On the Implementation of the Artificial Neural Network Approach for Forecasting Different Healthcare Events.

The rising number of confirmed cases and deaths in Pakistan caused by the coronavirus have caused problems in all areas of the country, not just healthcare. For accurate policy making, it is very important to have accurate and efficient predictions of confirmed cases and death counts. In this article, we use a coronavirus dataset that includes the number of deaths, confirmed cases, and recovered cases to test an artificial neural network model and compare it to different univariate time series models. In contrast to the artificial neural network model, we consider five univariate time series models to predict confirmed cases, deaths count, and recovered cases. The considered models are applied to Pakistan's daily records of confirmed cases, deaths, and recovered cases from 10 March 2020 to 3 July 2020. Two statistical measures are considered to assess the performances of the models. In addition, a statistical test, namely, the Diebold and Mariano test, is implemented to check the accuracy of the mean errors. The results (mean error and statistical test) show that the artificial neural network model is better suited to predict death and recovered coronavirus cases. In addition, the moving average model outperforms all other confirmed case models, while the autoregressive moving average is the second-best model.

Influence of COVID-19 vaccination on the dynamics of new infected cases in the world.

The initial COVID-19 vaccinations were created and distributed to the general population in 2020 thanks to emergency authorization and conditional approval. Consequently, numerous countries followed the process that is currently a global campaign. Taking into account the fact that people are being vaccinated, there are concerns about the effectiveness of that medical solution. Actually, this study is the first one focusing on how the number of vaccinated people might influence the spread of the pandemic in the world. From the Global Change Data Lab "Our World in Data", we were able to get data sets about the number of new cases and vaccinated people. This study is a longitudinal one from 14/12/2020 to 21/03/2021. In addition, we computed Generalized log-Linear Model on count time series (Negative Binomial distribution due to over dispersion in data) and implemented validation tests to confirm the robustness of our results. The findings revealed that when the number of vaccinated people increases by one new vaccination on a given day, the number of new cases decreases significantly two days after by one. The influence is not notable on the same day of vaccination. Authorities should increase the vaccination campaign to control well the pandemic. That solution has effectively started to reduce the spread of COVID-19 in the world.

Analyzing the Difference in the Length of Stay (LOS) in Moderate to Severe COVID-19 Patients Receiving Hydroxychloroquine or Favipiravir.

Background: The coronavirus 2019 (COVID-19) disease, caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus led to a global pandemic. HCQ and FPV were used early in the pandemic as a treatment modality for COVID-19. Various studies evaluated the HCQ and FPV effectiveness, based on the mortality endpoint and showed conflicting results. We hypothesize that analyzing the difference in the LOS as a significant endpoint would be of a major interest, especially for healthcare providers, to prevent a lengthy hospitalization and disease progression. Methods: This is a retrospective observational study, conducted via a medical chart review of COVD-19 patients who were admitted between April 2020 and March 2021 with a moderate to severe illness. The LOS endpoint was tested using the paired Wilcoxon signed-rank (WSR) model. Prior to using the WSR model, the balance between the HCQ and FPV groups, the propensity score matching, the LOS distribution, and the normality assumptions were tested. Two sensitivity statistical analyses were conducted to confirm the results (stratified log-rank test and U Welch test after transforming the LOS by the squared root values). Results: A total of 200 patients were included for the analysis: 83 patients in the HCQ group and 117 patients in the FPV group. Thirty-seven patients were matched in each group. The LOS data was positively skewed and violated the normality (Shapiro−Wilk p < 0.001) and had an unequal variance (Levene's test, p = 0.019). The WSR test showed no statistical significance in the LOS endpoint, with a median of −0.75 days (95% confidence interval: −4.0 to 2.5, p = 0.629), in favor of the HCQ group (four days), in comparison to seven days of the FPV group. The WSR findings were further confirmed with the stratified log rank test (p = 740) and the U Welch test (p = 391). Conclusions: The study concluded that the HCQ and FPV treatments have a comparable effectiveness in terms of the LOS in the moderate to severe COVID-19 patients. This study highlights the importance of analyzing the LOS as a relevant endpoint, in order to prevent the costs of a lengthy hospitalization and disease progression. The current study also emphasizes the importance of applying the appropriate statistical testing when dealing with two-sample paired data and analyzing non-parametric data such as the LOS.

Novel Type I Half Logistic Burr-Weibull Distribution: Application to COVID-19 Data.

In this work, we presented the type I half logistic Burr-Weibull distribution, which is a unique continuous distribution. It offers several superior benefits in fitting various sorts of data. Estimates of the model parameters based on classical and nonclassical approaches are offered. Also, the Bayesian estimates of the model parameters were examined. The Bayesian estimate method employs the Monte Carlo Markov chain approach for the posterior function since the posterior function came from an uncertain distribution. The use of Monte Carlo simulation is to assess the parameters. We established the superiority of the proposed distribution by utilising real COVID-19 data from varied countries such as Saudi Arabia and Italy to highlight the relevance and flexibility of the provided technique. We proved our superiority using both real data.

Prediction and Classification of COVID-19 Admissions to Intensive Care Units (ICU) Using Weighted Radial Kernel SVM Coupled with Recursive Feature Elimination (RFE).

Healthcare systems have been under immense pressure since the beginning of the COVID-19 pandemic; hence, studies on using machine learning (ML) methods for classifying ICU admissions and resource allocation are urgently needed. We investigated whether ML can propose a useful classification model for predicting the ICU admissions of COVID-19 patients. In this retrospective study, the clinical characteristics and laboratory findings of 100 patients with laboratory-confirmed COVID-19 tests were retrieved between May 2020 and January 2021. Based on patients' demographic and clinical data, we analyzed the capability of the proposed weighted radial kernel support vector machine (SVM), coupled with (RFE). The proposed method is compared with other reference methods such as linear discriminant analysis (LDA) and kernel-based SVM variants including the linear, polynomial, and radial kernels coupled with REF for predicting ICU admissions of COVID-19 patients. An initial performance assessment indicated that the SVM with weighted radial kernels coupled with REF outperformed the other classification methods in discriminating between ICU and non-ICU admissions in COVID-19 patients. Furthermore, applying the Recursive Feature Elimination (RFE) with weighted radial kernel SVM identified a significant set of variables that can predict and statistically distinguish ICU from non-ICU COVID-19 patients. The patients' weight, PCR Ct Value, CCL19, INF-ß, BLC, INR, PT, PTT, CKMB, HB, platelets, RBC, urea, creatinine and albumin results were found to be the significant predicting features. We believe that weighted radial kernel SVM can be used as an assisting ML approach to guide hospital decision makers in resource allocation and mobilization between intensive care and isolation units. We model the data retrospectively on a selected subset of patient-derived variables based on previous knowledge of ICU admission and this needs to be trained in order to forecast prospectively.

A new generalization of Gull Alpha Power Family of distributions with application to modeling COVID-19 mortality rates.

This paper proposes a new generalization of the Gull Alpha Power Family of distribution, namely the exponentiated generalized gull alpha power family of distribution abbreviated as (EGGAPF) with two additional parameters. This proposed family of distributions has some well known sub-models. Some of the basic properties of the distribution like the hazard function, survival function, order statistics, quantile function, moment generating function are investigated. In order to estimate the parameters of the model the method of maximum likelihood estimation is used. To assess the performance of the MLE estimates a simulation study was performed. It is observed that with increase in sample size, the average bias, and the RMSE decrease. A distribution from this family is fitted to two real data sets and compared to its sub-models. It can be concluded that the proposed distribution outperforms its sub-models.