Fusing Imaging and Spatial-Temporal Complexity Measures for Early Alzheimer's Detection and Neuromodulation

As populations age, Alzheimer's disease (AD) is set to become a major global health challenge, with its early stages often remaining unnoticed, leading to missed opportunities for timely diagnosis and intervention. To address this issue, this project will develop a predictive framework by integrating multimodal brain imaging with spatial-temporal complexity analysis of brain activity. The project will extract and fuse structural imaging data, complexity metrics, and time-series dynamics, employing advanced statistical modeling techniques to generate personalized brain health profiles. These analyses will help identify early biomarkers of cognitive decline, particularly in subclinical populations such as those with subjective memory complaints (SMC), providing critical insights for early AD risk detection. Additionally, the project will investigate the relationship between these biomarkers and AD progression, and develop neuromodulation strategies targeting key brain network parameters through sensitivity analysis. These strategies will be experimentally verified and ultimately result in the development of a clinical toolbox for early AD detection and neuromodulation-based intervention. This project not only aims to achieve significant breakthroughs in early detection but also proposes innovative solutions for targeted intervention, with the potential to slow or even prevent AD progression, offering vital support in addressing this growing global health issue.