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.
Acute poisoning is characterized by a sudden and rapid onset, most poisons lack specific antidotes. Even with the full use of blood purification, mechanical ventilation, and various drugs, it is often difficult to change the fatal outcome of critically ill patients. In recent years, extracorporeal membrane oxygenation (ECMO) has gradually gained attention and exploratory application in the treatment of acute poisoning due to its significant cardiopulmonary function support, veno-venous ECMO is used for severe lung injury after poisoning, acute respiratory distress syndrome and respiratory failure due to ineffective mechanical ventilation, and it can also be used to assist the removal of residual poisons in the lungs. Veno-arterial ECMO is commonly employed in patients with circulatory failure following poisoning, fatal cardiac arrhythmias, and arrest of cardiac and respiratory. The application of veno-arterio-venous ECMO has also been reported. The mode of ECMO necessitates timely adjustments according to the evolving illness, while ongoing exploration of additional clinical indications is underway. This review analyzes and evaluates the application scope and effectiveness of ECMO in acute poisoning in recent years, with a view to better exploring and rationalizing the use of this technology.
ObjectiveTo investigate the effectiveness of Tang’s arthroscopy approach in treatment of anterior and posterior ankle impingement syndrome.MethodsBetween August 2010 and September 2017, 92 patients with anterior and posterior ankle impingement syndrome were retrospectively analyzed. There were 58 patients were treated with Tang’s arthroscopy approach under floating decubitus (group A) and 34 patients were treated with standard anterior and posterior approaches (group B). There was no significant difference in gender, age, body mass index, side, disease duration, preoperative American Orthopaedic Foot and Ankle Society (AOFAS) score, and preoperative visual analogue scale (VAS) score between the two groups (P>0.05).The operation time, AOFAS score, VAS score, and Roles-Maudsley score were recorded to evaluated the pain and function of the ankle, and patient subjective satisfaction. The X-ray film and MRI at 12 months were used to observe the ankle impingement.ResultsMedian operation time of group A was 50.5 minutes ［95%CI (49.3, 54.6)］, which was significantly shorter than that of group B ［88.5 minutes, 95%CI (76.5, 92.8)］ (Z=−4.685, P=0.000). All incisions in group A healed by first intention; while the incisions of 2 cases in group B delayed healed after debridement. The follow-up time of group A was (54.7±18.8) months, while that of group B was (55.4±17.9) months, and there was no significant difference between the two groups (t=−0.178, P=0.859). The lateral X-ray films at 12 months showed that the talus process was removed incompletely in 2 cases (3.4%) of group A and 1 case (2.9%) of group B. There was no significant difference in the incidence between the two groups (χ2=0.014, P=0.699). At last follow-up, the AOFAS scores were 83.1±6.6 in group A and 85.2±6.4 in group B; the VAS scores were 1.3±1.1 in group A and 1.6±1.0 in group B. The AOFAS and VAS scores at last follow-up were superior to preoperative ones (P<0.05), but there was no significant difference between the two groups (P>0.05). The median subjective satisfaction score of group A was 2.0 ［95%(1.4, 1.7)］, which was better than that of group B ［2.0, 95%(1.6, 2.2)］ (Z=−2.480, P=0.013).ConclusionArthroscopic treatment of anterior and posterior ankle impingement syndrome through Tang’s approach can shorten the operation time, simplify the procedures, and obtain good effectiveness and patient satisfaction.