Prediction of Alzheimer's progression based on multimodal Deep-Learning-based fusion and visual Explainability of time-series data

Alzheimer's disease (AD) is a neurological illness that causes cognitive impairment and has no known treatment. The premise for delivering timely therapy is the early diagnosis of AD before clinical symptoms appear. Mild cognitive impairment is an intermediate stage in which cognitively normal patients can be distinguished from those with AD. In this study, we propose a hybrid multimodal deep-learning framework consisting of a 3D convolutional neural network (3D CNN) followed by a bidirectional recurrent neural network (BRNN). The proposed 3D CNN captures intra-slice features from each 3D magnetic resonance imaging (MRI) volume, whereas the BRNN module identifies the inter-sequence patterns that lead to AD. This study is conducted based on longitudinal 3D MRI volumes collected over a six-months time span. We further investigate the effect of fusing MRI with cross-sectional biomarkers, such as patients' demographic and cognitive scores from their baseline visit. In addition, we present a novel explainability approach that helps domain experts and practitioners to understand the end output of the proposed multimodal. Extensive experiments reveal that the accuracy, preci-sion, recall, and area under the receiver operating characteristic curve of the proposed framework are 96%, 99%, 92%, and 96%, respectively. These results are based on the fusion of MRI and demographic features and indicate that the proposed framework becomes more stable when exposed to a more complete set of longitudinal data. Moreover, the explainability module provides extra support for the progression claim by more accurately identifying the brain regions that domain experts commonly report during diagnoses.