Automatic sleep-stage scoring based on photoplethysmographic signals

Abstract

Objective: Sleep-stage scoring is important for sleep-quality evaluation and the diagnosis of related diseases. In this study, an automatic sleep-stage scoring method using photoplethysmographic (PPG) signals was proposed. Approach: To construct the classification model, we extracted 14 time-domain features, 17 frequency-domain features, and 20 pulse rate variability (PRV) features along with four SpO2 features from PPG signals. An artificial neural network classifier was used to integrate the results of ten binary support vector machine classifiers and realise sleep-stage classification. Leave-one-subject-out validation was applied to evaluate our proposed model. Main results: Thirty-one subjects were enrolled in the study, in which 21 subjects were with high sleep quality (sleep efficiencies ⩾85%). Our model achieved accuracies of 57% (κ = 0.39), 62% (κ = 0.41), and 78% (κ = 0.54) for the classification of five sleep stages (wake, N1, N2, N3, and rapid eye movement (REM) sleeps), four sleep stages (wake, light, deep, and REM sleeps) and three sleep stages (wake, non-rapid eye movement (NREM), and REM sleeps), respectively. For the remaining ten subjects with poor sleep quality, the results came to 55% (κ = 0.39), 62% (κ = 0.43), and 75% (κ = 0.52). Significance: The satisfactory performance of our proposed model reveals the potential of PPG signals for sleep-stage scoring, which may contribute to automatic sleep monitoring in the home environment.

A deep transfer learning approach for wearable sleep stage classification with photoplethysmography

“…For 4-class sleep stage classification, Fonseca et al 19 evaluated a model that was previously trained using HRV features from a large ECG data set on a smaller PPG data set (51 healthy middle-aged adults) and a linear discriminant classifier, reporting a Cohen’s kappa of 0.42 for 4-class sleep stage classification. Wu et al 22 developed a support vector machine algorithm on a small PPG data set (31 healthy subjects), and reported a Cohen’s kappa of 0.41. Beattie et al 20 reported a Cohen’s kappa of 0.52 for a similar healthy demographic by training on a PPG data set and Fujimoto et al 21 achieved an accuracy of 68.8% using a similar method, also with healthy individuals (100).…”

“…For sleep-wake classification, important sleep statistics can be evaluated such as total sleep time (TST), sleep efficiency (SE), sleep onset latency (SOL), and wake-aftersleep-onset (WASO). A few methods were evaluated in earlier work for PPG-based 4-class sleep stage classification using traditional machine learning models [19][20][21][22] . Recently, deep learning methods, specifically long-and short-term memory (LSTM) models, have shown unprecedented agreement levels with PSG [23][24][25] .…”

Automated sleep state classification of wide-field calcium imaging data via multiplex visibility graphs and deep learning

“…Although the MVG-CNN did not perform as well as automated EEG/EMG-based methods ( Barger et al, 2019 ; Yamabe et al, 2019 ), MVG-CNN classification of WFCI data compares favorably with the published gold standard of inter-rater reliability among human expert scorers of EEG/EMG ( Rosenberg et al, 2013 ), and that of two human experts scoring the simultaneously acquired EEG/EMG of this dataset. Additionally, the MVG-CNN method is superior to other automated sleep state classification methods with non-EEG/EMG biosignals ( Korkalainen et al, 2020 ; Wu et al, 2020 ; Gaiduk et al, 2018 ; Sridhar et al, 2020 ). Thus, the hybrid MVG-CNN method is an effective, accurate tool for automatically classifying sleep states in WFCI.…”

“…EEG/EMG-based methods have been successfully developed to automatically classify sleep in rodents ( Barger et al, 2019 ; Yamabe et al, 2019 ). While classification of sleep based on other biosignals such as photoplethysmogram (PPG) ( Korkalainen et al, 2020 ; Wu et al, 2020 ), heart rate and movement ( Gaiduk et al, 2018 ; Sridhar et al, 2020 ) have been proposed, their performance is generally not as good as that based on EEG/EMG. Here, we successfully applied an MVG-CNN model to a new imaging tool, WFCI, to classify sleep states in mice.…”

Automation of classification of sleep stages and estimation of sleep efficiency using actigraphy

“…Photoplethysmography (PPG)-based methods were used in several studies for distinguishing wake, sleep, or REM sleep ( 17 , 18 ). The HRV could be derived from PPG sensors.…”