Cross-cohort generalizability of deep and conventional machine learning for MRI-based diagnosis and prediction of Alzheimer's disease.

This work validates the generalizability of MRI-based classification of Alzheimer's disease (AD) patients and controls (CN) to an external data set and to the task of prediction of conversion to AD in individuals with mild cognitive impairment (MCI). We used a conventional support vector machine (SVM) and a deep convolutional neural network (CNN) approach based on structural MRI scans that underwent either minimal pre-processing or more extensive pre-processing into modulated gray matter (GM) maps. Classifiers were optimized and evaluated using cross-validation in the Alzheimer's Disease Neuroimaging Initiative (ADNI; 334 AD, 520 CN).

Frequency Band-Specific Electrical Brain Stimulation Modulates Cognitive Control Processes.

A large body of findings has tied midfrontal theta-band (4-8 Hz) oscillatory activity to adaptive control mechanisms during response conflict. Thus far, this evidence has been correlational. To evaluate whether theta oscillations are causally involved in conflict processing, we applied transcranial alternating current stimulation (tACS) in the theta band to a midfrontal scalp region, while human subjects performed a spatial response conflict task.