Dataset Information

Automatic scoring of sleep stages and cortical arousals using two electrodes on the forehead: validation in healthy adults.

ABSTRACT: Accuracy and limitations of automatic scoring of sleep stages and electroencephalogram arousals from a single derivation (Fp1 -Fp2 ) were studied in 29 healthy adults using a portable wireless polysomnographic recorder. All recordings were scored five times: twice by a referent scorer who viewed the standard polysomnographic montage and observed the American Academy of Sleep Medicine rules (referent scoring and blind rescoring); and once by the same scorer who viewed only the Fp1 -Fp2 signal (alternative scoring), by another expert from the same institution, and by the algorithm. Automatic, alternative and independent expert scoring were compared with the referent scoring on an epoch-by-epoch basis. The algorithm's agreement with the reference (81.0%, Cohen's ? = 0.75) was comparable to the inter-rater agreement (83.3%, Cohen's ? = 0.78) or agreement between the referent scoring and manual scoring of the frontopolar derivation (80.7%, Cohen's ? = 0.75). Most misclassifications by the algorithm occurred during uneventful wake/sleep transitions, whereas cortical arousals, rapid eye movement and stable non-rapid eye movement sleep were detected accurately. The algorithm yielded accurate estimates of total sleep time, sleep efficiency, sleep latency, arousal indices and times spent in different stages. The findings affirm the utility of automatic scoring of stages and arousals from a single frontopolar derivation as a method for assessment of sleep architecture in healthy adults.

SUBMITTER: Popovic D

PROVIDER: S-EPMC4156826 | biostudies-literature | 2014 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automatic scoring of sleep stages and cortical arousals using two electrodes on the forehead: validation in healthy adults.

Popovic Djordje D Khoo Michael M Westbrook Philip P

Journal of sleep research 20131207 2

Accuracy and limitations of automatic scoring of sleep stages and electroencephalogram arousals from a single derivation (Fp1 -Fp2 ) were studied in 29 healthy adults using a portable wireless polysomnographic recorder. All recordings were scored five times: twice by a referent scorer who viewed the standard polysomnographic montage and observed the American Academy of Sleep Medicine rules (referent scoring and blind rescoring); and once by the same scorer who viewed only the Fp1 -Fp2 signal (al ...[more]

PMID: 24313630

Similar Datasets

Project description:Study objectivesDevelopment of inter-database generalizable sleep staging algorithms represents a challenge due to increased data variability across different datasets. Sharing data between different centers is also a problem due to potential restrictions due to patient privacy protection. In this work, we describe a new deep learning approach for automatic sleep staging, and address its generalization capabilities on a wide range of public sleep staging databases. We also examine the suitability of a novel approach that uses an ensemble of individual local models and evaluate its impact on the resulting inter-database generalization performance.MethodsA general deep learning network architecture for automatic sleep staging is presented. Different preprocessing and architectural variant options are tested. The resulting prediction capabilities are evaluated and compared on a heterogeneous collection of six public sleep staging datasets. Validation is carried out in the context of independent local and external dataset generalization scenarios.ResultsBest results were achieved using the CNN_LSTM_5 neural network variant. Average prediction capabilities on independent local testing sets achieved 0.80 kappa score. When individual local models predict data from external datasets, average kappa score decreases to 0.54. Using the proposed ensemble-based approach, average kappa performance on the external dataset prediction scenario increases to 0.62. To our knowledge this is the largest study by the number of datasets so far on validating the generalization capabilities of an automatic sleep staging algorithm using external databases.ConclusionsValidation results show good general performance of our method, as compared with the expected levels of human agreement, as well as to state-of-the-art automatic sleep staging methods. The proposed ensemble-based approach enables flexible and scalable design, allowing dynamic integration of local models into the final ensemble, preserving data locality, and increasing generalization capabilities of the resulting system at the same time.

