Using hidden Markov models with raw, triaxial wrist accelerometry data to determine sleep stages

Abstract

Accelerometry is a low-cost and noninvasive method that has been used to discriminate sleep from wake, however, its utility to detect sleep stages is unclear. We detail the development and comparison of methods which utilise raw, triaxial accelerometry data to classify varying stages of sleep, ranging from sleep/wake detection to discriminating rapid eye movement sleep, stage one sleep, stage two sleep, deep sleep and wake. First-and second-order hidden Markov models (HMMs) with time-homogeneous and time-varying transition probability matrices, along with continuous acceleration observations in the form of a Gaussianobservation HMM and K-means classified acceleration in a discrete-observation HMM were explored. In addition, generalised linear mixed models (GLMMs) with binary and multinomial responses and logit link functions were considered as was whether incorporating adjoining acceleration information into the models improved prediction. Model predictions were compared to the reference-standard in sleep detection (polysomnography) and outcome accuracies were calculated. Consistently, HMMs yielded greater sleep stage detection than GLMMs but there was little difference between first-and second-order HMMs. Varying degrees of difference were observed when comparing Gaussian-observation HMMs to discrete-observation HMMs, and time-varying HMMs yielded greater discrimination than time-homogeneous HMMs, as did models which considered adjoining acceleration information. These results suggest that wrist-worn accelerometry data may be able to detect sleep stages but that further investigation is required to optimise classification accuracy.

Sleep classification from wrist-worn accelerometer data using random forests

“…Based on an exploratory analysis of our data, we observed that transition between sleep states is rare compared to remaining in the same state for prolonged periods of time. Hence, when using approaches like Hidden Markov Models (HMM) as in Trevenen et al 13 , the transition probability matrix is heavily diagonal and HMMs do not provide any advantage under such scenarios. Therefore, we trained discriminative models for every time interval based on engineered features.…”

“…Level Our sleep classification approach is most similar to that of Trevenen et al 13 . Based on an exploratory analysis of our data, we observed that transition between sleep states is rare compared to remaining in the same state for prolonged periods of time.…”

“…More recently Trevenen et al used machine learning to perform sleep classification. They extracted a variety of features from the acceleration vector magnitude and used these as input for a Hidden Markov Model (HMM) to classify sleep versus wakefulness, as well as to discriminate all four sleep stages 13 . The novel attempt to classify sleep stages from accelerometer-only data resulted in poor classification performance and was not able to accurately detect REM nor discriminate between Non-REM stages.…”

Recent Progress in Long-Term Sleep Monitoring Technology

“…Although there are multiple joints between the wrist and torso in sleep staging and the human body, restoring the overall body posture with the wrist is difficult. In 2019, Trevenen et al attempted to improve the accuracy of recognition with machine-learning algorithms [ 135 ]. In the same year, Walch et al also attempted to analyze raw acceleration data from Apple Watch to analyze sleep, but the specificity was not satisfactory [ 136 ].…”

Multi-Scale Evaluation of Sleep Quality Based on Motion Signal from Unobtrusive Device

“…Computational methods used to extract valuable information for screening purposes are mainly based on signal processing and Artificial Intelligence (AI). Common features extracted are averages, ranges, angles, skewness, kurtosis and Wavelet coefficients [ 32 , 33 ], whereas classifiers used are K-Nearest Neighbor (KNN) [ 34 ], Decision Tree, Random Forest, Support Vector Machine [ 10 , 24 , 34 , 35 , 36 ] and Hidden Markov Models (HMMs) [ 37 ].…”