Explainable Artificial Intelligence in Alzheimer’s Disease Classification: A Systematic Review
Объяснимый искусственный интеллект в классификации болезни Альцгеймера: систематический обзор
2023-11-13
SCID: 54.1/wgpc4b2m
Discuss with AI
Alzheimer’s disease classificationComputer-aided diagnosisExplainable artificial intelligenceLIMESHAP
Figures from the paper
Abstract (AI)
Abstract Context: Artificial Intelligence (AI) in the medical domain has achieved remarkable results on various metrics primarily due to recent advancements in computational capabilities. However, AI models used for Computer Aided Diagnosis (CAD) have limited acceptance and trust due to their typical {Blackbox} nature. Consequently, explainable AI (XAI) is needed to justify the trustworthiness of the machine's predictions. Approach: In this work, we undertake a systematic review based on PRISMA guidelines on research articles investigating Alzheimer's Disease (AD) prediction with XAI for the past decade. The review was driven by carefully formulated research questions (RQ) which helped categorize AI models into different XAI methods(Post-hoc, Ante-hoc, Model-Agnostic, Model-Specific, etc) and frameworks (LIME, SHAP, GradCAM, LRP, etc.). Summary: This categorisation provides broad coverage of the interpretation spectrum from intrinsic (model-specific, ante-hoc models) to complex patterns (model-agnostic, post-hoc models) and by taking local explanations to a global scope. Additionally, the study categorizes merit in terms of different forms of interpretation to provide in-depth insight into the factors that support the clinical diagnosis of AD. Finally, limitations and open research challenges are outlined, and possible prospects are presented.
Key Findings
1
It categorizes AD-detection models across XAI dimensions including post-hoc versus ante-hoc, model-agnostic versus model-specific, and local versus global explanations.
2
The review covers major XAI frameworks, including LIME, SHAP, GradCAM, and Layer-wise Relevance Propagation.
3
The review discusses clinically relevant interpretation factors, limitations, open challenges, and future prospects for adopting XAI in AD detection.
4
The surveyed methods span interpretations from intrinsically explainable models to complex post-hoc explanations and from local predictions to global understanding.
5
The systematic review examines explainable AI methods used for Alzheimer’s disease detection over the last decade.
Research Object
Explainable AI (XAI) methods applied to Alzheimer's disease detection/classification
Research Subject
Explainability and interpretability of AI predictions, including XAI approaches, frameworks, and clinical factors supporting Alzheimer’s disease diagnosis
Publication Details
Publication Date
2023-11-13
Journal
Publisher
ISSN
Cited by
215
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai8
The PRISMA 2020 statement: an updated guideline for reporting systematic reviews2021
A Unified Approach to Interpreting Model Predictions2017
"Why Should I Trust You?": Explaining the Predictions of Any Classifier2016
The potential for artificial intelligence in healthcare2019
A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI2020
Recent advances and applications of machine learning in solid-state materials science2019
A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer’s disease2021
Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification2019