Accuracy of COVID-19 evolution models for different forecast horizons

Currently, the statistics on COVID-19 for many regions are accumulated for the time span of over than two years, which facilitates the use of data-driven algorithms, such as neural networks, for prediction of the disease's further development. This article provides a comparative analysis of various forecasting models of COVID-19 dynamics. The forecasting is performed for the period from 07/20/2020 to 05/05/2022 using statistical data from the regions of the Russian Federation and the USA. The forecast target is defined as the sum of confirmed cases over the forecast horizon. Models based on the Exponential Smoothing (ES) method and deep learning methods based on Long Short-Term Memory (LSTM) units were considered. The training data set included the data from all regions available in the full data set. The MAPE metric was used for model comparison, the evaluation of the effectiveness of LSTM in the learning process was carried out using cross-validation on the mean squared error (MSE) metric. The comparisons were made with the models from various literature sources, as well as with the baseline model "tomorrow as today" (for which the sum of cases over the forecast horizon is supposed to be equal to the current case number multiplied by the forecast horizon length). It was shown that on small horizons (up to 28 days) the "tomorrow as today” model and ES algorithms show better accuracy than LSTM. In turn, on longer horizons (28 days or more), the preference should be given to the more complex LSTM-based model. © Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0)

On the accuracy of Covid-19 forecasting methods in Russia for two years

The effectiveness of predicting the dynamics of the coronavirus pandemic for Russia as a whole and for Moscow is studied for a two-year period beginning March 2020. The comparison includes well-proven population models and statistic methods along with a new data-driven model based on the LSTM neural network. The latter model is trained on a set of Russian regions simultaneously, and predicts the total number of cases on the 14-day forecast horizon. Prediction accuracy is estimated by the mean absolute percent error (MAPE). The results show that all the considered models, both simple and more complex, have similar efficiency. The lowest error achieved is 18% MAPE for Moscow and 8% MAPE for Russia.

Baseline Accuracies of Forecasting COVID-19 Cases in Russian Regions on a Year in Retrospect Using Basic Statistical and Machine Learning Methods.

The large amount of data accumulated so far on the dynamics of the COVID-19 outbreak has allowed assessing the accuracy of forecasting methods in retrospect. This work compares several basic time series analysis methods, including machine learning methods, for forecasting the number of confirmed cases for some days ahead. Year-long data for all regions of Russia has been used from the Yandex DataLens platform. As a result, accuracy estimates for these basic methods have been obtained for Russian regions and Russia as a whole, in dependence on the forecasting horizon. The best basic models for forecasting for 14 days are exponential smoothing and ARIMA, with an error of 11-19% by the MAPE metric for the latest part of the course of the epidemic. The accuracies obtained can be considered as baselines for more complex prospective models.

Rural development problems and new approaches to their solution in Russia

Russia faces a number of challenges to socio-economic development, the most dangerous of which is the depopulation of rural areas. Traditionally, policymakers have viewed rural development as a secondary goal to agricultural production, especially in the light of policies to increase agricultural exports. All this does not contribute to their development. The authors discuss the main challenges to rural development and describe how the recently adopted state program for integrated rural development, focused on supporting local initiatives, can reverse current trends. Among the most important measures are the development of the Internet and the participation of citizens, businesses, municipalities and their consortia in initiative projects. The effects of COVID-19 will have both positive and negative effects on rural development, but the pandemic has made people more likely to think about moving to the countryside.

The Russian language corpus and a neural network to analyse Internet tweet reports about Covid-19

This work is aimed at creating a tool for filtering messages from Twitter users by the presence of mentions of coronavirus disease in them. For this purpose, a corpus of Russian-language tweets was created, which contains the part of 10 thousand tweets that are manually divided into several classes with different levels of confidence: potentially have covid, have covid now, other cases, and an unmarked part – 2 million tweets on the topic of the pandemic. The paper presents the process of creating a corpus of tweets from the stage of data collection, their preliminary filtering and subsequent annotation according to the presence of disease description. Machine learning methods were compared according to classification task on tweets. It is shown that a model based on the XLM-RoBERTa topology with additional training on corpus of unmarked tweets gives the F1 score of 0.85 on binary classification task ("potentially have covid have covid now" vs "other"). This is 12% higher relative to the simplest model using TF-IDF encoding and SVM classifier and 5% higher relative to the RuDR-BERT-based model. The created toolkit will expand the feature space of models for predicting the spread of coronavirus infection and other pandemics by adding the dynamics of discussion on social networks, which characterizes people’s attitudes towards it. © Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0).

New approaches to rural development in Russia

As many other countries, Russia suffers from fast depopulation of rural areas and decline of rural economy. For years, the state policy for mitigate negative consequences of these processes was considering agriculture as the main pillar of rural development and most of governmental finding was oriented to its support. Recently, the new state strategy for rural development was formulated, and in 2019 an ambitious national program approved. It assumes different options for rural territories to develop economy and achieve welfare, depending on natural and human resources availability, remoteness and other features. The paper presents a review of the current state of rural areas of the Russian Federation. It focuses on the main issues the countryside faces at the national level and also reveals regional differences in rural development. The study is based mainly on the author's analysis of national statistical data sources, including the Russian Agricultural census of 2016, and the results of conducted survey. Possible effects of the measures of the new state policy of rural development such as encouraging community-based initiatives and promotion of housing construction through preferential rural mortgage loans programs are analysed. Finally, the authors provide a brief description of impact of the COVID-19 pandemic on rural development in Russia and attempt to forecast its further implications.