Project description:Study Objectives:A negative intrathoracic pressure threshold is one commonly proposed mechanism for triggering respiratory-induced arousals in obstructive sleep apnea (OSA). If so, they should occur during inspiration, shortly after maximal negative pressure swings. Alternatively, respiratory-induced arousals may occur throughout the respiratory cycle if other mechanisms also contribute. However, arousal timing has been minimally investigated. This study aimed to (1) determine the temporal relationship between respiratory-induced arousals and breathing phase and (2) characterize neuromuscular and load compensation responses prior to arousal. Methods:Fifty-one CPAP-treated OSA patients underwent a sleep physiology study with genioglossus and tensor palatini EMG, nasal mask/pneumotachograph, and epiglottic pressure. Transient CPAP reductions were delivered to induce respiratory-related arousals. Results:Of 354 arousals, 65(60-70)%[mean(CI)] occurred during inspiration, 35(30-40)% during expiration. Nadir epiglottic pressure occurred 68(66-69)% into inspiration while inspiratory arousals had a uniform distribution throughout inspiration. Expiratory arousals occurred predominantly in early expiration. CPAP reductions initially reduced minute ventilation by ~2.5 liter/min, which was restored immediately prior to expiratory but not inspiratory arousals. Duty cycle just prior to arousal was greater for inspiratory versus expiratory arousals [0.20(0.18-0.21) vs. 0.13(0.11-0.15)?baseline, p = 0.001]. Peak tensor palatini EMG was higher for expiratory versus inspiratory arousals during prearousal breaths [7.6(5.8-9.6) vs. 3.7(3.0-4.5)%?baseline, p = 0.001], whereas genioglossus and tonic tensor palatini EMG were similar between arousal types. Conclusions:Over one third of respiratory-induced arousals occur during expiration. These findings highlight the importance of nonpressure threshold mechanisms of respiratory-induced arousals in OSA and suggest that expiratory arousals may be a novel marker of enhanced tensor palatini neuromuscular compensation.

Project description:Background:Autonomic arousals can be considered as surrogates of electroencephalography (EEG) arousals when calculating respiratory disturbance index (RDI). The main objective of this proof of concept study was to evaluate the use of heart rate acceleration (HRa) arousals associated with sleep respiratory events in a population undergoing full polysomnography (type 1) and in another undergoing portable monitor study (type 3). Our hypothesis is that when compared to other commonly used indexes, RDI based on HRa will capture more events in both types of recording. Materials and Methods:A retrospective analysis was performed in two different populations of patients with suspected OSA: a) 72 patients undergoing one night of type 1 recording and b) 79 patients undergoing one night of type 3 recording. Variables for type 1 were 4% oxygen desaturation index (ODI), apnea/hypopnea index (AHI), RDI based on EEG arousals (RDIe), and RDI based on HRa with threshold of 5bpm (RDIa5). For type 3, variables were 4% ODI, AHI, and RDIa5 (it is not possible to calculate RDIe due to the absence of EEG). Calculated data were 1) Mean values for each sleep disturbance index in type 1 and 3 recordings; 2) Frequency of migration from lower to higher OSA severity categories using RDIa5 in comparison to AHI (thresholds: ?5/h mild, ?15/h moderate, ?30/h severe); and 3) Bland-Altman plots to assess agreement between AHI vs RDIe and RDIa5 in type 1 population, and AHI vs RDIa5 in type 3 populations. Results:More respiratory disturbance events were captured with RDIa5 index in both type 1 and type 3 recordings when compared to the other indexes. In type 1 recording, when using RDIa5 37% of patients classified as not having OSA with AHI were now identified as having OSA, and a total of 59% migrated to higher severity categories. In type 3 recording, similar results were obtained, as 37% of patients classified as not having OSA with AHI were now identified as having OSA using RDIa5, and a total of 55% patients migrated to higher severity categories. Mean differences for RDIa5 and AHI in type 1 and 3 populations were similar. Conclusion:The use of autonomic arousals such as HRa can help to detect more respiratory disturbance events when compared to other indexes, being a variable that may help to capture borderline mild cases. This becomes especially relevant in type 3 recordings. Future research is needed to determine its validity, optimization, and its clinical significance.

Dataset Information

Automatic scoring of sleep stages and cortical arousals using two electrodes on the forehead: validation in healthy adults.

Publications

Automatic scoring of sleep stages and cortical arousals using two electrodes on the forehead: validation in healthy adults.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets