Exploring Neurodegenerative Progression: Healthcare 6.0 Insights Using Sustainable Convolutional Neural Networks

The research intricately navigates the complex landscape of cognitive disorders, with a primary objective to forecast the progression of Alzheimer’s disease (AD) and dementia. Employing advanced methodologies, the study is dedicated to unravelling intricate patterns embedded in neuroimaging data, with a strong commitment to refining the precision and reliability of prognostication models through the utilization of digital twins. The methodology places strategic emphasis on the adept utilization of sophisticated techniques in both deep feature extraction and model tuning, leveraging insights from digital twins. The holistic approach adopted encompasses not only predicting but also comprehending cognitive disorders, with digital twins providing valuable reference points for understanding individual variations. The synthesis of cutting-edge methodologies, data analytics, and optimization techniques, augmented by insights from digital twins, positions this study as a noteworthy contribution to the broader field of neurodegenerative disease research. In the face of challenges posed by AD and dementia, our work seeks to offer valuable insights, potentially paving the way for improved diagnostic tools and therapeutic strategies in the future. The proposed research focuses on the convolutional neural network model over the Open-Access Series of Imaging Studies (OASIS) dataset and the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, with digital twins aiding in refining model performance and interpretation. The model yields an average accuracy of 95.70% over the OASIS dataset and 94.2% over the ADNI dataset, showcasing the effectiveness of integrating digital twins into neurodegenerative disease research.