Sign in Subscribe
Alzheimer's disease

Breakthrough in Alzheimer's Disease Prediction: IoMT-Driven Model Empowered with Transfer Learning and Explainable AI

Strategic Insights

— 1 min read

Researchers from the Department of Computer Science have made a groundbreaking discovery in the field of Alzheimer's disease prediction using the Internet of Medical Things (IoMT). The study proposes an IoMT-driven Alzheimer's prediction framework that combines transfer learning with explainable AI, achieving 97.77% accuracy and outperforming several state-of-the-art methods. This breakthrough has the potential to support timely diagnosis, patient monitoring, and personalized interventions, positioning the framework as a practical candidate for integration into Healthcare 5.0 ecosystems.

Key Takeaways:

  • The proposed IoMT-driven Alzheimer's prediction model achieved 97.77% accuracy, with a precision of 0.981, recall of 0.987, F1-score of 0.983, and specificity of 99.13%, outperforming several state-of-the-art methods.
  • The study employed the publicly available Kaggle Alzheimer's MRI dataset, comprising 33,984 images across four classes (Non-Demented, Very Mild, Mild, and Moderate Demented).
  • To address class imbalance, a Conditional Wasserstein GAN was applied for synthetic image generation and balanced sampling.
  • The proposed framework ensures interpretability through Grad-CAM, SHAP, and LIME, highlighting clinically relevant brain regions such as the Hippocampus and ventricles.
  • The study integrates IoMT-enabled data acquisition, transfer learning for efficient training, and multi-method XAI for transparency, demonstrating strong potential for early, accurate, and interpretable Alzheimer's staging.

Statistics:

  • 97.77% accuracy achieved by the proposed IoMT-driven Alzheimer's prediction model
  • 0.981 precision, 0.987 recall, 0.983 F1-score, and 99.13% specificity
  • 33,984 images in the Kaggle Alzheimer's MRI dataset
  • 4 classes (Non-Demented, Very Mild, Mild, and Moderate Demented) in the Kaggle Alzheimer's MRI dataset
  • 15% class imbalance in the Kaggle Alzheimer's MRI dataset

Sources:

  • IoMT driven Alzheimer's prediction model empowered with transfer learning and explainable AI approach in healthcare 5.0. Scientific Reports, 2025,15(1):1-21.
  • NewsRx. Research Results from Department of Computer Science Update Knowledge of Alzheimer Disease (IoMT driven Alzheimer's prediction model empowered with transfer learning and explainable AI approach in healthcare 5.0). Health & Medicine Week. October 31, 2025; p 5534.

Read more