Key result
Deep learning techniques applied to EEG data in mental disorders often lack systematic clinical characterization and frequently use misguided model selection or flawed testing procedures.
Why the study?
Tremendous progress has been made with deep learning techniques in medical research, but a systematic review of their application to electroencephalogram data for diagnostic and predictive purposes in mental disorders was needed.
How have deep learning techniques been applied to EEG data for diagnostic and predictive purposes in mental disorders?
Systematic Review
How have deep learning techniques been applied to EEG data for diagnostic and predictive purposes in mental disorders?
This systematic review highlights methodological flaws in current deep learning applications to EEG data in psychiatry, calling for improved clinical data quality and rigorous model testing.
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 been applied to electroencephalogram (EEG) data for diagnostic and predictive purposes in conducting research on mental disorders. EEG-studies on psychiatric diseases based on the ICD-10 or DSM-V classification that used either convolutional neural networks (CNNs) or long -short-term-memory (LSTMs) networks for classification were searched and examined for the quality of the information they contained in three domains: clinical, EEG-data processing, and deep learning. Although we found that the description of EEG acquisition and pre-processing was sufficient in most of the studies, we found, that many of them lacked a systematic characterization of clinical features. Furthermore, many studies used misguided model selection procedures or flawed testing. It is recommended that the study of psychiatric disorders using DL in the future must improve the quality of clinical data and follow state of the art model selection and testing procedures so as to achieve a higher research standard and head toward a clinical significance.
No takes yet. Share an insight, caveat, or question.
Bardeci et al. (2021) conducted a systematic review in Mental disorders. Deep learning techniques (CNNs or LSTMs) applied to EEG data was evaluated on Quality of information in three domains: clinical, EEG-data processing, and deep learning. Deep learning techniques applied to EEG data in mental disorders often lack systematic clinical characterization and frequently use misguided model selection or flawed testing procedures.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: