AUTHOR=Ren Zhe , Zhao Yibo , Han Xiong , Yue Mengyan , Wang Bin , Zhao Zongya , Wen Bin , Hong Yang , Wang Qi , Hong Yingxing , Zhao Ting , Wang Na , Zhao Pan 

TITLE=An objective model for diagnosing comorbid cognitive impairment in patients with epilepsy based on the clinical-EEG functional connectivity features

JOURNAL=Frontiers in Neuroscience

VOLUME=16

YEAR=2023

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2022.1060814

DOI=10.3389/fnins.2022.1060814

ISSN=1662-453X

ABSTRACT=<sec><title>Objective</title><p>Cognitive impairment (CI) is a common disorder in patients with epilepsy (PWEs). Objective assessment method for diagnosing CI in PWEs would be beneficial in reality. This study proposed to construct a diagnostic model for CI in PWEs using the clinical and the phase locking value (PLV) functional connectivity features of the electroencephalogram (EEG).</p></sec><sec><title>Methods</title><p>PWEs who met the inclusion and exclusion criteria were divided into a cognitively normal (CON) group (<italic>n</italic> = 55) and a CI group (<italic>n</italic> = 76). The 23 clinical features and 684 PLV<italic><sub><italic>EEG</italic></sub></italic> features at the time of patient visit were screened and ranked using the Fisher score. Adaptive Boosting (AdaBoost) and Gradient Boosting Decision Tree (GBDT) were used as algorithms to construct diagnostic models of CI in PWEs either with pure clinical features, pure PLV<italic><sub><italic>EEG</italic></sub></italic> features, or combined clinical and PLV<italic><sub><italic>EEG</italic></sub></italic> features. The performance of these models was assessed using a five-fold cross-validation method.</p></sec><sec><title>Results</title><p>GBDT-built model with combined clinical and PLV<italic><sub><italic>EEG</italic></sub></italic> features performed the best with accuracy, precision, recall, F1-score, and an area under the curve (AUC) of 90.11, 93.40, 89.50, 91.39, and 0.95%. The top 5 features found to influence the model performance based on the Fisher scores were the magnetic resonance imaging (MRI) findings of the head for abnormalities, educational attainment, PLV<italic><sub><italic>EEG</italic></sub></italic> in the beta (β)-band C3-F4, seizure frequency, and PLV<italic><sub><italic>EEG</italic></sub></italic> in theta (θ)-band Fp1-Fz. A total of 12 of the top 5% of features exhibited statistically different PLV<italic><sub><italic>EEG</italic></sub></italic> features, while eight of which were PLV<italic><sub><italic>EEG</italic></sub></italic> features in the θ band.</p></sec><sec><title>Conclusion</title><p>The model constructed from the combined clinical and PLV<italic><sub><italic>EEG</italic></sub></italic> features could effectively identify CI in PWEs and possess the potential as a useful objective evaluation method. The PLV<italic><sub><italic>EEG</italic></sub></italic> in the θ band could be a potential biomarker for the complementary diagnosis of CI comorbid with epilepsy.</p></sec>