Dataset Information

Automatic Sleep Stage Classification Based on Subthalamic Local Field Potentials.

ABSTRACT: Deep brain stimulation (DBS) is an established treatment for patients with Parkinson's disease (PD). Sleep disorders are common complications of PD and affected by subthalamic DBS treatment. To achieve more precise neuromodulation, chronicsleepmonitoringand closed-loop DBS toward sleep-wake cycles could potentially be utilized. Local field potential (LFP) signals that are sensed by the DBS electrode could be processed as primary feedback signals. This is the first study to systematically investigate the sleep-stage classification based on LFPs in subthalamic nucleus (STN). With our newly developed recording and transmission system, STN-LFPs were collected from 12 PD patients during wakefulness and nocturnal polysomnography sleep monitoring at one month after DBS implantation. Automatic sleep-stage classificationmodels were built with robust and interpretable machine learning methods (support vector machine and decision tree). The accuracy, sensitivity, selectivity, and specificity of the classification reached high values (above90% at most measures) at group and individual levels. Features extracted in alpha (8-13 Hz), beta (13-35 Hz), and gamma (35-50 Hz) bandswere found to contribute the most to the classification. These results will directly guide the engineering development of implantable sleepmonitoring and closed-loopDBS and pave the way for a better understanding of the STN-LFP sleep patterns.

SUBMITTER: Chen Y

PROVIDER: S-EPMC6544463 | biostudies-literature | 2019 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automatic Sleep Stage Classification Based on Subthalamic Local Field Potentials.

Chen Yue Y Gong Chen C Hao Hongwei H Guo Yi Y Xu Shujun S Zhang Yuhuan Y Yin Guoping G Cao Xin X Yang Anchao A Meng Fangang F Ye Jingying J Liu Hesheng H Zhang Jianguo J Sui Yanan Y Li Luming L

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society 20190101 2

Deep brain stimulation (DBS) is an established treatment for patients with Parkinson's disease (PD). Sleep disorders are common complications of PD and affected by subthalamic DBS treatment. To achieve more precise neuromodulation, chronicsleepmonitoringand closed-loop DBS toward sleep-wake cycles could potentially be utilized. Local field potential (LFP) signals that are sensed by the DBS electrode could be processed as primary feedback signals. This is the first study to systematically investi ...[more]

PMID: 30605104

Similar Datasets

Project description:BACKGROUND:The interplay between sleep structure and seizure probability has previously been studied using electroencephalography (EEG). Combining sleep assessment and detection of epileptic activity in ultralong-term EEG could potentially optimize seizure treatment and sleep quality of patients with epilepsy. However, the current gold standard polysomnography (PSG) limits sleep recording to a few nights. A novel subcutaneous device was developed to record ultralong-term EEG, and has been shown to measure events of clinical relevance for patients with epilepsy. We investigated whether subcutaneous EEG recordings can also be used to automatically assess the sleep architecture of epilepsy patients. METHOD:Four adult inpatients with probable or definite temporal lobe epilepsy were monitored simultaneously with long-term video scalp EEG (LTV EEG) and subcutaneous EEG. In total, 11 nights with concurrent recordings were obtained. The sleep EEG in the two modalities was scored independently by a trained expert according to the American Academy of Sleep Medicine (AASM) rules. By using the sleep stage labels from the LTV EEG as ground truth, an automatic sleep stage classifier based on 30 descriptive features computed from the subcutaneous EEG was trained and tested. RESULTS:An average Cohen's kappa of [Formula: see text] was achieved using patient specific leave-one-night-out cross validation. When merging all sleep stages into a single class and thereby evaluating an awake-sleep classifier, we achieved a sensitivity of 94.8% and a specificity of 96.6%. Compared to manually labeled video-EEG, the model underestimated total sleep time and sleep efficiency by 8.6 and 1.8 min, respectively, and overestimated wakefulness after sleep onset by 13.6 min. CONCLUSION:This proof-of-concept study shows that it is possible to automatically sleep score patients with epilepsy based on two-channel subcutaneous EEG. The results are comparable with the methods currently used in clinical practice. In contrast to comparable studies with wearable EEG devices, several nights were recorded per patient, allowing for the training of patient specific algorithms that can account for the individual brain dynamics of each patient. Clinical trial registered at ClinicalTrial.gov on 19 October 2016 (ID:NCT02946151).

Project description:Segmented deep brain stimulation leads feature directional electrodes that allow for a finer spatial control of electrical stimulation compared to traditional ring-shaped electrodes. These segmented leads have demonstrated enlarged therapeutic windows and have thus the potential to improve the treatment of Parkinson's disease patients. Moreover, they provide a unique opportunity to record directional local field potentials. Here, we investigated whether directional local field potentials can help identify the best stimulation direction to assist device programming. Four Parkinson's disease patients underwent routine implantation of the subthalamic nucleus. Firstly, local field potentials were recorded in three directions for two conditions: In one condition, the patient was at rest; in the other condition, the patient's arm was moved. Secondly, current thresholds for therapeutic and side effects were identified intraoperatively for directional stimulation. Therapeutic windows were calculated from these two thresholds. Thirdly, the spectral power of the total beta band (13-35 Hz) and its sub-bands low, high, and peak beta were analyzed post hoc. Fourthly, the spectral power was used by different algorithms to predict the ranking of directions. The spectral power profiles were patient-specific, and spectral peaks were found both in the low beta band (13-20 Hz) and in the high beta band (20.5-35 Hz). The direction with the highest spectral power in the total beta band was most indicative of the 1st best direction when defined by therapeutic window. Based on the total beta band, the resting condition and the moving condition were similarly predictive about the direction ranking and classified 83.3% of directions correctly. However, different algorithms were needed to predict the ranking defined by therapeutic window or therapeutic current threshold. Directional local field potentials may help predict the best stimulation direction. Further studies with larger sample sizes are needed to better distinguish the informative value of different conditions and the beta sub-bands.

Dataset Information

Automatic Sleep Stage Classification Based on Subthalamic Local Field Potentials.

Publications

Automatic Sleep Stage Classification Based on Subthalamic Local Field Potentials.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets