Towards Alzheimer's Disease Progression Assessment: A Review of Machine Learning Methods

TL;DR

This review paper discusses recent machine learning methods for assessing Alzheimer's Disease progression, highlighting advances, challenges, and future research directions in leveraging big data and imaging techniques.

Contribution

It provides a comprehensive overview of prevalent ML models for AD progression assessment and insights into future research opportunities.

Findings

ML models show promise in early AD detection

Imaging data enhances disease progression understanding

Challenges include data quality and model interpretability

Abstract

Alzheimer's Disease (AD), as the most devastating neurodegenerative disease worldwide, has reached nearly 10 million new cases annually. Current technology provides unprecedented opportunities to study the progression and etiology of this disease with the advanced in imaging techniques. With the recent emergence of a society driven by big data and machine learning (ML), researchers have exerted considerable effort to summarize recent advances in ML-based AD diagnosis. Here, we outline some of the most prevalent and recent ML models for assessing the progression of AD and provide insights on the challenges, opportunities, and future directions that could be advantageous to future research in AD using ML.