Baseline accuracy of forecasting COVID-19 cases in Moscow region on a year in retrospect using basic statistical and machine learning methods

The large amount of data that has accumulated so far on the dynamics of the COVID-19 outbreak has allowed to assess the accuracy of forecasting methods in retrospect. This work is devoted to comparing a set of basic time series analysis methods for forecasting the number of confirmed cases for 14 days ahead: machine learning methods, exponential smoothing, autoregressive methods, along with variants of SIR and SEIR. On the year-long data for Moscow, the best basic model is showed to be SEIR within which the basic reproduction number R0 is predicted using a regression model, achieving the mean error of 16% by the MAPE metric. The resulting accuracy can be considered a baseline for a more complex prospective model that would be based on the presented approach. © 2021 Institute of Physics Publishing. All rights reserved.

Pathobiochemical pathways of redox imbalance in the neurological long-term effects of COVID-19 and the role of chondroitin sulfate in the redox status restoration

The review examines the epidemiology and clinical manifestations of COVID-19 long-term neurological effects, main pathobiochemical mechanisms, and integrated circuits of redox status impairment in COVID-19, such as the decrease of adenosine triphosphate production, fatty acids levels, acylcarnitine, and amino acids, impairment of oxidative phosphorylation and glycolysis, hypometabolic state, redox imbalance with the increase of peroxides and superoxides, isoprostanes, the decrease of α-tocopherol, substances reacting with thiobarbituric acid, increased nitrosative stress with the increase of inducible synthase of nitric oxide, nitric oxide, peroxynitrite, and nitrate. Neuroprotective approaches aimed at suppressing excitotoxicity, oxidative stress, and neuroinflammation are presented. Recent data on the relationship between mechanisms of chondroitin sulfate and its derivatives (chondroitin sulfate glycoprotein disaccharide) neuroprotective effects and characteristics of their chemical structure are analyzed. The mechanism of action and neuroprotective effects of chondroitin sulfate and its derivatives in fatigue syndrome in patients with SARS-CoV2 infection are discussed (regulation of the PKC/PI3K/Akt activity, the increase of heme oxygenase-1 level, the decrease of reactive oxygen species). The position that chondroitin sulfate and its derivatives can become promising drugs to prevent the long-term neurological effects of COVID-19 is reasoned.

Treating Chronic Pain during Isolation

Objective of the Review: To present provisional guidelines for rheumatologists developed by the European League Against Rheumatism, the British Society for Rheumatology, the American Society of Regional Anesthesia and Pain Medicine, the European Society of Regional Anaesthesia and Pain Therapy, the American College of Rheumatology, and the Russian Association of Rheumatologists (a nationwide public organization). Key Points: The authors discuss publications touching on the management of rheumatic disorders during the coronavirus disease (COVID-19) pandemic, primarily medication therapy in patients with these conditions. They propose using chondroprotective agents as a possible alternative. According to World Health Organization recommendations, elderly people should exercise at home while self-isolating. I Conclusion: In attempting to present possible treatments for patients with joint disorders, the authors boldly propose using chondroprotective agents, which have all the properties required for long-term treatment during isolation. Цель обзора: представление предварительных рекомендаций для ревматологов Европейской антиревматической лиги (European League Against Rheumatism), Британской ассоциации ревматологов (British Society for Rheumatology), Американского общества регионарной анестезии и обезболивания (American Society of Regional Anesthesia and Pain Medicine) и Европейского общества регионарной анестезии и обезболивания (European Society of Regional Anaesthesia and Pain Therapy), Американской коллегии ревматологов (American College of Rheumatology) и Общероссийской общественной организации «Ассоциация ревматологов России». Основные положения. Обсуждаются опубликованные сообщения, затрагивающие вопросы ревматологии в период пандемии коронавирусной инфекции (COVID-19), прежде всего касающиеся лекарственных препаратов, применяемых у пациентов с ревматическими заболеваниями. В качестве альтернативных средств терапии рассматриваются хондропротекторы. В условиях самоизоляции лицами пожилого возраста, согласно рекомендациям Всемирной организации здравоохранения, предложено выполнять физические упражнения дома. Заключение. Нами предпринята попытка предоставить выбор терапии больным с заболеваниями суставов, и мы взяли на себя смелость рекомендовать хондропротекторы, обладающие всеми необходимыми свойствами для длительного лечения в условиях изоляции.

Novel coronavirus infection SARS-CoV-2 in elderly and senile patients: Prevention, diagnosis and treatment. Expert Position Paper of the Russian Association of Gerontology and Geriatrics

A novel coronavirus infection SARS-CoV-2 (COVID19) is especially dangerous for elderly and senile patients. Preventive measures for elderly people should cover three areas: 1) direct prevention of the viral infection, 2) preservation of the functional status and prevention of geriatric syndromes, including the use of social support measures, 3) control of comorbidities. The clinical pattern of COVID-19 in older patients may be atypical, while the mildness of symptoms (no fever, cough, shortness of breath) may not correspond to the severity of the prognosis. Delirium may be the first manifestation of COVID-19, which requires special care in its screening. Management of elderly and senile patients with COVID-19 should include measures for delirium prevention, the detection and improvement of nutrition. The risk of malnutrition with sarcopenia increases with hospitalization of a patient, especially when using artificial ventilation, is associated with an unfavorable prognosis during hospitalization, accelerates the progression of senile asthenia and reduces the quality of life. Geriatric assessment is the cornerstone of determining the management of an elderly patient.