Dataset Information

Expert-level automated sleep staging of long-term scalp electroencephalography recordings using deep learning.

ABSTRACT:

Study objectives

Develop a high-performing, automated sleep scoring algorithm that can be applied to long-term scalp electroencephalography (EEG) recordings.

Methods

Using a clinical dataset of polysomnograms from 6,431 patients (MGH-PSG dataset), we trained a deep neural network to classify sleep stages based on scalp EEG data. The algorithm consists of a convolutional neural network for feature extraction, followed by a recurrent neural network that extracts temporal dependencies of sleep stages. The algorithm's inputs are four scalp EEG bipolar channels (F3-C3, C3-O1, F4-C4, and C4-O2), which can be derived from any standard PSG or scalp EEG recording. We initially trained the algorithm on the MGH-PSG dataset and used transfer learning to fine-tune it on a dataset of long-term (24-72 h) scalp EEG recordings from 112 patients (scalpEEG dataset).

Results

The algorithm achieved a Cohen's kappa of 0.74 on the MGH-PSG holdout testing set and cross-validated Cohen's kappa of 0.78 after optimization on the scalpEEG dataset. The algorithm also performed well on two publicly available PSG datasets, demonstrating high generalizability. Performance on all datasets was comparable to the inter-rater agreement of human sleep staging experts (Cohen's kappa ~ 0.75 ± 0.11). The algorithm's performance on long-term scalp EEGs was robust over a wide age range and across common EEG background abnormalities.

Conclusion

We developed a deep learning algorithm that achieves human expert level sleep staging performance on long-term scalp EEG recordings. This algorithm, which we have made publicly available, greatly facilitates the use of large long-term EEG clinical datasets for sleep-related research.

SUBMITTER: Abou Jaoude M

PROVIDER: S-EPMC7686563 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Introduction: Automated sleep staging using deep learning models typically requires training on hundreds of sleep recordings, and pre-training on public databases is therefore common practice. However, suboptimal sleep stage performance may occur from mismatches between source and target datasets, such as differences in population characteristics (e.g., an unrepresented sleep disorder) or sensors (e.g., alternative channel locations for wearable EEG). Methods: We investigated three strategies for training an automated single-channel EEG sleep stager: pre-training (i.e., training on the original source dataset), training-from-scratch (i.e., training on the new target dataset), and fine-tuning (i.e., training on the original source dataset, fine-tuning on the new target dataset). As source dataset, we used the F3-M2 channel of healthy subjects (N = 94). Performance of the different training strategies was evaluated using Cohen's Kappa (κ) in eight smaller target datasets consisting of healthy subjects (N = 60), patients with obstructive sleep apnea (OSA, N = 60), insomnia (N = 60), and REM sleep behavioral disorder (RBD, N = 22), combined with two EEG channels, F3-M2 and F3-F4. Results: No differences in performance between the training strategies was observed in the age-matched F3-M2 datasets, with an average performance across strategies of κ = .83 in healthy, κ = .77 in insomnia, and κ = .74 in OSA subjects. However, in the RBD set, where data availability was limited, fine-tuning was the preferred method (κ = .67), with an average increase in κ of .15 to pre-training and training-from-scratch. In the presence of channel mismatches, targeted training is required, either through training-from-scratch or fine-tuning, increasing performance with κ = .17 on average. Discussion: We found that, when channel and/or population mismatches cause suboptimal sleep staging performance, a fine-tuning approach can yield similar to superior performance compared to building a model from scratch, while requiring a smaller sample size. In contrast to insomnia and OSA, RBD data contains characteristics, either inherent to the pathology or age-related, which apparently demand targeted training.

Project description:BackgroundThe advent of home sleep testing has allowed for the development of an ambulatory care model for OSA that most health-care providers can easily deploy. Although automated algorithms that accompany home sleep monitors can identify and classify disordered breathing events, it is unclear whether manual scoring followed by expert review of home sleep recordings is of any value. Thus, this study examined the agreement between automated and manual scoring of home sleep recordings.MethodsTwo type 3 monitors (ApneaLink Plus [ResMed] and Embletta [Embla Systems]) were examined in distinct study samples. Data from manual and automated scoring were available for 200 subjects. Two thresholds for oxygen desaturation (≥ 3% and ≥ 4%) were used to define disordered breathing events. Agreement between manual and automated scoring was examined using Pearson correlation coefficients and Bland-Altman analyses.ResultsAutomated scoring consistently underscored disordered breathing events compared with manual scoring for both sleep monitors irrespective of whether a ≥ 3% or ≥ 4% oxygen desaturation threshold was used to define the apnea-hypopnea index (AHI). For the ApneaLink Plus monitor, Bland-Altman analyses revealed an average AHI difference between manual and automated scoring of 6.1 (95% CI, 4.9-7.3) and 4.6 (95% CI, 3.5-5.6) events/h for the ≥ 3% and ≥ 4% oxygen desaturation thresholds, respectively. Similarly for the Embletta monitor, the average difference between manual and automated scoring was 5.3 (95% CI, 3.2-7.3) and 8.4 (95% CI, 7.2-9.6) events/h, respectively.ConclusionsAlthough agreement between automated and manual scoring of home sleep recordings varies based on the device used, modest agreement was observed between the two approaches. However, manual review of home sleep test recordings can decrease the misclassification of OSA severity, particularly for those with mild disease.Trial registryClinicalTrials.gov; No.: NCT01503164; www.clinicaltrials.gov.