Joint Classification and Prediction CNN Framework for Automatic Sleep Stage Classification
share
Sleep staging plays an important role in assessment and treatment of sleep issues. This work proposes a joint classification-and-prediction framework based on convolutional neural networks (CNNs) for automatic sleep staging, and, subsequently, introduces a simple yet efficient CNN architecture to power the framework. Given a single input epoch, the framework jointly determines its label (classification) and those of its neighboring epochs in the contextual output (prediction). While the proposed framework is orthogonal to the widely adopted classification schemes, which takes one or multiple epochs as a contextual input and produces a single classification decision on the target epoch, we demonstrate its advantages in different ways. First, it leverages the dependency among consecutive sleep epochs while surpassing the problems experienced with the common classification schemes. Second, even with a single model, the framework effortlessly produces multiple decisions as in ensemble-of-models methods which are essential in obtaining a good performance. Probabilistic aggregation techniques are then proposed to leverage the availability of multiple decisions. We demonstrate good performance on the Montreal Archive of Sleep Studies (MASS) dataset consisting 200 subjects with an average accuracy of 83.6 is superior to the baselines based on the common classification schemes but also outperforms existing deep-learning approaches. To our knowledge, this is the first work going beyond the standard single-output classification to consider neural networks with multiple outputs for automatic sleep staging. This framework could provide avenues for further studies of different neural-network architectures for this problem.
READ FULL TEXT