Enhancing Alzheimer’s Disease Diagnosis using Transparent AI Models: A Survey

Madhvi Garg; Akshay Juneja; Deepak Painuli; Priyanka Kumari

doi:10.70454/JRICST.2026.030306

Authors

Madhvi Garg Department of Computer Science and Engineering, College of Smart Computing, COER University, Roorkee, Uttarakhand, 247667, India. Author
Akshay Juneja Department of Computer Science and Engineering, College of Smart Computing, COER University, Roorkee, Uttarakhand, 247667, India Author
Deepak Painuli Department of Computer Science and Engineering, College of Smart Computing, COER University, Roorkee, Uttarakhand, 247667, India Author
Priyanka Kumari ECE Department, School of Engineering and Technology, CGC University, Mohali, Punjab, India Author

DOI:

https://doi.org/10.70454/JRICST.2026.030306

Keywords:

Alzheimer, GradCAM, LIME, LRP, SHAP, XAI

Abstract

The integration of artificial intelligence (AI) in Alzheimer’s disease detection has improved diagnostic capabilities. It enables accurate and early identification of the disease through advanced analysis of neuroimaging data, biomarkers, and cognitive assessments. The complexity of modern AI models is high and lack clinical adoption due to lack of transparency and interpretability. It creates a barrier for healthcare professionals to understand and trust the AI's decision-making process. This paper presents role of explainable artificial intelligence (XAI) to highlight the importance of high-performing AI models. The various XAI techniques are categorized based on their scope (global vs. local), implementation timing (ante-hoc vs. post-hoc), and applications (model-specific vs. model-agnostic). The global explanations provide an overall understanding of the model's behavior while local explanations focus on individual predictions. The ante-hoc models are interpretable from the start, and post-hoc models require additional techniques to explain their outputs. Also, model-specific approaches are used for particular algorithms, model-agnostic approaches are applied across different model types. The different XAI frameworks such as SHAP, LIME, Grad-CAM, and LRP are studied for AD classification to obtain model decisions without compromising accuracy. This paper also presents different challenges such as data imbalance and over fitting that provides a balance between model complexity and interpretability. The availability of small dataset of different stages of Alzheimer introduces scenes in the model’s performance. Also, model performs well during training and generates poor results during testing. It is observed that XAI algorithms have improved the transparency and trustworthiness in AI-assisted diagnostic systems for effective Alzheimer’s disease detection.

Downloads

Download data is not yet available.

References

[1] Kanpur, S., Bharadwaj, C. B., Hardwar, R., & Kayak, J. S. (2024). An approach for XAI visualizations for explains ability of Alzheimer's detection. In 2024 2nd International Conference on Networking, Embedded and Wireless Systems (ICNEWS) (pp. 1-6). IEEE.

[2] Visa, V., Shaffer, N., Mahmud, M., Subramanian, K., & Hajamohideen, F. (2024). Explainable artificial intelligence in Alzheimer's disease classification: A systematic review. Cognitive Computation, 16(1), 1-44.

[3] Nimbi, V., Shaffer, N., & Mahmud, M. (2024). Interpreting artificial intelligence models: A systematic review on the application of LIME and SHAP in Alzheimer's disease detection. Brain Informatics, 11(1), 10.

[4] Taine Khosroshahi, M., et al. (2025). Explainable artificial intelligence in neuroimaging of Alzheimer's disease. Diagnostics, 15(5), 612.

[5] Booting, D., et al. (2025). ADAMAEX—Alzheimer's disease classification via attention-enhanced auto encoders and XAI. Egyptian Informatics Journal, 30, 100688.

[6] Bib, N., Courtney, J., & McGuiness, K. (2025). Enhancing brain disease diagnosis with XAI: A review of recent studies. ACM Transactions on Computing for Healthcare, 6(2), 1-35.

[7] Ray, A. (2020). Explainable AI: From black box to glass box. Journal of the Academy of Marketing Science, 48(1), 137-141.

