A novel virtual simulation training improves providers' knowledge and confidence to manage obstetric emergencies

Objective: Maternal mortality in the United States (US) is rising and many deaths are preventable. We sought to determine the efficacy of virtual simulation training to optimize management of obstetric emergencies within low and moderate volume delivery hospitals that are disproportionately affected by adverse maternal outcomes. Study Design: The educational platform was designed and deployed within urban non-teaching and rural hospitals, with low and moderate delivery volumes, in the US during the COVID-19 pandemic. Self-paced, interactive, online didactics on postpartum hemorrhage and hypertensive disorders of pregnancy were followed by two, 2-hour live virtual simulation trainings and debriefings. In this innovative simulation modality, participants verbalized actions to their co-participants and the simulation faculty as scenarios evolved with images, vitals and videos displayed on a PowerPoint. Participants completed multiple-choice questionnaires and confidence and attitude surveys prior to, immediately after and 3-months post-training. The multiple-choice questions were evidence-based using information from published guidelines and were validated by local experts. Paired t-tests were performed to asses for changes in knowledge and confidence. Result(s): From December 2021 to March 2022, four hospitals received training (Table 1). Participants (n=22) were comprised of nurses (59%), certified nurse midwives (14%) and attending physicians (23%) in Obstetrics, Family Practice or Anesthesiology. The survey response rate was 59%. The mean difference in knowledge and confidence scores significantly improved immediately post-training compared to baseline (P < 0.05 for all, Table 2). This improvement was maintained 3 months following the training. Participants reported their preferred training format was hybrid (43%), virtual (35.7%) or in-person (21.4%). Conclusion(s): Virtual obstetric simulation is feasible and improves knowledge and confidence, which can be retained over time. This educational modality is sustainable, scalable and an accessible format to enhance education and training. [Formula presented] [Formula presented] Copyright © 2022

Finding an Efficient Image Size for Covid-19 Diagnosis using Chest X-Ray Images

Covid-19 or coronavirus is a new virus that infects the upper respiratory tract as well as the lungs. On the scale of the global pandemic, the number of cases and deaths has been increasing on a regular basis. Fostering a prediction system will assist officials in responding appropriately and rapidly. Medical imaging, such as X-ray, has been used to track coronavirus disease, which has proved to be effective for tracking various lung diseases. The promising Convolutional Neural Network (CNN) model with transfer learning for the accurate diagnosis of covid-19 has been presented in this paper. Multi-class classification will be generated in this study (covid vs. normal(healthy) vs. pneumonia). Experiments were performed with 1, 143 covid-19, 1, 341 normal, 1, 345 pneumonia CXR images. Performance measures such as accuracy, precision, recall, and f1 score are used to assess the proposed system efficacy. The purpose of this study is to compare the performance of each model while resizing the image [(256, 256), (224, 224), (128, 128), (64, 64)]. For the three-class classification, the proposed CNN model provides an accuracy of 90%, which is the best result among all results. © 2021 ACM.

Covid-19 chest radiography images analysis based on integration of image preprocess, guided grad-CAM, machine learning and risk management

COVID19 coronavirus has widely infected more than 10 million people and killed more than 500,000 globally till July 1, 2020. In this paper, we describe a potential methodology, integration of image preprocess, Guided Grad-CAM, machine learning and risk management based on chest radiography images, as one of workable alarm and analysis systems to support clinicians against COVID-19 outbreak threat. We leverage pre-trained CNN models as backbone with further transfer learning to analyze public open datasets composed of 5851 chest radiography images for 4 classes classification, and 15478 images from COVIDx dataset for 3 classes classification, facilitated with steps of ROI and mask, and CNN layer visualization of guided grad-CAM to help CNN focused on critical infection focus in qualitative perspective. In quantitative perspective of 4 classes classification result, accuracy, average sensitivity, average precision, and COVID19 sensitivity of single ResNet50 and our second bagging ensemble model are (77.2%/78.8%/81.9%/100%) and (81.5%/81.4%,86.8%/100%) respectively. Ensemble way of several CNNs and other machine learning methods used here is to contribute about 4% accuracy improvement on top of best single CNN (ResNet50). In our 3 classes classification, those metrics of ensemble model and benchmark are (93.1%/90.1%/89.7%/83%) and (90%/85.9%, 82.4%/77%). We conclude ensemble approach would facilitate weaker classifier more. Beside to accuracy-oriented analysis, a cost minimization approach is suggested here to provide clinicians options of different risk consideration flexibility by trade off among different categories and performance rates. © 2020 ACM.

'Occupational dermatoses from Personal Protective Equipment during the COVID-19 pandemic in the tropics - A Review'.

The COVID-19 pandemic has enveloped the world and there has been a high incidence of occupational dermatoses related to Personal Protective Equipment (PPE) amongst healthcare workers (HCWs) during this period. Prevention and management of these conditions will not only improve staff morale and quality of life, but will also minimize the risk of breaching PPE protocol due to such symptoms. The tropical climate in Singapore predisposes HCWs to more skin damage and pruritus due to intense heat, high humidity and sun exposure. The effects of friction, occlusion, hyperhidrosis and overheating on the skin in the tropics should not be neglected. Preventive measures can be taken based on our recommendations, and the working environment can be made more conducive for frontline HCWs. We review the literature and discuss various preventive and management strategies for these occupational skin diseases for our frontline HCWs, especially those working in less controlled working environments beyond the hospital in Singapore. Shorter shifts and frequent breaks from PPE are recommended. Duration of continuous PPE-usage should not exceed 6 h, with breaks in non-contaminated areas every 2-3 h to hydrate and mitigate the risk of skin reactions. Other strategies, such as teledermatology, should be considered so that consultations can remain accessible, while ensuring the safety and well-being of our clinical staff.