Recommendations for performance assessment of automatic sleep staging algorithms

A number of automatic sleep scoring algorithms have been published in the last few years. These can potentially help save time and reduce costs in sleep monitoring. However, the use of both R&K and AASM classification, different databases and varying performance metrics makes it extremely difficult to compare these algorithms. In this paper, we describe some readily available polysomnography databases and propose a set of recommendations and performance metrics to promote uniform testing and direct comparison of different algorithms. We use two different polysomnography databases with a simple sleep staging algorithm to demonstrate the usage of all recommendations and presentation of performance results. We also illustrate how seemingly similar results using two different databases can have contrasting accuracies in different sleep stages. Finally, we show how selection of different training and test subjects from the same database can alter the final performance results.