On the impact of arousals on the performance of sleep and wake classification using actigraphy

We evaluated the impact of arousals on the performance of actigraphy-based sleep/wake classification. Using a dataset of 15 healthy adults and a threshold optimized for this task we found that the percentage of sleep epochs with activity counts above that threshold was significantly larger in epochs with and following arousals. We also found that 41.1% of all false positive classifications occurred in these epochs. Finally, we determined that excluding these epochs from the evaluation led to a maximum precision increase of 17.2%. Considering wake detections in those epochs as correct led to a maximum precision increase of 31.3%. We concluded that unless arousals can be automatically identified or at least distinguished from wake, the performance of actigraphy-based sleep/wake classifiers is limited by their presence