OBJECTIVE: The goal of this work is to objectively evaluate the effectiveness of responsive (or closed-loop) Vagus nerve stimulation (VNS) therapy in sleep quality in patients with medically refractory epilepsy. METHODS: Using quantitative features obtained from electroencephalography, we first developed a new automatic sleep-staging framework that consists of a multi-class support vector machine (SVM) classification, based on a decision tree approach. To train and evaluate the performance of the framework, we used polysomnographic data of 23 healthy subjects from the PhysioBank database where the sleep stages have been visually annotated. We then used the trained classifier to label the sleep stages using data from 22 patients with epilepsy, treated with short term responsive VNS therapy during an epilepsy-monitoring unit visit, one month after VNS implantation, and ten VNS-naïve patients with epilepsy. RESULTS: Application of multi-class SVM classifier to classify the three sleep stages of awake, light sleep + rapid eye movement, and deep sleep achieved a classification accuracy of 90%. Results of the application of this methodology to VNS-treated and VNS-naïve patients revealed that the patients treated with short term responsive VNS therapy showed significant increase in sleep efficiency, and significant decrease in seizures plus interictal epileptiform discharges and awakenings. CONCLUSION: These results indicate that VNS treatment can reduce the epileptiform activities and thus help in achieving better sleep quality for patients with epilepsy. SIGNIFICANCE: The proposed approach can be used to investigate the effect of long-term VNS therapy on sleep quality.
OBJECTIVE: The goal of this work is to objectively evaluate the effectiveness of responsive (or closed-loop) Vagus nerve stimulation (VNS) therapy in sleep quality in patients with medically refractory epilepsy. METHODS: Using quantitative features obtained from electroencephalography, we first developed a new automatic sleep-staging framework that consists of a multi-class support vector machine (SVM) classification, based on a decision tree approach. To train and evaluate the performance of the framework, we used polysomnographic data of 23 healthy subjects from the PhysioBank database where the sleep stages have been visually annotated. We then used the trained classifier to label the sleep stages using data from 22 patients with epilepsy, treated with short term responsive VNS therapy during an epilepsy-monitoring unit visit, one month after VNS implantation, and ten VNS-naïve patients with epilepsy. RESULTS: Application of multi-class SVM classifier to classify the three sleep stages of awake, light sleep + rapid eye movement, and deep sleep achieved a classification accuracy of 90%. Results of the application of this methodology to VNS-treated and VNS-naïve patients revealed that the patients treated with short term responsive VNS therapy showed significant increase in sleep efficiency, and significant decrease in seizures plus interictal epileptiform discharges and awakenings. CONCLUSION: These results indicate that VNS treatment can reduce the epileptiform activities and thus help in achieving better sleep quality for patients with epilepsy. SIGNIFICANCE: The proposed approach can be used to investigate the effect of long-term VNS therapy on sleep quality.
Authors: Fábio Mendonça; Sheikh Shanawaz Mostafa; Diogo Freitas; Fernando Morgado-Dias; Antonio G Ravelo-García Journal: Int J Environ Res Public Health Date: 2022-09-01 Impact factor: 4.614