Background Management errors during pre-hospital care, triage process and resuscitation have been widely reported as the major source of preventable and potentially preventable deaths in multiple trauma patients. Common tools for defining whether it is a preventable, potentially preventable or non-preventable death include the Advanced Trauma Life Support (ATLS Ò ) clinical guideline, the Injury Severity Score (ISS) and the Trauma and Injury Severity Score (TRISS). Therefore, these surrogated scores were utilized in reviewing the study's trauma services. Methods Trauma data were prospectively collected and retrospectively reviewed from January 1, 2018, to December 31, 2018. All cases of trauma death were discussed and audited by the Hospital Trauma Committee on a regular basis. Standardized form was used to document the patient's management flow and details in every case during the meeting, and the final verdict (whether death was preventable or not) was agreed and signed by every member of the team. The reasons for the death of the patients were further classified into severe injuries, inappropriate/delayed examination, inappropriate/delayed treatment, wrong decision, insufficient supervision/guidance or lack of appropriate guidance. Results A total of 1913 trauma patients were admitted during the study period, 82 of whom were identified as major trauma (either ISS [ 15 or trauma team was activated). Among the 82 patients with major trauma, eight were trauma-related deaths, one of which was considered a preventable death and the other 7 were considered unpreventable. The decision from the hospital's performance improvement and patient safety program indicates that for every trauma patient, basic life support principles must be followed in the course of primary investigations for bedside trauma series X-ray (chest and pelvis) and FAST scan in the resuscitation room by a person who meets the criteria for trauma team activation recommended by ATLS Ò . Conclusion Mechanisms to rectify errors in the management of multiple trauma patients are essential for improving the quality of trauma care. Regular auditing in the trauma service is one of the most important parts of performance improvement and patient safety program, and it should be well established by every major trauma center in Mainland China. It can enhance the trauma management processes, decision-making skills and practical skills, thereby continuously improving quality and reducing mortality of this group of patients.
Highlights
Complicated gallstone disease during pregnancy can be successfully managed by combined laparoscopic cholecystectomy and exploration of common bile duct through trans-cystic duct approach.
This approach is safe and can cure cholecystitis and choledocholithiasis in one goal.
This approach avoids ionizing radiation to the developing fetus.
Facial Expression Recognition (FER) can achieve an understanding of the emotional changes of a specific target group. The relatively small dataset related to facial expression recognition and the lack of a high accuracy of expression recognition are both a challenge for researchers. In recent years, with the rapid development of computer technology, especially the great progress of deep learning, more and more convolutional neural networks have been developed for FER research. Most of the convolutional neural performances are not good enough when dealing with the problems of overfitting from too-small datasets and noise, due to expression-independent intra-class differences. In this paper, we propose a Dual Path Stacked Attention Network (DPSAN) to better cope with the above challenges. Firstly, the features of key regions in faces are extracted using segmentation, and irrelevant regions are ignored, which effectively suppresses intra-class differences. Secondly, by providing the global image and segmented local image regions as training data for the integrated dual path model, the overfitting problem of the deep network due to a lack of data can be effectively mitigated. Finally, this paper also designs a stacked attention module to weight the fused feature maps according to the importance of each part for expression recognition. For the cropping scheme, this paper chooses to adopt a cropping method based on the fixed four regions of the face image, to segment out the key image regions and to ignore the irrelevant regions, so as to improve the efficiency of the algorithm computation. The experimental results on the public datasets, CK+ and FERPLUS, demonstrate the effectiveness of DPSAN, and its accuracy reaches the level of current state-of-the-art methods on both CK+ and FERPLUS, with 93.2% and 87.63% accuracy on the CK+ dataset and FERPLUS dataset, respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.