Interpreting artificial intelligence models: a systematic review on the application of LIME and SHAP in Alzheimer’s disease detection
Интерпретация моделей искусственного интеллекта: систематический обзор применения LIME и SHAP для обнаружения болезни Альцгеймера
2024-04-05
SCID: 54.1/3gzkehdj
Discuss with AI
Alzheimer's disease detectionExplainable artificial intelligenceLIMEPRISMASHAP
Figures from the paper
Abstract (AI)
Explainable artificial intelligence (XAI) has gained much interest in recent years for its ability to explain the complex decision-making process of machine learning (ML) and deep learning (DL) models. The Local Interpretable Model-agnostic Explanations (LIME) and Shaply Additive exPlanation (SHAP) frameworks have grown as popular interpretive tools for ML and DL models. This article provides a systematic review of the application of LIME and SHAP in interpreting the detection of Alzheimer's disease (AD). Adhering to PRISMA and Kitchenham's guidelines, we identified 23 relevant articles and investigated these frameworks' prospective capabilities, benefits, and challenges in depth. The results emphasise XAI's crucial role in strengthening the trustworthiness of AI-based AD predictions. This review aims to provide fundamental capabilities of LIME and SHAP XAI frameworks in enhancing fidelity within clinical decision support systems for AD prognosis.
Key Findings
1
A systematic review following PRISMA and Kitchenham identified 23 relevant studies applying LIME and/or SHAP to AD detection models.
2
LIME and SHAP are prominent XAI frameworks frequently applied to interpret ML and DL models for Alzheimer’s disease (AD) detection.
3
LIME and SHAP provide fundamental capabilities to enhance fidelity in clinical decision support systems for AD prognosis.
4
The review examines the prospective capabilities, benefits, and challenges of using LIME and SHAP specifically in AD detection contexts.
5
The reviewed literature indicates XAI (via LIME and SHAP) plays a crucial role in strengthening the trustworthiness of AI-based AD predictions.
Research Object
Application of LIME and SHAP explainable AI frameworks in Alzheimer’s disease detection models
Research Subject
Capabilities, benefits, challenges, and impact of LIME and SHAP on the interpretability, fidelity, and trustworthiness of ML/DL-based Alzheimer’s disease detection and clinical decision support
Publication Details
Publication Date
2024-04-05
Journal
Publisher
ISSN
Cited by
410
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai6
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
Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence2023
A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer’s disease2021
Explainable Artificial Intelligence in Alzheimer’s Disease Classification: A Systematic Review2023
Cited by3
Explainable Artificial Intelligence in Neuroimaging of Alzheimer’s Disease2025
Explainable AI for Alzheimer Detection: A Review of Current Methods and Applications2024
Reducing misdiagnosis in AI-driven medical diagnostics: a multidimensional framework for technical, ethical, and policy solutions2025