DeepAD: A Robust Deep Learning Model of Alzheimer's Disease Progression for Real-World Clinical Applications
This work addresses the challenge of generalizing disease progression predictions across different clinical cohorts for Alzheimer's disease, which is incremental as it builds on existing multimodal and multi-task approaches.
The authors tackled the problem of predicting Alzheimer's disease progression by developing a multimodal multi-task deep learning model that integrates clinical, demographic, and neuroimaging data from multiple cohorts, resulting in significant improvements over baseline models and showing that 3D CNN features outperform MRI-derived volumetric features.
The ability to predict the future trajectory of a patient is a key step toward the development of therapeutics for complex diseases such as Alzheimer's disease (AD). However, most machine learning approaches developed for prediction of disease progression are either single-task or single-modality models, which can not be directly adopted to our setting involving multi-task learning with high dimensional images. Moreover, most of those approaches are trained on a single dataset (i.e. cohort), which can not be generalized to other cohorts. We propose a novel multimodal multi-task deep learning model to predict AD progression by analyzing longitudinal clinical and neuroimaging data from multiple cohorts. Our proposed model integrates high dimensional MRI features from a 3D convolutional neural network with other data modalities, including clinical and demographic information, to predict the future trajectory of patients. Our model employs an adversarial loss to alleviate the study-specific imaging bias, in particular the inter-study domain shifts. In addition, a Sharpness-Aware Minimization (SAM) optimization technique is applied to further improve model generalization. The proposed model is trained and tested on various datasets in order to evaluate and validate the results. Our results showed that 1) our model yields significant improvement over the baseline models, and 2) models using extracted neuroimaging features from 3D convolutional neural network outperform the same models when applied to MRI-derived volumetric features.