About this Research Topic
Cognitive decline or impairment is common across different mental disorders and neurodegenerative diseases, such as major depressive disorder (MDD), attention deficit hyperactivity disorder (ADHD), and Alzheimer's disease, etc. which are all prevalent and have become one of the leading contributors to the global burden of disease. However, there are currently no reliable biological markers or physiological measurements for accurate diagnosis, or to identify homogeneous subgroups for matching an effective treatment strategy. In this regard, fortunately, an increasing body of evidence has shown that Brain-Computer Interface (BCI) systems have the potential to provide effective and accurate computer-aided diagnosis (CADx) in clinical practice.
Furthermore, considerable evidence shows that BCI can serve as an effective neurofeedback tool to assess the response of pharmacological and/or non-pharmacological interventions. However, although the current BCI achievements are promising, there is still a gap between BCI prototypes and product level. Key factors, such as accuracy, consistency, stability, and replicability, are all related to the reliability and validity of a BCI. Moreover, the practical utility is also crucial to determine whether a BCI can be eventually applied in clinical practice. For instance, high-density electrode montage could limit the usability of clinical BCI in real-world applications. All these critical issues are considered to be challenging in developing BCI systems for diagnostic assistance (i.e., CADx) and/or intervention guidance (i.e., treatment response assessment).
The goal of this Research Topic, therefore, is to encourage researchers to develop novel BCI systems/methods and examine the performance of individuals with cognitive impairment, with a focus on diagnosis, cognitive assessment, intervention, and intervention response assessment. The inputs of a BCI can be EEG or fNIRS and hybrid BCI is also welcome. For instance, BCI integrating EEG, EMG, and eye-tracking information in a virtual environment for the purpose of intervention and cognitive assessment is also appreciated. We encourage authors to take the usability of BCI systems into consideration when maximizing its accuracy, in order to meet the requirement of applicability. We also welcome researches using statistical analysis, advanced machine learning or deep learning methods to deal with the critical issues mentioned above. However, the neuro-signature (feature) used for prediction should be explainable: not just to adjust a network structure or network parameters by taking trial and error when applying a deep learning model.
We welcome empirical BCI studies carried out on real data collected from individuals with cognitive impairment/decline. Subtopics of interest include, but are not limited to:
- CADx methods for detecting a specific disease related to cognitive impairment/decline, or identifying the homogeneous subgroup of the disease
- CADx methods for differentially classifying between diseases.
- BCI-based intervention system which helps improve cognitive ability
- Neurofeedback mechanism for assessing the severity of a disease related to cognitive impairment/decline, or assessing the treatment response.
Keywords: Brain-computer interface (BCI), EEG, fNIRS, Cognitive impairment, Computer-aided diagnosis (CADx), Diagnostic assistance, Intervention, Mental disorder, Neurodegenerative disease
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.