[8] Kauri, D., et al. (2022). Trustworthy artificial intelligence: A review. ACM Computing Surveys, 55(2), 1-38.

[9] Near, M., et al. (2021). A systematic review of human-computer interaction and explainable artificial intelligence in healthcare with artificial intelligence techniques. IEEE Access, 9, 153316-153348.

[10] Mamoshina, P., et al. (2016). Applications of deep learning in biomedicine. Molecular Pharmaceutics, 13(5), 1445-1454.

[11] Juneau, A., et al. (2024). XcepCovidNet: Deep neural networks-based COVID-19 diagnosis. Multimedia Tools and Applications, 1-31.

[12] Yang, G., et al. (2022). Inbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review, two showcases and beyond. Information Fusion, 77, 29-52.

[13] Kumar, D., & Mehta, M. A. (2023). An overview of explainable AI methods, forms and frameworks. In Springer International Publishing (pp. 43-59).

[14] Loch, H. W., et al. (2022). Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011-2022). Computer Methods and Programs in Biomedicine, 221, 107161.

[15] Ribera, M. T., Singh, S., & Guest in, C. (2016). "Why should I trust you?" Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1135-1144).

[16] Descant, L. A., et al. (2022). An explainable convolution neural network for the early diagnosis of Alzheimer's disease from 18F-FDG PET. Journal of Digital Imaging, 1-15.

[17] Ghassemi, M., et al. (2021). The false hope of current approaches to explainable artificial intelligence in health care. The Lancet Digital Health, 3(11), e745-e750.

[18] Jung, Y. J., et al. (2021). Explaining CNN and RNN using selective layer-wise relevance propagation. IEEE Access, 9, 18670-18681.

[19] Kamala, M. S., et al. (2021). Alzheimer's patient analysis using image and gene expression data and explainable-AI to present associated genes. IEEE Transactions on Instrumentation and Measurement, 70, 1-7.

[20] Shad, H. A., et al. (2021). Exploring Alzheimer's disease prediction with XAI in various neural network models. In TENCON 2021-2021 IEEE Region 10 Conference (pp. 720-725).

[21] Sidulova, M., et al. (2021). Analysis explainable image for Alzheimer's disease and mild cognitive impairment diagnosis. In IEEE Applied Imagery Pattern Recognition Workshop (AIPR) (pp. 1-6).

[22] Iliac, L., & Astounds, D. (2022). Explainable identification of dementia from transcripts using transformer networks. IEEE Journal of Biomedical and Health Informatics, 26(8), 4153-4164.

[23] El-Sapping, S., et al. (2021). A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer's disease. Scientific Reports, 11(1), 2660.

[24] Yang, C., et al. (2018). Visual explanations from deep 3D convolution neural networks for Alzheimer's disease classification. In AMIA Annual Symposium Proceedings (p. 1571).

[25] Lombardi, A., et al. (2022). A robust framework to investigate the reliability and stability of explainable artificial intelligence markers of mild cognitive impairment and Alzheimer's disease. Brain Informatics, 9(1), 1-17.

[26] Hernandez, M., et al. (2022). Explainable AI toward understanding the performance of the top three TADPOLE Challenge methods in the forecast of Alzheimer's disease diagnosis. Plops One, 17(5), e0264695.

[27] Lai, Y., et al. (2022). Identification of endoplasmic reticulum stress-associated genes and subtypes for prediction of Alzheimer's disease based on interpretable machine learning. Frontiers in Pharmacology, 13.

[28] Bogdanovic, B., et al. (2022). In-depth insights into Alzheimer's disease by using explainable machine learning approach. Scientific Reports, 12(1), 1-26.

[29] Chun, M. Y., et al. (2022). Prediction of conversion to dementia using interpretable machine learning in patients with amnesic mild cognitive impairment. Frontiers in Aging Neuroscience, 14.

[30] CSU, X., & Yan, X. (2022). A convenient and reliable multi-class classification model based on explainable artificial intelligence for Alzheimer's disease. In IEEE AEECA (pp. 671-675).

