We propose an end-to-end deep learning method to detect sleep arousals, especially non-apnea sleep arousals, which is the aim of Physionet/CinC Challenge 2018. We use filtered multi-physiological signals as the input of the network without any other hand-crafted features. The network automatically selects the best features to match arousal targets that we want to identify, and outputs the test result. The proposed network architecture is a 35-layer convolutional neural network (CNN) with three parts: a linear spatial filtering with 1 CNN layer, 33-layer Residual Networks (ResNets), and 1 fully connected layer. For the multi-physiological signals provided in the dataset we choose the 6-channel electroencephalography (EEG) and the 3-channel electroencephalography (EMG) signals, since these signals can better represent the characteristics of nonapnea sleep arousals. In the prediction phase, we use a sliding window method to maximize the performance of sleep arousals detection. For the training set, the result of the area under the precision-recall curve (AUPRC) is 0.3173; the area under the receiver operating characteristic curve (AUROC) is 0.8646. For the final test subset, the result of AUPRC is 0.315; AUROC is 0.858.
The quality of ECG signals is commonly affected by severe noise, especially for the single-lead ECG signals acquired from long-term wearable devices. Recognizing and ignoring these interfered signals can reduce the error rate of automatic ECG analysis system, and in addition, improve the efficiency of cardiologists. Based on XGBoost classifier, we propose an unreadable ECG segment recognition method using features extracted through Shannon Energy Envelope (SEE) and Empirical Mode Decomposition (EMD). An unreadable CarePatchTM ECG patch database is established, containing 8169 readable segments and 6114 unreadable segments with a length of 10 seconds. The XGBoost with 5-fold cross-validation is applied and obtained an accuracy of 99.51+/-0.15%. In conclusion, SSE and EMD features contribute to the unreadable segments recognition and alleviate the misdiagnosis of abnormal rhythms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.