Explainable Artificial Intelligence in Neuroimaging of Alzheimer’s Disease DOI Creative Commons

Mahdieh Taiyeb Khosroshahi,

Soroush Morsali, Sohrab Gharakhanlou

et al.

Diagnostics, Journal Year: 2025, Volume and Issue: 15(5), P. 612 - 612

Published: March 4, 2025

Alzheimer's disease (AD) remains a significant global health challenge, affecting millions worldwide and imposing substantial burdens on healthcare systems. Advances in artificial intelligence (AI), particularly deep learning machine learning, have revolutionized neuroimaging-based AD diagnosis. However, the complexity lack of interpretability these models limit their clinical applicability. Explainable Artificial Intelligence (XAI) addresses this challenge by providing insights into model decision-making, enhancing transparency, fostering trust AI-driven diagnostics. This review explores role XAI neuroimaging, highlighting key techniques such as SHAP, LIME, Grad-CAM, Layer-wise Relevance Propagation (LRP). We examine applications identifying critical biomarkers, tracking progression, distinguishing stages using various imaging modalities, including MRI PET. Additionally, we discuss current challenges, dataset limitations, regulatory concerns, standardization issues, propose future research directions to improve XAI's integration practice. By bridging gap between AI interpretability, holds potential refine diagnostics, personalize treatment strategies, advance research.

Language: Английский

Interpreting artificial intelligence models: a systematic review on the application of LIME and SHAP in Alzheimer’s disease detection DOI Creative Commons
Vimbi Viswan,

Noushath Shaffi,

Mufti Mahmud

et al.

Brain Informatics, Journal Year: 2024, Volume and Issue: 11(1)

Published: April 5, 2024

Abstract 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 (DL) models. The Local Interpretable Model-agnostic Explanations (LIME) Shaply Additive exPlanation (SHAP) frameworks have grown as popular interpretive tools ML DL This article provides a systematic review application LIME SHAP interpreting detection Alzheimer’s disease (AD). Adhering PRISMA Kitchenham’s guidelines, we identified 23 relevant articles investigated these frameworks’ prospective capabilities, benefits, challenges depth. results emphasise XAI’s crucial role strengthening trustworthiness AI-based AD predictions. aims provide fundamental capabilities XAI enhancing fidelity within clinical decision support systems prognosis.

Language: Английский

Citations

58
Explainable machine learning models based on multimodal time-series data for the early detection of Parkinson’s disease DOI
Muhammad Junaid, Sajid Ali, Fatma Eid

et al.

Computer Methods and Programs in Biomedicine, Journal Year: 2023, Volume and Issue: 234, P. 107495 - 107495

Published: March 23, 2023

Language: Английский

Citations

50
Explainable Artificial Intelligence in Alzheimer’s Disease Classification: A Systematic Review DOI Creative Commons
Vimbi Viswan,

Noushath Shaffi,

Mufti Mahmud

et al.

Cognitive Computation, Journal Year: 2023, Volume and Issue: 16(1), P. 1 - 44

Published: Nov. 13, 2023

Abstract The unprecedented growth of computational capabilities in recent years has allowed Artificial Intelligence (AI) models to be developed for medical applications with remarkable results. However, a large number Computer Aided Diagnosis (CAD) methods powered by AI have limited acceptance and adoption the domain due typical blackbox nature these models. Therefore, facilitate among practitioners, models' predictions must explainable interpretable. emerging field (XAI) aims justify trustworthiness predictions. This work presents systematic review literature reporting Alzheimer's disease (AD) detection using XAI that were communicated during last decade. Research questions carefully formulated categorise into different conceptual approaches (e.g., Post-hoc, Ante-hoc, Model-Agnostic, Model-Specific, Global, Local etc.) frameworks (Local Interpretable Model-Agnostic Explanation or LIME, SHapley Additive exPlanations SHAP, Gradient-weighted Class Activation Mapping GradCAM, Layer-wise Relevance Propagation LRP, XAI. categorisation provides broad coverage interpretation spectrum from intrinsic Ante-hoc models) complex patterns Post-hoc taking local explanations global scope. Additionally, forms interpretations providing in-depth insight factors support clinical diagnosis AD are also discussed. Finally, limitations, needs open challenges research outlined possible prospects their usage detection.

Language: Английский

Citations

50
Review on Alzheimer Disease Detection Methods: Automatic Pipelines and Machine Learning Techniques DOI Creative Commons
Amar Shukla, Rajeev Tiwari, Shamik Tiwari

et al.

Sci, Journal Year: 2023, Volume and Issue: 5(1), P. 13 - 13

Published: March 21, 2023

Alzheimer’s Disease (AD) is becoming increasingly prevalent across the globe, and various diagnostic detection methods have been developed in recent years. Several techniques are available, including Automatic Pipeline Methods Machine Learning that utilize Biomarker Methods, Fusion, Registration for multimodality, to pre-process medical scans. The use of automated pipelines machine learning systems has proven beneficial accurately identifying AD its stages, with a success rate over 95% single binary class classifications. However, there still challenges multi-class classification, such as distinguishing between MCI, well sub-stages MCI. research also emphasizes significance using multi-modality approaches effective validation detecting stages.

