Your research can change the world
More on impact ›


Front. Digit. Health | doi: 10.3389/fdgth.2021.665946

A Multi-level Classification Approach for Sleep Stage Prediction with Processed Data Derived from Consumer Wearable Activity Trackers Provisionally accepted The final, formatted version of the article will be published soon. Notify me

 Zilu Liang1, 2* and Mario A. Chapa-Martell3
  • 1Kyoto University of Advanced Science (KUAS), Japan
  • 2The University of Tokyo, Japan
  • 3Silver Egg Technology, Japan

Consumer wearable activity trackers such as Fitbit are widely used in ubiquitous and longitudinal sleep monitoring in free-living environments. However, these devices are known to be inaccurate for measuring sleep stages. In this study, we develop and validate a novel approach that leverages the processed data readily available from consumer activity trackers (i.e., steps, heart rate, and sleep metrics) to predict sleep stages. The proposed approach adopts a selective correction strategy and consists of two levels of classifiers. The level-I classifier judges whether a Fitbit labelled sleep epoch is misclassified, and the level-II classifier re-classifies misclassfied epochs into one of the four sleep stages (i.e., light sleep, deep sleep, REM sleep and wakefulness). Best epoch-wise performance was achieved when support vector machine and gradient boosting decision tree (XGBoost) with up sampling were used respectively at the level-I and level-II classification. The model achieved an overall per-epoch accuracy of 0.731 (SD: 0.119), Cohen's Kappa of 0.433 (SD: 0.212), and multi-class Matthew's correlation coefficient (MMCC) of 0.451 (SD: 0.214). Regarding the total duration of individual sleep stage, the mean normalized absolute bias (MAB) of this model was 0.469, which is a 23.9% reduction against the proprietary Fitbit algorithm. The model that combines support vector machine and XGBoost with down sampling achieved sub-optimal per-epoch accuracy of 0.704 (SD: 0.097), Cohen's Kappa of 0.427 (SD: 0.178), and MMCC of 0.439 (SD: 0.180). The sub-optimal model obtained a MAB of 0.179, a significantly reduction of 71.0% compared to the proprietary Fitbit algorithm. We highlight the challenges in machine learning based sleep stage prediction with consumer wearables, and suggest directions for future research.

Keywords: Sleep tracking, machine learning, consumer sleep technology, wearable sleep trackers, Fitbit, Ambulatory sleep monitoring, Ubiquitous Computing

Received: 09 Feb 2021; Accepted: 19 Apr 2021.

Copyright: © 2021 Liang and Chapa-Martell. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Dr. Zilu Liang, Kyoto University of Advanced Science (KUAS), Kyoto, Japan,