Bayesian deep neural networks for low-cost neurophysiological markers of Alzheimer's disease severity
This work addresses the need for objective diagnosis and progression assessment of Alzheimer's disease in aging populations, but it is incremental as it applies existing Bayesian methods to a new dataset.
The researchers tackled the lack of low-cost, non-invasive biomarkers for Alzheimer's disease severity by developing a multivariate predictor using Bayesian neural networks on quantitative EEG data, demonstrating its potential in clinical neuroscience with uncertainty bounds.
As societies around the world are ageing, the number of Alzheimer's disease (AD) patients is rapidly increasing. To date, no low-cost, non-invasive biomarkers have been established to advance the objectivization of AD diagnosis and progression assessment. Here, we utilize Bayesian neural networks to develop a multivariate predictor for AD severity using a wide range of quantitative EEG (QEEG) markers. The Bayesian treatment of neural networks both automatically controls model complexity and provides a predictive distribution over the target function, giving uncertainty bounds for our regression task. It is therefore well suited to clinical neuroscience, where data sets are typically sparse and practitioners require a precise assessment of the predictive uncertainty. We use data of one of the largest prospective AD EEG trials ever conducted to demonstrate the potential of Bayesian deep learning in this domain, while comparing two distinct Bayesian neural network approaches, i.e., Monte Carlo dropout and Hamiltonian Monte Carlo.