Language: Английский

Citations

45
Alzheimer’s disease diagnosis from single and multimodal data using machine and deep learning models: Achievements and future directions DOI
Ahmed Elazab, Changmiao Wang, M. Abdel-Aziz

et al.

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 255, P. 124780 - 124780

Published: July 14, 2024

Language: Английский

Citations

19
Orchestrating explainable artificial intelligence for multimodal and longitudinal data in medical imaging DOI Creative Commons
Aurélie Pahud de Mortanges, Haozhe Luo,

Shelley Zixin Shu

et al.

npj Digital Medicine, Journal Year: 2024, Volume and Issue: 7(1)

Published: July 22, 2024

Abstract Explainable artificial intelligence (XAI) has experienced a vast increase in recognition over the last few years. While technical developments are manifold, less focus been placed on clinical applicability and usability of systems. Moreover, not much attention given to XAI systems that can handle multimodal longitudinal data, which we postulate important features many workflows. In this study, review, from perspective, current state for datasets highlight challenges thereof. Additionally, propose orchestrator, an instance aims help clinicians with synopsis resulting AI predictions, corresponding explainability output. We several desirable properties such as being adaptive, hierarchical, interactive, uncertainty-aware.

Language: Английский

Citations

11
Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning DOI
Emrullah Şahin, Naciye Nur Arslan, Durmuş Özdemir

et al.

Neural Computing and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 18, 2024

Language: Английский

Citations

11
Applications of AI in Neurological Disease Detection — A Review of Specific Ways in Which AI Is Being Used to Detect and Diagnose Neurological Disorders, Such as Alzheimer's and Parkinson's DOI
Dolly Sharma, Priyanka Kaushik

Published: Jan. 3, 2025

This chapter presents a groundbreaking procedure to neurological affliction location through coordination of wearable sensors with predominant engineered insights (AI) calculations. Continuously collected data from guides the devices recognize early biomarkers disease, encouraging convenient intervention and optimized treatment outcomes. In addition, closed-loop feedback mechanism characteristic grants versatile checking custom-fitted each patient's ensuring doubt precise discovery adjustments in notoriety. The integration AI into sensor machine enhances predictive analytics, providing valuable bits knowledge viability personalized plans. Standardization information codecs conventions is basic encourage consistent records substitute collaboration among healthcare carriers. Collaborative efforts analysts, clinicians, policymakers, ethicists are essential establish guidelines quality practices for mindful evenhanded execution AI-driven innovation healthcare. By embracing development, collaboration, ethical stewardship, we will open full potential those innovations upgrade individual care boost this field neurology.

Language: Английский

Citations

1
Explainable Artificial Intelligence of Multi-Level Stacking Ensemble for Detection of Alzheimer’s Disease Based on Particle Swarm Optimization and the Sub-Scores of Cognitive Biomarkers DOI Creative Commons
Abdulaziz AlMohimeed, Redhwan M. A. Saad, Sherif Mostafa

et al.

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 123173 - 123193

Published: Jan. 1, 2023

Alzheimer's disease (AD) is a progressive neurological disorder characterized by memory loss and cognitive decline, affecting millions worldwide. Early detection crucial for effective treatment, as it can slow progression improve quality of life. Machine learning has shown promise in AD using various medical modalities. In this paper, we propose novel multi-level stacking model that combines heterogeneous models modalities to predict different classes AD. The include sub-scores (e.g., clinical dementia rating – sum boxes, assessment scale) from the Disease Neuroimaging Initiative dataset. proposed approach, level 1, used six base (Random Forest (RF), Decision Tree (DT), Support Vector (SVM), Logistic Regression (LR), K-nearest Neighbors (KNN), Native Bayes (NB)to train each modality (ADAS, CDR, FQA). Then, build training outputs set staking testing outcomes set. 2, three are produced trains evaluates based on output 6 (RF, LR, DT, SVM, KNN, NB) combined Stacking meta-learners evaluate (RF). Finally, 3, prediction FQA) datasets merged new dataset, which testing. Training meta-learner, meta-learner produce final prediction. Our research also aims provide explanations, ensuring efficiency, effectiveness, trust through explainable artificial intelligence (XAI). Feature selection optimization Particle Swarm Optimization select most appropriate sub-scores. shows significant potential improving early diagnosis. results demonstrate multi-modality approach outperforms single-modality approaches. Moreover, achieve highest performance with selected features compared regular ML classifiers full multi-modalities, achieving accuracy, precision, recall, F1-scores 92.08%, 92.07%, 92.01% two classes, 90.03%, 90.19%, 90.05% respectively.

Language: Английский

Citations

19
Alzheimer's disease diagnosis in the metaverse DOI Creative Commons
Jalal Safari Bazargani, Nasir Rahim, Abolghasem Sadeghi‐Niaraki

et al.

Computer Methods and Programs in Biomedicine, Journal Year: 2024, Volume and Issue: 255, P. 108348 - 108348

Published: July 21, 2024

Language: Английский

Citations

8