Deep learning applied to electroencephalogram data in mental disorders: A systematic review

In recent medical research, tremendous progress has been made in the application of deep learning (DL) techniques. This article systematically reviews how DL techniques have applied to electroencephalogram (EEG) data for diagnostic and predictive purposes conducting research on mental disorders. EEG-studies psychiatric diseases based ICD-10 or DSM-V classification that used either convolutional neural networks (CNNs) long -short-term-memory (LSTMs) were searched examined quality information they contained three domains: clinical, EEG-data processing, learning. Although we found description EEG acquisition pre-processing was sufficient most studies, found, many them lacked a systematic characterization clinical features. Furthermore, studies misguided model selection procedures flawed testing. It is recommended study disorders using future must improve follow state art testing so as achieve higher standard head toward significance.