Usefulness of the Continuous Glucose Monitoring (Freestyle Device) to Assess Glycemic Control of Diabetic Patients With and Without COVID 19 in a Hospital of Bogotá Colombia

In the context of the COVID19 pandemic, diabetes mellitus constitutes a main risk factor that increases overall mortality (1). The continuous glucose monitoring system (CGM) is an alternative that allows strict glucose monitoring and reduces the contact of the healthcare providers with the patients in the pandemic era. We conducted a study using CGM in COVID vs non-COVID patients hospitalized at the San José Hospital in Bogotá Colombia. Methods: Single center, prospective study of glucose monitoring in patients with and without COVID19 using the Freestyle system. We included patients of 18 years and older, hospitalized at Hospital San José de Bogotá, with diagnosis of diabetes and treated with insulin. We used the T student distribution to analize the data. Primary outcomes were the usefulness of the device in inpatients, and the clinical outcomes according to glucometric measures in patients with and without COVID19 infection. Results: CGM devices were placed on 30 patients: 10 with, and 20 without COVID. The system was feasible with good nurse acceptance. The age of the patients was between 18 and 90 years. Of the COVID positive patients, 30% required ICU and 10% died, the mean HBA1C was 9.5% (CI 95% 7.5–10.09%) with a general variability of 35.6%, only 3 patients archieved goals of time in range. The general glycemic index was 7.04% (CI 0.66-0.100)Of the non COVID patients, 10% required ICU and 10% died, the average variability was 30.9% and hypoglycemic episodes predominated in 3 patients. The general glycemic index was 6.6% (CI 0.61–0.71)The patients who required ICU had an average HBA1C of 10.4%, 80% received corticosteroid management during the hospital stay. No patient had skin or soft tissue infection at the sensor insertion site. Conclusions: During the COVID-19 pandemic, CGM is a useful method for glucometric control that reduces the contact of healthcare providers and allows early interventions to improve metabolic control. Worse outcomes are seen in patients with higher variability and with COVID infection. References: 1. Apicella M. Campopiano MC. Mantuano M. Mazoni L. Coppelli A. Del Prato S. COVID-19 in people with diabetes: understanding the reasons for worse outcomes. Lancet Diabetes Endocrinol.2020: 8; 782–92.

Proyecciones matemáticas del COVID-19: simulación de escenarios para la elección 2021 en México

En este trabajo analizamos escenarios hipotéticos para contagios de COVID-19 durante la elección 2021 en México. Del 2 de abril al 2 de junio 2021 se llevarán a cabo elecciones de diputados federales, diputados locales, gubernaturas y presidencias municipales en lo que es considerada como la elección más grande en la historia de México; se estima que las actividades de las campañas electorales y el día de la votación se incrementará la movilidad de las personas y con ello su riesgo de contagio por COVID-19. Usando datos históricos de razones de contagios se define la media de estos datos, su desviación estándar y mediante una distribución t-Student se obtiene un intervalo de 90% de confianza para la media. Se utilizan el centro y ambos extremos de este intervalo como tasas de incremento para simular el crecimiento de casos en dos periodos (primer mes: elección diputados federales; segundo mes: elección gubernaturas, diputados locales y ayuntamientos); se reportan simulaciones usando algoritmos de aprendizaje de máquina a 2 meses pasadas las elecciones.Palabras clave: aprendizaje máquina, proyecciones COVID-19, elección 2021 México.SUMMARYIn this work we analyze hypothetical scenarios for COVID-19 infections during the 2021 election in Mexico; from april 2 to june 2, 2021, elections for federal deputies, local deputies, governorships and municipal presidencies will be held in what is considered the largest election in Mexico´s history; it is estimated that the activities of the electoral campaigns and the election day will increase the mobility of people and with it their risk of contagion by COVID-19. Using historical data on infection rates, the mean of these data is defined, its standard deviation and a t-Student distribution is used to obtain a 90% confidence interval for the mean. The center and both ends of this interval are used as rates of increase to simulate the growth of cases in two periods (first month; election of federal deputies; second month; election of governorships, local deputies and municipalities), simulations are reported using machine learning algorithms 2 monts after the elections.Keywords: machine learning, COVID-19 projections, Mexico 2021 electionINTRODUCCIÓNAl momento de escribir este trabajo, se han confirmado alrededor de 110 millones de casos de

Long Memory in the Volatility of Selected Cryptocurrencies: Bitcoin, Ethereum and Ripple

This paper examines the volatility of cryptocurrencies, with particular attention to their potential long memory properties. Using daily data for the three major cryptocurrencies, namely Ripple, Ethereum, and Bitcoin, we test for the long memory property using, Rescaled Range Statistics (R/S), Gaussian Semi Parametric (GSP) and the Geweke and Porter-Hudak (GPH) Model Method. Our findings show that squared returns of three cryptocurrencies have a significant long memory, supporting the use of fractional Generalized Auto Regressive Conditional Heteroscedasticity (GARCH) extensions as suitable modelling technique. Our findings indicate that the Hyperbolic GARCH (HYGARCH) model appears to be the best fitted model for Bitcoin. On the other hand, the Fractional Integrated GARCH (FIGARCH) model with skewed student distribution produces better estimations for Ethereum. Finally, FIGARCH model with student distribution appears to give a good fit for Ripple return. Based on Kupieck’s tests for Value at Risk (VaR) back-testing and expected shortfalls we can conclude that our models perform correctly in most of the cases for both the negative and positive returns.

Statistics Born in Brewery

One of the most important statistical tools is the t-test and its associated Student distribution. These techniques resulted from the work of W. S. Gosset, who published under the pseudonym Student. This paper presents the biographical facts and context of Gosset’s statistical research with his work at the Guinness Brewery. Gosset’s collaboration with important personalities of that time and his work are described. His core article, which laid the foundations of the small sample theory, is discussed in more detail.