Electrocardiogram (ECG) data recorded by Holter monitors are extremely hard to analyze manually. Therefore, it is necessary to automatically analyze and categorize each heartbeat using a computer-aid method. Because convolutional neural networks (CNNs) can classify ECG signals automatically without trivial manual feature extractions, they have received extensive attention. However, it is anticipated that improving the existing CNN classifiers might provide better overall accuracy, sensitivity, positive predictivity, etc. In this study, we proposed a CNN based ECG heartbeat classification method. Based on the MIT-BIH arrhythmia database, our proposed method achieved a sensitivity of 99.2% and positive predictivity of 99.4% in VEB detection; a sensitivity of 97.5% and positive predictivity of 99.1% in SVEB detection; and an overall accuracy of 99.43%. Our proposed system can be directly implemented on wearable devices to monitor long-term ECG data.

Monitoring single-channel EEG is a promising home-based approach for insomnia identification. Currently, many automatic sleep stage scoring approaches based on single-channel EEG have been developed, whereas few studies research on automatic insomnia identification based on single-channel EEG labelled with sleep stage annotations. In this paper, we propose a one-dimensional convolutional neural network (1D-CNN) model for automatic insomnia identification based on single-channel EEG labelled with sleep stage annotations, and further investigate the identification performance based on different sleep stages EEG epochs. Single-channel EEG on 9 insomnia patients and 9 healthy subjects was used in this study. We constructed 4 subdatasets from EEG epochs based on the sleep stage annotations: All sleep stage dataset (ALL-DS), REM sleep stage dataset (REM-DS), light sleep stage dataset (LSS-DS), and SWS sleep stage dataset (SWS-DS). Subsequently, 4 subdatasets were fed into our 1D-CNN. We conducted experiments under intra-patient and inter-patient paradigms, respectively. Our experiments demonstrated that our 1D-CNN leveraging 3 subdatasets composed of REM, LSS and SWS epochs, respectively, achieved higher average accuracies in comparison with baseline methods under both intra-patient and inter-patient paradigms. The experimental results also indicated that amongst all the sleep stages, 1D-CNN leveraging REM and SWS epochs exhibited the best insomnia identification average accuracies in intra-patient paradigm, which are 98.98% and 99.16% respectively, whereas no statistically significant difference was found in inter-patient paradigm. For automatic insomnia identification based on single-channel EEG labelled with sleep stage annotations, 1D-CNN model introduced in this paper could achieve superior performance than traditional methods.

Automatic sleep stage classification has gained much attention in recent researches. Various classification algorithms have been proposed for automatic sleep staging, including deep neural networks and traditional machine learning models. However, the output of those models has unreasonable sleep stage transitions, as temporal dependency of sleep stage label of adjacent data segment is ignored. In this paper, we propose a novel sleep stage contextual refinement algorithm based on conditional random fields (CRFs). The algorithm works as a post-processing step to rectify the hypnogram produced by sleep staging pre-classifiers. Unreasonable sleep stage transitions can be corrected via our algorithm to further improve the classification performance. We utilize CNN based, CNN-LSTM based, random forest, and two existing sleep staging models UTSN and UTSN-L as pre-classifiers. Our algorithm is evaluated on three sleep datasets, Sleep-EDF-20, DRM-SUB and SVUH-UCD datasets. Results demonstrate our CRF contextual refinement algorithm can improve the classification performance of five sleep staging pre-classifiers, including overlapping based and non-overlapping based models, and the algorithm works both on healthy subjects and patients with sleep disorder. When using CNN as pre-classifiers, our algorithm improves the overall accuracy and macro F1-score by 2.5%, 4.7% on Sleep-EDF-20, by 3.6%, 6.6% on DRM-SUB, and by 5.5%, 7.8% on SVUH-UCD dataset.

Sleep arousals is a type of sleep disorder, which refers to the phenomenon of waking up and falling asleep again. Monitoring the number and duration of sleep arousals is a crucial aspect of sleep quality assessment. The detection of sleep arousals caused by apnea is relatively easy, and existing methods have been able to give high quality results. However, sleep arousals caused by non-apnea remains an ongoing challenge, and this is also the subject of PhysioNet Computing in Cardiology Challenge 2018. We proposed a non-apnea sleep arousals automatic detection algorithm based on polysomnography (PSG) data. We took 8 most representative signals selected from the 13 channels of PSG signals as input, conducted preliminary classification through multiple convolutional neural networks, and then sent the initial results to the random forest module for ensemble voting, and obtained the final judgment. We carried out some experiments using the CinC 2018 database. We grouped the original dataset reasonably, and based on each group of data, we trained a corresponding CNN, ensuring the balance of positive and negative samples during the training. Our 4-fold cross validation results for the AUROC and AUPRC were 0.953 and 0.552, which were better than the results of the team which ranked first in the CinC 2018.

ECG signal is relatively weak and vulnerable to various noise interferences, such as electromyography. There will be robustness problems when detecting the instantaneous heart rate independently. In some cases, multiple human physiologic parameters are monitored to help in heart rate detection. In this paper, an algorithm that marks the R-wave peaks with the help of simultaneously recorded continuous blood pressure is proposed and tested on two databases. One database, called the challenge database, is provided by the PhysioNet/Computing in Cardiology Challenge 2014, and the other is the MGH/MF waveform database. The final scores of the proposed algorithm are 97.3% for the challenge database and 96.6% for the MGH/MF waveform database. The experimental results show that this algorithm has high detection accuracy and a relatively strong robustness.