Analysis of 54 cases of COVID-19

Objective: The clinical features and test results of Corona Virus Disease 2019 were analyzed retrospectively in order to understand the diagnostic significance of clinical test index, and to summarize the experience of clinical treatment. Methods: From February 10thto February 28th, 2020, 54 patients with Corona Virus Disease 2019 from Wuhan Red Cross hospital were included, whose clinical data were analyzed and integrated. The clinical manifestation and laboratory examination were analyzed by descriptive statistical analysis. Results: The average age of the patients was 63.9 years (40-84 years). The median time from onset to diagnosis was 6.5 days (2-20 days), and the median time from onset to first hospitalization was 8 days (3-20 days). The main manifestations were that the percentage of neutrophil increased and the number of lymphocyte decreased in most cases. Most of them were combined with liver damage and myocardial cell damage, and chest CT showed lesion of bilateral lung. Conclusion: In addition to the nucleic acid test of 2019-nCoV, some laboratory tests may indicate Corona Virus Disease 2019 in the early stages. The clinician may conduct repeated follow-up examinations to assess the progress and outcome of the disease.

COVID-19 Trend Forecasting by Using Dropout - LSTM Model

To improve the accuracy of COVID-19 trend forecasting, a method of COVID-19 trend forecasting by using dropout and long short-term memory (LSTM) is proposed. The method uses web crawler based on python to obtain complete domestic historical data of COVID-19, which improves the efficiency of data collection and reduces data errors caused by subjective reasons. To avoid adding time features artificially and explore the nonlinear relationship fully between the less data of COVID-19, the proposed model extends the layers of the deep learning network. Then, the dropout technique is applied to the non-circular part of each hidden layer to randomly deactivate neurons, preventing the neural network from overfitting. The experiment demonstrates that the method can predict the number of cumulative confirmed cases, current confirmed cases and recovered cases. Copyright ©2020 Journal of University of Electronic Science and Technology of China. All rights reserved.

The utility of simulation in preparing the healthcare workforce for providing CPR during medical emergencies in the COVID-19 pandemic

Background and aim: Healthcare workers (HCW) are at increased risk of developing coronavirus disease 2019 (COVID-19). Providing cardiopulmonary resuscitation (CPR) to a COVID-19 patient is an aerosol-generating procedure. Guidelines for personal protective equipment (PPE) use and providing CPR to COVID-19 patients have been developed locally for the purpose of improving patient and HCW safety. Medical simulation is used to educate HCWs. We aimed to the determine the utility of COVID-19 CPR simulation in improving HCWs ability, confidence and knowledge in managing medical emergencies. Methods: 108 HCWs participated in a standardised 1-h moderate-fidelity CPR simulation designed and delivered in the medical simulation laboratory at our tertiary metropolitan hospital in Sydney, Australia. Participant-filled surveys were collected pre and post-simulation. Data was categorised into assessment of perceived knowledge, confidence and ability in PPE use and providing CPR using a 5-point Likert scale. Statistical analyses were performed using the Mann–Whitney U test. Results: Of 108 participants, 94 were doctors and 14 nurses. The mean subjective scores of confidence in providing CPR pre and post-simulation were 2.3 and 3.9 respectively (p < 0.001);perceived ability to provide CPR pre and post-simulation were 2.5 and 4.0 respectively (p < 0.001);confidence in PPE use pre and post-simulation were 3.1 and 4.2 respectively (p < 0.001);perceived ability in PPE use pre and post-simulation were 3.3 and 4.2 respectively (p < 0.001) (see Fig. 1). Adequate knowledge of specific elements of newly developed guidelines improved from 14% to 97% of participants pre and post-simulation. Conclusion: Our study shows that during the COVID-19 pandemic, simulation of medical emergency scenarios is a valuable tool in improving knowledge, confidence and perceived ability of HCWs in PPE use and providing CPR in medical emergencies where real-life experience may be limited. Inadequate preparation before encountering real-life scenarios in COVID-19 patients may compromise the safety of both patients and healthcare workers.