A machine-learning sleep-wake classification model using a reduced number of features derived from photoplethysmography and activity signals

XGBoost sleep–wake classifier from a reduced PPG + activity-count feature set aimed at wearable compute limits. Reported Sensitivity 91.15 ± 1.16%, Specificity 53.66 ± 1.12%, F1 83.88 ± 0.56%, κ 48.0 ± 0.86%. Emphasizes feature thrift for on-device deployment (binary wake/sleep, not full hypnogram).

• Form factor: wrist

Sleep is a crucial aspect of our overall health and well-being. It plays a vital role in regulating our mental and physical health, impacting our mood, memory, and cognitive function to our physical resilience and immune system. The classification of sleep stages is a mandatory step to assess sleep quality, providing the metrics to estimate the quality of sleep and how well our body is functioning during this essential period of rest. Photoplethysmography (PPG) has been demonstrated to be an effective signal for sleep stage inference, meaning it can be used on its own or in a combination with others signals to determine sleep stage. This information is valuable in identifying potential sleep issues and developing strategies to improve sleep quality and overall health. In this work, we present a machine learning sleep-wake classification model based on the eXtreme Gradient Boosting (XGBoost) algorithm and features extracted from PPG signal and activity counts. The performance of our method was comparable to current state-of-the-art methods with a Sensitivity of 91.15 ± 1.16%, Specificity of 53.66 ± 1.12%, F1-score of 83.88 ± 0.56%, and Kappa of 48.0 ± 0.86%. Our method offers a significant improvement over other approaches as it uses a reduced number of features, making it suitable for implementation in wearable devices that have limited computational power.

Verbatim from arXiv (opens in a new tab) · arXiv metadata (abstracts are released under CC0)

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.