Key result
XGBoost achieves a leading ~81% accuracy for 5-class sleep stage classification using Dreem headband signals.
Why the study?
The authors sought to develop a model for automatic sleep stage classification using physiological signals acquired by the Dreem Headband and the XGBoost method.
Does an XGBoost model using physiological signals from the Dreem headband accurately classify sleep stages?
Does an XGBoost model using physiological signals from the Dreem headband accurately classify sleep stages?
An XGBoost model using physiological signals from the Dreem headband can accurately classify sleep stages with an accuracy of 81.34%.
Supports wearable sleep staging research; leaves open prospective validation before clinical adoption.
In this paper, we aim to propose a model for automatic sleep stage classification based on physiological signals acquired by Dreem Headband and extreme gradient boosting (XGBoost) method. The dataset used in this study belongs to a challenge competition, namely as “Challenge Data”, held in 2017-2018, and is publicly available on their website. Recordings, includes 4 EEG channels (FpZ-O1, FpZ-O2, FpZ-F7, F8-F7), 2 Pulse oximeter (RED & infra-red), and 3 accelerometer channels (X, Y, Z). In this work, sleep stages have been scored according to the AASM standard. Different features were extracted from the physiological signals after applying a preprocessing step. Each of the elicited features from EEG and PPG signals is falling into one of the three categories: time-domain, frequency domain, or non-linear features. Moreover, ancillary features including body movement, frequency features, breathing frequency, and respiration rate variability were also extracted from the accelerometer signal. Significance of the extracted features was examined through the Kruskal Wallis test, and features with P-value>0.01 were discarded from features set. Finally, significant features were classified by using support vector machine (SVM), K-nearest neighbors (KNN), random forest (RF), and XGBoost classifiers. Due to the class imbalance problem, repeated stratified 5-fold cross-validation was performed in order to tune systems parameters. Results show that among the four above-mentioned models, XGBoost has the best performance for the 5-class classification problem with accuracy: 81.34%±0.76% and Kappa 0.7388±0.0101. The proposed model shows promising results, therefore the model can be implemented in Dreem headband to differentiate between sleep states efficiently and be applicable in clinical trial.
No takes yet. Share an insight, caveat, or question.
Dogaheh et al. (2023) studied Sleep stage classification. XGBoost model using physiological signals from Dreem Headband vs. SVM, KNN, and RF classifiers was evaluated on 5-class sleep stage classification accuracy. The XGBoost model achieved the best performance for 5-class sleep stage classification using Dreem headband signals, with an accuracy of 81.34%±0.76% and Kappa of 0.7388±0.0101.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: