Primitive Identification of Alzheimer's Disease Using Machine Learning: A Generalized Approach With Deep CNN-LSTM Network

Our society's longer lifetime is a double-edged sword that results in a rise in people with neurocognitive disorders, with Alzheimer's disease being the most common. New techniques for the early diagnosis of neurocognitive diseases with the aim of avoiding or minimizing cognitive decline are made possible by advancements in medical imaging and computer capability. For patients with moderate cognitive impairment, which is occasionally a symptomatic stage of Alzheimer's disease dementia, computer-aided picture analysis and early identification of changes in cognition is a potential strategy. Deep learning can be applied to neuroimaging data in order to predict whether patients with mild cognitive impairment might develop Alzheimer's disease dementia or remain stable. The datasets which is mainly used for such studies are the OASIS database with some exceptions. We will consider this database to generate results for gaining prediction accuracy which can be compared with other state of art algorithms to prove our point.