Electrocardiogram (ECG) signals are easily disturbed by internal and external noise, and its morphological characteristics show significant variations for different patients. Even for the same patient, its characteristics are variable under different temporal and physical conditions. Therefore, ECG signal detection and recognition for the heart disease real-time monitoring and diagnosis are still difficult. Based on this, a wavelet self-adaptive threshold denoising combined with deep residual convolutional neural network algorithm was proposed for multiclass arrhythmias recognition. ECG signal filtering was implemented using wavelet adaptive threshold technology. A 20-layer convolutional neural network (CNN) containing multiple residual blocks, namely deep residual convolutional neural network (DR-CNN), was designed for recognition of five types of arrhythmia signals. The DR-CNN constructed by residual block local neural network units alleviated the difficulty of deep network convergence, the difficulty in tuning and so on. It also overcame the degradation problem of the traditional CNN when the network depth was increasing. Furthermore, the batch normalization of each convolution layer improved its convergence. Following the recommendations of the Association for the Advancements of Medical Instrumentation (AAMI), experimental results based on 94 091 2-lead heart beats from the MIT-BIH arrhythmia benchmark database demonstrated that our proposed method achieved the average detection accuracy of 99.034 9%, 99.498 0% and 99.334 7% for multiclass classification, ventricular ectopic beat (Veb) and supra-Veb (Sveb) recognition, respectively. Using the same platform and database, experimental results showed that under the comparable network complexity, our proposed method significantly improved the recognition accuracy, sensitivity and specificity compared to the traditional deep learning networks, such as deep Multilayer Perceptron (MLP), CNN, etc. The DR-CNN algorithm improves the accuracy of the arrhythmia intelligent diagnosis. If it is combined with wearable equipment, internet of things and wireless communication technology, the prevention, monitoring and diagnosis of heart disease can be extended to out-of-hospital scenarios, such as families and nursing homes. Therefore, it will improve the cure rate, and effectively save the medical resources.
Objective To systematically assess the correlation between smoking and the risk of endometriosis, so as to offer scientific basis to health education and preventing decision. Methods A literature search was performed in The Cochrane Library, Pubmed, Embase, CBM, CNKI and Wanfang database to collect the case control studies on the correlation between smoking and endometriosis. Two reviewers independently screened the literatures according to the inclusion and exclusion criteria, extracted the data, assessed the quality, and then conducted Meta-analyses on the 13 included RCTs by using RevMan 5.0 software, with calculation of the OR value and 95%CI. Results A total of 13 case control studies involving 14260 cases were included, of which 1900 ones were endometriosis. The quality assessment indicated that 2 studies were in quality of Level A, 4 were Level B, 7 were Level C, totally meant low quality. Meta-analyses showed that compared with non-smokers, there was no increasing possibility of endometriosis in smokers (OR= 0.91, 95%CI 0.82 to 1.02). The geographical subgroup analyses showed there was no significant difference in the incidence of endometriosis between the non-smokers and smokers in North America (OR=0.96, 95%CI 0.84 to 1.08), but a significant difference was found between non-smokers and smokers in Europe (OR=0.72, 95%CI 0.54 to 0.97). Conclusion There is no causative relationship between smoking and incidence of endometriosis. However, more high-quality trials are expected for further study because of the heterogeneity and poor quality of the current included studies.