, leading to potential biases. This project aims to develop a cost-effective AI telemedicine system, enhance early AD detection in underdeveloped areas, reduce healthcare disparities, and assess XAI methods with quality and fairness to mitigate biases for high-quality and fair explained outcomes.