Identifying Alzheimer’s Dementia Patients Using MRI Clinical Data

Alzheimer's disease is a debilitating and progressive neurological disorder that is characterized by a range of symptoms, including memory loss, difficulties with thinking, language, and perception, and a loss of the ability to perform simple daily tasks. Although the exact cause of Alzheimer's disease is unknown, a number of factors are believed to contribute to its development, including the accumulation of amyloid proteins and neurofibrillary tangles in the brain, genetic predisposition, age-related changes in the brain, and lifestyle factors. [1] Given the lack of a cure for Alzheimer's, a model has been proposed to decrease the number of pa-tients with dementia. This model utilizes three blocks of convolutional neural network (CNN) layers, each containing different filter sizes, to improve the accuracy of the model in identifying images based on visual cues. This approach resulted in high loss and validation accuracy, and the model achieved an impressive 98.64% accuracy in training classification and 96% accuracy in testing. When compared with other models, including VGG16, VGG19, and InceptionResNet V2, the proposed model performed better with a higher accuracy rate. InceptionResNet V2 was the closest competitor with an accuracy of 86%, while VGG16 and VGG19 performed similarly, achieving accuracies of 74% and 76% respectively. The accuracy rates suggest that the proposed model is a promising approach to decreasing the number of patients with Alzheimer's disease.