Multimodal deep learning for Alzheimer’s disease dementia assessment

Abstract

Worldwide, there are nearly 10 million new cases of dementia annually, of which Alzheimer’s disease (AD) is the most common. New measures are needed to improve the diagnosis of individuals with cognitive impairment due to various etiologies. Here, we report a deep learning framework that accomplishes multiple diagnostic steps in successive fashion to identify persons with normal cognition (NC), mild cognitive impairment (MCI), AD, and non-AD dementias (nADD). We demonstrate a range of models capable of accepting flexible combinations of routinely collected clinical information, including demographics, medical history, neuropsychological testing, neuroimaging, and functional assessments. We then show that these frameworks compare favorably with the diagnostic accuracy of practicing neurologists and neuroradiologists. Lastly, we apply interpretability methods in computer vision to show that disease-specific patterns detected by our models track distinct patterns of degenerative changes throughout the brain and correspond closely with the presence of neuropathological lesions on autopsy. Our work demonstrates methodologies for validating computational predictions with established standards of medical diagnosis.

Graph-generative neural network for EEG-based epileptic seizure detection via discovery of dynamic brain functional connectivity

“…EEG analysis of AD is usually based on some statistical signal processing methods, such as phase leg index and minimum spanning trees. These methods assumed that the EEG signals could distinguish from other dementia diseases in several frequency bands and specific lobe areas 63 . The functional connectivity of AD patients shows the presence of the small-world network features by graph theory 56 .…”

Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases

“…Machine-assisted diagnosis offers the opportunity to shorten diagnostic delays for rare disease patients. Advances in artificial intelligence (AI) and deep learning have considerably improved diagnostic accuracy [6][7][8][9][10][11][12][13][14][15]. Deep learning models that have been trained (via supervised learning) on labeled datasets can achieve near-expert clinical accuracy for common diseases, including diabetic retinopathy [16], skin cancers [17], and pediatric diseases [18].…”

A Review of the Recent Advances in Alzheimer’s Disease Research and the Utilization of Network Biology Approaches for Prioritizing Diagnostics and Therapeutics

“…Many research efforts focused on utilizing ML and AI approaches to mine data from records to evaluate anti-AD therapeutics in different stages of clinical development to study their mechanisms of action and important clinical trial characteristics [ 10 , 372 , 378 , 379 , 380 , 381 , 382 ]. AI and ML approaches can lead to important discoveries by learning from the recent advances in clinical trials and anti-Alzheimer’s drug development pipelines [ 383 , 384 , 385 , 386 , 387 , 388 ].…”