Alzheimer's Disease Prediction Using Machine Learning

References

[1] Nanni, L., Lumini, A., & Brahnam, S. (2021). Ensemble learning strategies for Alzheimer’s disease classification using MRI scans. Computer Methods and Programs in Biomedicine, 198, 105773.

[2] Limitations: Increased computational time and limited clinical interpretability.

[3] Zhang, Y., Wang, X., & Li, H. (2022). Dual- attention convolutional neural networks for Alzheimer’s disease stage classification. IEEE Journal of Biomedical and Health Informatics, 26(2), 567–576.

[4] Limitations: Attention maps were sensitive to training data and failed under unseen anomalies.

[5] Ravi, D., Wong, C., & Lo, B. (2022). Deep multimodal learning for early Alzheimer’s diagnosis: Integrating clinical and imaging data. Neurocomputing, 493, 45–55.

[6] Limitations: Integration complexity and data heterogeneity made real-world deployment challenging.

[7] Yu, X., Liu, Z., & Zhao, J. (2023). Transformer- based 3D models for Alzheimer’s disease detection from brain MRI scans. Medical Image Analysis, 85, 102727.

[8] Limitations: High memory usage and low interpretability of Transformer architectures.

[9] Joshi, M., Patel, D., & Kaur, R. (2023). Unsupervised contrastive learning for feature representation in Alzheimer's detection. Pattern Recognition Letters, 169, 104–112.

[10] Limitations: Strong dependency on data augmentation quality and labeled fine-tuning.

[11] Gupta, A., Sharma, T., & Rao, V. (2024). Capsule networks for structural abnormality detection in early-stage Alzheimer’s disease. Artificial Intelligence in Medicine, 144, 102460.

[12] Limitations: Difficult to train and computationally intensive compared to CNNs.

[13] El-Gamal, A., Farag, A., & Saad, A. (2024). Federated deep learning for privacy-preserving Alzheimer’s disease prediction. Journal of Biomedical Informatics, 144, 104235.

[14] Limitations: Communication overhead and non- i.i.d. data across hospitals hindered performance.

[15] Singh, R., & Verma, N. (2025). Lightweight CNN model for Alzheimer’s screening on mobile devices. Journal of Medical Systems, 49(1), 8.

[16] Limitations: Slight reduction in accuracy due to model quantization and shallower architecture.

@article{1710498,
      author = {Syeda Jamala Fatima, Dr. Omar khan Durrani},
      title = {Alzheimer's Disease Prediction Using Machine Learning},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {9},
      number = {3},
      pages = {210-214},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1710498.pdf},
      abstract = {Alzheimer?s disease is a progressive neurodegenerative condition that affects millions of people worldwide, causing memory loss, cognitive decline, and eventual loss of independence. Early detection is essential for slowing its progression and improving patient quality of life. This project presents a deep learning-based system for the automatic detection of Alzheimer?s disease using medical imaging data, specifically MRI scans. Leveraging convolutional neural networks (CNNs), the model is trained to distinguish between healthy individuals and patients at different stages of the disease. It learns to identify subtle spatial and structural abnormalities in brain images that often go unnoticed in traditional analysis. The framework is developed and validated using benchmark datasets such as ADNI, ensuring robust and reliable performance. Experimental results show high accuracy, sensitivity, and specificity, highlighting the effectiveness of deep learning in detecting early signs of Alzheimer?s. This approach represents a promising advancement toward automated, non-invasive, and efficient diagnosis, supporting clinicians in early intervention and personalized treatment planning.},
      keywords = {Alzheimer, convolutional neural networks (CNNs), MRI, deep learning, ADNI},
      month = {September},
      doi = {https://doi.org/10.64388/IREV9I3-1710498-4358}
  }