Predicting Clinical Scores for Alzheimer’s Disease Based on Joint and Deep Learning

Abstract Alzheimer's disease (AD) is a progressive neurodegenerative disease that often grows in middle-aged and elderly people with the gradual loss of cognitive ability. Presently, there is no cure for AD. Furthermore, the current clinical diagnosis of AD is too time-consuming. In this paper, we design a joint and deep learning framework to predict clinical scores of AD. Specifically, the feature selection method combining group LASSO and correntropy is used to reduce dimensions and screen the features of brain regions related to AD. We explore the multi-layer independently recurrent neural network regression to study the internal connection between different brain regions and the time correlation between longitudinal data. The proposed joint deep learning network studies the relationship between the magnetic resonance imaging and clinical score, and predicts the clinical score. The predicted clinical score values allow doctors to perform early diagnosis and timely treatment of patients’ disease condition.