Nanotechnology-Driven Intelligent Systems for Early Detection of Alzheimer's Disease

Abstract

Alzheimer's Disease (AD) is recognized as a progressive neurodegenerative disorder that affects many individuals and families. Severe symptoms, viz., memory loss, neuronal damage, and cognitive decline, are commonly traceable nowadays. These can be caused by the growth of Amyloid-${\beta}(\mathrm{A} \beta)$ plaques and the tangles of tau protein in the brain. Identifying AD at an early stage has been a significant challenge because of the gradual onset of symptoms and the minimal levels of biomarkers present in biological fluids. Recent advancements in nanotechnology have enabled the effective detection of $A \beta$, tau protein, and other biomarkers through biosensors and imaging systems. Firstly, we performed an extensive literature survey on the usage of different nanomaterials, i.e., gold nanoparticles (AuNPs), quantum dots (QDs), magnetic nanoparticles $(\text{Fe}_{3} \mathrm{O}_{4})$, and graphene-based nanostructures, in pursuit of early and accurate AD detection. Secondly, we have used Magnetic Resonance Imaging (MRI), in which AuNPs are combined with their magnetic substance to provide signal clarity in our proposed structure. Image processing algorithms detect the $\mathrm{A} \beta$ plaque and quantify nanoparticle accumulation. Therefore, AD-affected tissue can be differentiated through pattern recognition. An accuracy level of 97.2% is recorded by our proposed hybrid model (CNN+SVM) using nanotechnology-driven image processing techniques to identify hidden patterns, classify disease stages, and make early predictions with high accuracy.