Analysis of M-SEIR and LSTM models for the prediction of COVID-19 using RMSLE

During an epidemic period, it is important to perform the time forecasting analysis to track the growth of pandemic and plan accordingly to overcome the situation. The paper aims at performing the time forecasting of coronavirus disease 2019 (COVID-19) with respect to confirmed, recovered, and death cases of Karnataka, India. The modified mathematical epidemiological model used here are Susceptible - Exposed - Infectious - Recovered (SEIR) and recurrent neural network such as long short-term memory (LSTM) for analysis and comparison of the simulated output. To train, test, and optimize the model, the official data from Health and Family Welfare Department - Government of Karnataka is used. The evaluation of the model is conducted based on root mean square logarithmic error (RMSLE). © 2022 Scrivener Publishing LLC.

Analysis of M-SEIR and LSTM Models for the Prediction of COVID-19 Using RMSLE The impact of Covid-19 on the initiation of clinical trials in Europe and the United States

Summary During an epidemic period, it is important to perform the time forecasting analysis to track the growth of pandemic and plan accordingly to overcome the situation. The paper aims at performing the time forecasting of coronavirus disease 2019 (COVID-19) with respect to confirmed, recovered, and death cases of Karnataka, India. The modified mathematical epidemiological model used here are Susceptible - Exposed - Infectious - Recovered (SEIR) and recurrent neural network such as long short-term memory (LSTM) for analysis and comparison of the simulated output. To train, test, and optimize the model, the official data from Health and Family Welfare Department - Government of Karnataka is used. The evaluation of the model is conducted based on root mean square logarithmic error (RMSLE). The Covid-19 pandemic has a major impact not only on public health and daily living, but also on clinical trials worldwide. To investigate the potential impact of the Covid-19 pandemic on the initiation of clinical trials, we have descriptively analysed the longitudinal change in phase II and III interventional clinical trials initiated in Europe and in the United States. Based on the public clinical trial register EU Clinical Trials Register and clinicaltrials.gov, we conducted (a) a yearly comparison of the number of initiated trials from 2010 to 2020 and (b) a monthly comparison from January 2020 to February 2021 of the number of initiated trials. The analyses indicate that the Covid-19 pandemic affected both the initiation of clinical trials overall and the initiation of non-Covid-19 trials. An increase in the overall numbers of clinical trials could be observed both in Europe and the US in 2020 as compared to 2019. However, the number of non-Covid-19 trials initiated is reduced as compared to the previous decade, with a slightly larger relative decrease in the US as compared to Europe. Additionally, the monthly trend for the initiation of non-Covid-19 trials differs between regions. In the US, after a sharp decrease in April 2020, trial numbers reached the levels of 2019 from June 2020 onwards. In Europe, the decrease was less pronounced, but trial numbers mainly remained below the 2019 average until February 2021.