Our method achieved 90% accuracy in classifying sleep-wake epochs using data from the Apple Watch.
The best performance for sleep-wake classification was obtained using neural networks.
Specificity for true wake epochs was 59.6%, while sensitivity for true sleep epochs was 93%.
Overall accuracy for distinguishing between wake, NREM sleep, and REM sleep was approximately 72% when all features were utilized.
Models trained on Apple Watch data successfully predicted sleep patterns using external data from the Multi-ethnic Study of Atherosclerosis (MESA).
This work provides a novel approach to analyzing raw data from wearable devices to enhance sleep prediction accuracy.
Simplified
Wearable, multisensor, consumer devices that estimate sleep are now commonplace, but the algorithms used by these devices to score sleep are not open source, and the raw sensor data is rarely accessible for external use. As a result, these devices are limited in their usefulness for clinical and research applications, despite holding much promise. We used a mobile application of our own creation to collect raw acceleration data and heart rate from the Apple Watch worn by participants undergoing , as well as during the ambulatory period preceding in lab testing. Using this data, we compared the contributions of multiple features (motion, local standard deviation in heart rate, and "clock proxy") to performance across several classifiers. Best performance was achieved using neural nets, though the differences across classifiers were generally small. For sleep-wake classification, our method scored 90% of epochs correctly, with 59.6% of true wake epochs (specificity) and 93% of true sleep epochs (sensitivity) scored correctly. Accuracy for differentiating wake, NREM sleep, and REM sleep was approximately 72% when all features were used. We generalized our results by testing the models trained on Apple Watch data using data from the Multi-ethnic Study of Atherosclerosis (MESA), and found that we were able to predict sleep with performance comparable to testing on our own dataset. This study demonstrates, for the first time, the ability to analyze raw acceleration and heart rate data from a ubiquitous wearable device with accepted, disclosed mathematical methods to improve accuracy of sleep and sleep stage prediction.
Key numbers
90%
Sleep/Wake Classification Accuracy
Percentage of epochs correctly classified as sleep or wake.
93%
True Sleep Epoch Sensitivity
Fraction of true sleep epochs correctly scored.
72%
REM/NREM Classification Accuracy
Accuracy for classifying wake, NREM, and REM sleep.
Full Text
We can’t show the full text here under this license.
