Explainable AI for Alzheimer Detection: A Review of Current Methods and Applications
Объяснимый искусственный интеллект для выявления болезни Альцгеймера: обзор современных методов и применений
2024-11-05
SCID: 54.1/bx9dud88
Discuss with AI
Alzheimer’s disease detectionExplainable AIFeature-AugmentedInterpretability frameworkMagnetic resonance imaging
Figures from the paper
Abstract (AI)
Alzheimer’s disease (AD) is the most common cause of dementia, marked by cognitive decline and memory loss. Recently, machine learning and deep learning techniques have introduced promising solutions for improving AD detection through MRI, especially in settings where specialists may not be readily available. These techniques offer the potential to assist general practitioners and non-specialists in busy clinical environments. However, the ‘black box’ nature of many AI techniques makes it challenging for non-expert physicians to fully trust their diagnostic accuracy. In this review, we critically evaluate current explainable AI (XAI) methods applied to AD detection and highlight their limitations. In addition, a new interpretability framework, called “Feature-Augmented”, was theoretically designed to improve model interpretability. This approach remains underexplored, primarily due to the scarcity of explainable AD-specific datasets. Furthermore, we underscore the importance of AI models being accurate and explainable, which enhance diagnostic confidence and patient care outcomes.
Key Findings
1
Accurate and explainable AI models are emphasized as important for increasing diagnostic confidence and improving patient-care outcomes.
2
Machine learning and deep learning applied to MRI show promise for improving Alzheimer’s disease detection, particularly where specialist access is limited.
3
The black-box nature of many AI models limits diagnostic trust and usability among non-expert physicians in clinical settings.
4
The proposed “Feature-Augmented” interpretability framework is theoretically designed to improve model interpretability but remains underexplored because explainable Alzheimer’s-specific datasets are scarce.
5
The review critically evaluates current explainable AI methods for Alzheimer’s detection and identifies important limitations in their application.
Research Object
Explainable AI methods and applications for Alzheimer’s disease detection from MRI
Research Subject
Interpretability, limitations, and diagnostic-trust implications of AI models for Alzheimer’s disease detection
Publication Details
Publication Date
2024-11-05
Journal
Publisher
ISSN
Cited by
44
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest