Sleep apnea automatic detection method based on convolutional neural network / 生物医学工程学杂志

Sleep apnea (SA) detection method based on traditional machine learning needs a lot of efforts in feature engineering and classifier design. We constructed a one-dimensional convolutional neural network (CNN) model, which consists in four convolution layers, four pooling layers, two full connection layers and one classification layer. The automatic feature extraction and classification were realized by the structure of the proposed CNN model. The model was verified by the whole night single-channel sleep electrocardiogram (ECG) signals of 70 subjects from the Apnea-ECG dataset. Our results showed that the accuracy of per-segment SA detection was ranged from 80.1% to 88.0%, using the input signals of single-channel ECG signal, RR interval (RRI) sequence, R peak sequence and RRI sequence + R peak sequence respectively. These results indicated that the proposed CNN model was effective and can automatically extract and classify features from the original single-channel ECG signal or its derived signal RRI and R peak sequence. When the input signals were RRI sequence + R peak sequence, the CNN model achieved the best performance. The accuracy, sensitivity and specificity of per-segment SA detection were 88.0%, 85.1% and 89.9%, respectively. And the accuracy of per-recording SA diagnosis was 100%. These findings indicated that the proposed method can effectively improve the accuracy and robustness of SA detection and outperform the methods reported in recent years. The proposed CNN model can be applied to portable screening diagnosis equipment for SA with remote server.

Effect of the CAD/CAM zirconia all-ceramic crown restoration on periodontal tissue / 中国组织工程研究

BACKGROUND:To maintain the long-term effect of ful crown largely depends on the health of periodontal tissues. OBJECTIVE:To explore the effect of CAD/CAM zirconia al-ceramic crown restoration on the state of periodontal health. METHODS:Sixty-four abutments of 55 patients were randomly divided into two groups:the experimental group included 32 abutments of 29 patients which would be restored by CAD/CAM zirconia al-ceramic crowns;the control ed group included 32 abutments of 26 patients which would be restored by Ni-Cr al oy porcelain-fused-to-metal restorations. The volume of gingival crevicular fluid and the levels of interleukin-6 and tumor necrosis factor-αin the two groups were examined at the pre-restoration and post-restoration stages. Meanwhile, periodontal clinical indicators, including sulcus bleeding index, probing depth, plaque index and attachment loss were recorded. RESULTS AND CONCLUSION:No difference in various indexes was found in the experimental group before and after restoration (P>0.05). At 12 months after restoration, in the control group, the volume of gingival crevicular fluid, the levels of interleukin-6 and tumor necrosis factor-α, sulcus bleeding index, probing depth, and plaque index were al increased (P>0.05);meanwhile, these indexes in the experimental group were significantly lower than those in the control group (P<0.05). Experimental findings suggest that the CAD/CAM zirconia al-ceramic crown restoration is more favorable to the health of periodontal tissues.