Purpose To evaluate the benefits of applying an improved sleep detection and staging algorithm on minimally processed multi-sensor wearable data collected from older generation hardware. Patients and Methods 58 healthy, East Asian adults aged 23–69 years (M = 37.10, SD = 13.03, 32 males), each underwent 3 nights of PSG at home, wearing 2 nd Generation Oura Rings equipped with additional memory to store raw data from accelerometer, infra-red photoplethysmography and temperature sensors. 2-stage and 4-stage sleep classifications using a new machine-learning algorithm (Gen3) trained on a diverse and independent dataset were compared to the existing consumer algorithm (Gen2) for whole-night and epoch-by-epoch metrics. Results Gen 3 outperformed its predecessor with a mean (SD) accuracy of 92.6% (0.04), sensitivity of 94.9% (0.03), and specificity of 78.5% (0.11); corresponding to a 3%, 2.8% and 6.2% improvement from Gen2 across the three nights, with Cohen’s d values >0.39, t values >2.69, and p values <0.01. Notably, Gen 3 showed robust performance comparable to PSG in its assessment of sleep latency, light sleep, rapid eye movement (REM), and wake after sleep onset (WASO) duration. Participants <40 years of age benefited more from the upgrade with less measurement bias for total sleep time (TST), WASO, light sleep and sleep efficiency compared to those ≥40 years. Males showed greater improvements on TST and REM sleep measurement bias compared to females, while females benefitted more for deep sleep measures compared to males. Conclusion These results affirm the benefits of applying machine learning and a diverse training dataset to improve sleep measurement of a consumer wearable device. Importantly, collecting raw data with appropriate hardware allows for future advancements in algorithm development or sleep physiology to be retrospectively applied to enhance the value of longitudinal sleep studies.

The availability of commercial wearable trackers equipped with features to monitor sleep duration and quality has enabled more useful sleep health monitoring applications and analyses. However, much research has reported the challenge of long-term user retention in sleep monitoring through these modalities. Since modern Internet users own multiple mobile devices, our work explores the possibility of employing ubiquitous mobile devices and passive WiFi sensing techniques to predict sleep duration as the fundamental measure for complementing long-term sleep monitoring initiatives. In this paper, we propose SleepMore, an accurate and easy-to-deploy sleep-tracking approach based on machine learning over the user's WiFi network activity. It first employs a semi-personalized random forest model with an infinitesimal jackknife variance estimation method to classify a user's network activity behavior into sleep and awake states per minute granularity. Through a moving average technique, the system uses these state sequences to estimate the user's nocturnal sleep period and its uncertainty rate. Uncertainty quantification enables SleepMore to overcome the impact of noisy WiFi data that can yield large prediction errors. We validate SleepMore using data from a month-long user study involving 46 college students and draw comparisons with the Oura Ring wearable. Beyond the college campus, we evaluate SleepMore on non-student users of different housing profiles. Our results demonstrate that SleepMore produces statistically indistinguishable sleep statistics from the Oura ring baseline for predictions made within a 5% uncertainty rate. These errors range between 15-28 minutes for determining sleep time and 7-29 minutes for determining wake time, proving statistically significant improvements over prior work. Our in-depth analysis explains the sources of errors.

BackgroundThe rapid advancement in wearable solutions to monitor and score sleep staging has enabled monitoring outside of the conventional clinical settings. However, most of the devices and algorithms lack extensive and independent validation, a fundamental step to ensure robustness, stability, and replicability of the results beyond the training and testing phases. These systems are thought not to be feasible and reliable alternatives to the gold standard, polysomnography (PSG).Materials and methodsThis validation study highlights the accuracy and precision of the proposed heart rate (HR)-based deep-learning algorithm for sleep staging. The illustrated solution can perform classification at 2-levels (Wake; Sleep), 3-levels (Wake; NREM; REM) or 4- levels (Wake; Light; Deep; REM) in 30-s epochs. The algorithm was validated using an open-source dataset of PSG recordings (Physionet CinC dataset, n = 994 participants, 994 recordings) and a proprietary dataset of ECG recordings (Z3Pulse, n = 52 participants, 112 recordings) collected with a chest-worn, wireless sensor and simultaneous PSG collection using SOMNOtouch.ResultsWe evaluated the performance of the models in both datasets in terms of Accuracy (A), Cohen’s kappa (K), Sensitivity (SE), Specificity (SP), Positive Predictive Value (PPV), and Negative Predicted Value (NPV). In the CinC dataset, the highest value of accuracy was achieved by the 2-levels model (0.8797), while the 3-levels model obtained the best value of K (0.6025). The 4-levels model obtained the lowest SE (0.3812) and the highest SP (0.9744) for the classification of Deep sleep segments. AHI and biological sex did not affect scoring, while a significant decrease of performance by age was reported across the models. In the Z3Pulse dataset, the highest value of accuracy was achieved by the 2-levels model (0.8812), whereas the 3-levels model obtained the best value of K (0.611). For classification of the sleep states, the lowest SE (0.6163) and the highest SP (0.9606) were obtained for the classification of Deep sleep segment.ConclusionThe results of the validation procedure demonstrated the feasibility of accurate HR-based sleep staging. The combination of the proposed sleep staging algorithm with an inexpensive HR device, provides a cost-effective and non-invasive solution deployable in the home environment and robust across age, sex, and AHI scores.