An integrative prediction algorithm of drug-refractory epilepsy based on combined clinical-EEG functional connectivity features

Abstract

Objective Although the use of antiepileptic drugs (AEDs) is routine, 30-40% of patients with epilepsy (PWEs) experience drug resistance. Thus, early identification of AED resistance will help optimize treatment regimens and improve patients' prognoses. However, there have been few studies on this topic to date. Here, we try to establish an integrative prediction model of AED resistance for drug-naive PWEs, and to identify the clinical and Electroencephalogram (EEG) factors that affect their outcomes. Methods One hundred sixty-four PWEs naive to AEDs treated at a tertiary care center from January 2014 to June 2020 were retrospectively analyzed. A total of 113 of these patients were well controlled and 53 were drug refractory with regular AED treatment for more than one year. Eighty clinical characteristics and 684 EEG functional connectivity variables based on phase lag index before drug initiation were identified. Overall, 80% of each group was chosen to establish a support vector machine (SVM) model with ten-fold cross validation, and the other 20% were used to evaluate the model's performance. Absolute weight value was used to rank the features that had impacts on classification. Results An integrative algorithm was modeled to predict AED resistance for drug-naive PWEs by SVM based on clinical characteristics and EEG functional connectivity values. The model had an accuracy of 94% [95% confidence interval (CI) 0.85-1.0], sensitivity of 95% [95% CI 0.82-1.0], specificity of 93% [95% CI 0.77-1.0], and an area under the curve (AUC) of 0.98 [95% CI 0.91-1.0]. The p values of accuracy, sensitivity specificity and AUC were calculated as 0.001, 0.001, 0.01 and 0.001, respectively. The δ band fromT4-FZ and T3-PZ, α band from T3-T6 and β band from F7-CZ and FP2-F3 were the top five EEG features that impacted the SVM classifier. ConclusionWe constructed an integrative prediction algorithm of AED resistance for drug-naive PWEs. Its utility in clinical settings should be evaluated in the future.

The performance evaluation of the state-of-the-art EEG-based seizure prediction models

“…Preictal critical slowing down as a feature in the EEG over hours to days is hypothesized to also have predictive value of seizures occurrence (105). In a study on predicting drug responsiveness in epilepsy patients (106), an SVM model constructed by extracting features of brain network connectivity obtained a sensitivity of 94%. The feature of effective connectivity in the frequency domain has constituted the basis for development of novel biomarkers for epileptogenic focus localization from interictal periods (107,108) as well as for evaluation of the risk to status epilepticus (SE) and sudden unexpected death in epilepsy (SUDEP) (109,110).…”

Wireless electroencephalogram monitoring system for deciphering neurological disorders using brain connectivity patterns

“…Connectivity studies in epilepsy reported higher classification score in detection of epilepsy in children (Kinney‐Lang et al, 2019; van Diessen et al, 2013) and in paediatric population (Sargolzaei, Cabrerizo, Sargolzaei, et al, 2015). Based on functional connectivity and clinical characteristics, a integrative model by SVM was developed to predict the antiepileptic drug resistance in drug‐naïve epileptic patients (Wang et al, 2022).…”

EEG-Driven Prediction Model of Oxcarbazepine Treatment Outcomes in Patients With Newly-Diagnosed Focal Epilepsy

“…Electroencephalogram can be used as a biomarker for the treatment of brain diseases such as epilepsy (16). Other studies and our previous work have shown that it is possible to predict ASM response using EEG-based artificial intelligence (17)(18)(19)(20). So, here we test whether the integration of EEG and clinical data can be used to construct a prediction model of OXC treatment outcomes, that can facilitate the correct selection of ASM in newly-diagnosed patients with focal epilepsy patients.…”