Electroencephalography (EEG) is at the forefront of non-invasive methodologies for diagnosing and monitoring several neurological disorders, including Parkinson's disease, Alzheimer's disease, epilepsy, autism spectrum disorder, mild cognitive impairment, and schizophrenia. Despite its potential, several critical challenges remain, such as issues related to low signal-to-noise ratios, data heterogeneity across diverse devices and populations, and the limited applicability of artificial intelligence (AI) models generalized for various demographics. These challenges are compounded by the "black-box" nature of advanced algorithms, which undermines clinical trust and complicates biomarker discovery. The field remains divided over the best features, biomarkers, and validation frameworks. Although promising methodologies are emerging, there is still an urgent need to consolidate these advances into reliable and clinically actionable diagnostic tools.

This Research Topic aims to bridge technological advancements and clinical utility in EEG diagnostics. We seek to promote rigorous research that explores explainable AI approaches to bolster clinical trust and improve transparency in biomarker discovery. By rigorously evaluating existing tools and methodologies, this Research Topic strives to refine EEG diagnostics into more actionable, reliable clinical instruments. We endeavor to foster dialogue and development around the technological innovations that aim to overcome current barriers and establish robust frameworks for effective neurological disorder diagnosis using EEG.

In advancing rigorous translational EEG research, we are particularly interested in studies that address specific challenges within constraints and limitations of current EEG diagnostics. By focusing on these areas, we hope to facilitate the creation and deployment of clinically actionable EEG tools that enable early and accurate detection of neurological disorders. To gather further insights into this domain, we welcome articles addressing, but not limited to, the following themes:

• Novel EEG signal processing techniques for neurological disorder detection
• Machine learning and deep learning models for EEG classification and prediction
• Explainable AI (XAI) approaches to improve interpretability and clinical trust
• Identification and validation of EEG-based biomarkers
• Real-time and computationally efficient EEG diagnostic systems
• Multimodal approaches combining EEG with other physiological or imaging data
• Comparative studies, benchmarking, and cross-dataset generalizability
• Clinical applications and translational research in EEG diagnostics
• Challenges in data quality, feature selection, and model robustness
• Reviews or perspectives discussing current trends and future directions

Manuscript types of interest include:

• Original Research Articles
• Review Articles
• Methodological or Technical Reports
• Perspectives and Mini-Reviews

Are you interested in contributing a manuscript to this Research Topic?

Advancing EEG Diagnostics: Navigating Challenges in Detecting Neurological Disorders