[31] Salish, A., et al. (2022). Investigating explainable artificial intelligence for MRI-based classification of dementia: A new stability criterion for explainable methods. In IEEE ICIP (pp. 4003-4007).

[32] Bloch, L., & Friedrich, C. M. (2022). Machine learning workflow to explain black-box models for early Alzheimer's disease classification evaluated for multiple datasets. ArXiv: 2205.05907.

[33] Dansk, S. O., et al. (2021). Developing an explainable machine learning-based personalised dementia risk prediction model: A transfer learning approach with ensemble learning algorithms. Frontiers in Big Data, 4, 21.

[34] Hammond, T. C., et al. (2020). Β-amyloidal and tau drive early Alzheimer's disease decline while glucose hypo metabolism drives late decline. Communications Biology, 3(1), 1-13.

[35] Bohlen, M., et al. (2019). Layer-wise relevance propagation for explaining deep neural network decisions in MRI-based Alzheimer's disease classification. Frontiers in Aging Neuroscience, 11, 194.

[36] Sudan, K. M., et al. (2022). Alzheimer's disease analysis using explainable artificial intelligence (XAI). In IEEE ICSCDS (pp. 419-423).

[37] Wang, D., et al. (2023). Deep neural network heat maps capture Alzheimer's disease patterns reported in a large meta-analysis of neuroimaging studies. NeuroImage, 269.

[38] Pohl, T., et al. (2022). Interpretability of deep neural networks used for the diagnosis of Alzheimer's disease. International Journal of Imaging Systems and Technology, 32(2), 673-686.

[39] Ruengchaijatuporn, N., et al. (2022). An explainable self-attention deep neural network for detecting mild cognitive impairment using multi-input digital drawing tasks. Alzheimer's Research & Therapy, 14(1), 1-11.

[40] Jain, V., et al. (2021). A novel AI-based system for detection and severity prediction of dementia using MRI. IEEE Access, 9, 154324-154346.

[41] Zhang, X., et al. (2021). An explainable 3D residual self-attention deep neural network for joint atrophy localization and Alzheimer's disease diagnosis using structural MRI. IEEE Journal of Biomedical and Health Informatics.

[42] Oh, K., et al. (2023). Learn-explain-reinforce: Counterfactual reasoning and its guidance to reinforce an Alzheimer's disease diagnosis model. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4), 4843-4857.

[43] Graham, N., et al. (2023). Prediction of Alzheimer's progression based on multimodal deep-learning-based fusion and visual explain ability of time-series data. Information Fusion, 92, 363-388.

[44] Shojaei, S., et al. (2023). An evolutionary explainable deep learning approach for Alzheimer's MRI classification. Expert Systems with Applications, 220.

[45] Lovelies, G., et al. (2022). Explanation-driven HCI model to examine the mini-mental state for Alzheimer's disease. ACM Transactions on Multimedia Computing, Communications, and Applications.

[46] Yu, L., et al. (2022). A novel explainable neural network for Alzheimer's disease diagnosis. Pattern Recognition, 131.

[47] Kim, M., et al. (2021). Interpretable temporal graph neural network for prognostic prediction of Alzheimer's disease using longitudinal neuroimaging data. In IEEE BIBM (pp. 1381-1384).

[48] Borden, V., et al. (2022). Explainable AI points to white matter hyper intensities for Alzheimer's disease identification: A preliminary study. In IEEE EMBC (pp. 484-487).

[49] Garcia-Gutierrez, F., et al. (2022). GA-MADRID: Design and validation of a machine learning tool for the diagnosis of Alzheimer's disease and front temporal dementia using genetic algorithms. Medical & Biological Engineering & Computing, 60(9), 2737-2756.

[50] Wreaked, J., et al. (2018). Visualizing convolution networks for MRI-based diagnosis of Alzheimer's disease. In Understanding and Interpreting Machine Learning in Medical Image Computing Applications (pp. 24-31). Springer.