Alzheimer's disease is the most common cause of dementia that affects millions of lives worldwide. Investigating the underlying causes and risk factors of Alzheimer's disease is essential to prevent its progression. Mild Cognitive Impairment (MCI) is considered an intermediate stage before Alzheimer's disease. Early prediction of the conversion from the MCI to Alzheimer's is crucial to take necessary precautions for decelerating the progression and developing suitable treatments. In this study, we propose a deep learning framework to discover the variables which are identifiers of the conversion from MCI to Alzheimer's disease. In particular, the latent space of a variational auto-encoder network trained with the MCI and Alzheimer's patients is manipulated to obtain the significant attributes and decipher their behavior that leads to the conversion from MCI to Alzheimer's disease. By utilizing a generative decoder and the dimensions that lead to the Alzheimer's diagnosis, we generate synthetic dementia patients from MCI patients in the dataset. Experimental results show promising quantitative and qualitative results on one of the most extensive and commonly used Alzheimer's disease neuroimaging datasets in literature.

Over the past decade a wide spectrum of machine learning models have been developed to model the neurodegenerative diseases, associating biomarkers, especially non-intrusive neuroimaging markers, with key clinical scores measuring the cognitive status of patients. Multi-task learning (MTL) has been commonly utilized by these studies to address high dimensionality and small cohort size challenges. However, most existing MTL approaches are based on linear models and suffer from two major limitations: 1) they cannot explicitly consider upper/lower bounds in these clinical scores; 2) they lack the capability to capture complicated non-linear interactions among the variables. In this paper, we propose Subspace Network, an efficient deep modeling approach for non-linear multi-task censored regression. Each layer of the subspace network performs a multi-task censored regression to improve upon the predictions from the last layer via sketching a low-dimensional subspace to perform knowledge transfer among learning tasks. Under mild assumptions, for each layer the parametric subspace can be recovered using only one pass of training data. Empirical results demonstrate that the proposed subspace network quickly picks up the correct parameter subspaces, and outperforms state-of-the-arts in predicting neurodegenerative clinical scores using information in brain imaging.