The doctor determines whether there are lesions in the human body through the diagnosis of medical images, and classifies and identifies the lesions. Therefore, the automatic classification and recognition of medical images has received extensive attention. Since the inflammatory phenomenon of vascular endothelial cells is closely related to the varicose veins of the lower extremities, in order to realize the automatic classification and recognition of varicose veins of the lower extremities, this paper proposes a varicose vein recognition algorithm based on vascular endothelial cell inflammation images and multi-scale deep learning, called MSDCNN. First, we obtained images of vascular endothelial cells in patients with varicose veins of the lower extremities and normal subjects. Second, multiple convolutional layers extract multi-scale features of vascular endothelial cell images. Then, the MFM activation function is used instead of the ReLU activation function to introduce a competitive mechanism that extracts more features that are compact and reduces network layer parameters. Finally, the network uses a 3 × 3 convolution kernel to improve the network feature extraction capability and use the 1 × 1 convolution kernel for dimensionality reduction to further streamline network parameters. The experimental results tell us that the network has the advantages of high recognition accuracy, fast running speed, few network parameters, and is suitable for small-embedded devices. INDEX TERMS Vascular endothelial cells, inflammation, multi-scale deep learning, varicose veins of the lower extremities.

Objective: To compare the efficacy of automated cardiopulmonary resuscitation (A-CPR) and manual cardiopulmonary resuscitation (M-CPR) in the rescue of cardiac and respiratory arrest. Methods: A retrospective, single-center observational study was conducted to identify 106 patients by reviewing medical records of 269 patients with cardiac and respiratory arrest treated in The Second Hospital of Hebei Medical University, Shandong Provincial Third Hospital (Jinan, China) from February 2019 to February 2021. Patients were divided into A-CPR group (n = 55) and M-CPR group (n = 51) based on the resuscitation treatment method. The groups were matched for age, gender and the cause of cardiac arrest. Rescue effects, blood gas analysis indicators, respiratory dynamics and condition improvement of the two groups were compared. Results: In terms of rescue effects, return of spontaneous circulation (ROSC) rate, successful rate of cardiopulmonary resuscitation (CPR), 24-hour survival rate and survival discharge rate in the A-CPR group were higher than M-CPR group (P<0.05). With respect to blood gas analysis indicators and respiratory dynamics, the partial pressure of carbon dioxide (PaCO2) in the A-CPR group was lower than M-CPR group at 15 and 30 minutes after CPR, while the partial pressure of oxygen (PaO2), blood oxygen saturation (SaO2), end expiratory carbon dioxide (PetCO2), coronary perfusion pressure (CPP) and mean arterial pressure (MAP) in the A-CPR group were higher than M-CPR group (P<0.05). In aspect of condition improvement, spontaneous breathing, heart rate, spontaneous circulation, blood pressure recovery time and CPR time in the A-CPR group were shorter than M-CPR group (P<0.05). Conclusion: The application effect of A-CPR in the rescue of cardiac and respiratory arrest, the improvement of blood gas analysis indexes, respiration and condition improvement are more significant than M-CPR. doi: https://doi.org/10.12669/pjms.38.8.6598 How to cite this:Gao M, Niu H, Yuan S. Comparison between automated cardiopulmonary resuscitation and manual cardiopulmonary resuscitation in the rescue of cardiac and respiratory arrest. Pak J Med Sci. 2022;38(8):2208-2214. doi: https://doi.org/10.12669/pjms.38.8.6598 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

No abstract

Background: We designed this systematic review and meta-analysis protocol to provide new medical evidence for clinical management by comparing the prognostic outcomes of visual laryngoscopy with those of conventional blinded insertion methods. Methods: We will intend to search English databases including Medicine, Embase, Web of Science, Cochrane Central Register of Controlled Trials, Scopus, and Google Scholar. The Chinese databases, such as Wanfang, China Knowledge Network, and China Biomedical Literature Database will also be searched. The outcome measures include intubation success rate, pain score, intubation-related complications, patient satisfaction, operation time, and cost. The Jadad scale will be used to evaluate the methodological quality of each randomized controlled trial in this meta-analysis. We will use the Methodological Index of Non-Randomized Studies criteria to assess the risk of bias in non-randomized study. An I 2 value greater than 50% indicates the presence of significant heterogeneity. P < .05 in a 2-tailed test is considered statistically significant. Results: It is hypothesized that video laryngoscope will provide better outcomes compared with traditional blind gastric tube insertion. Conclusions: The results of our review will be reported strictly following the PRISMA criteria and the review will add to the existing literature by showing compelling evidence and improved guidance in clinic settings.