Machine Learning Approaches for Temporal and Spatio-Temporal Covid-19 Forecasting: A Brief Review and a Contribution

In December 2019 an outbreak of a new disease happened, in Wuhan city, China, in which the symptoms were very similar to pneumonia. The disease was attributed to SARS-CoV-2 as the infectious agent and it was called the new coronavirus or Covid-19. In March 2020, the World Health Organization declared a worldwide pandemic of the new coronavirus. We have already counted more than 110 million cases and almost 2.5 million deaths worldwide. In order to assist in decision-making to contain the disease, several scientists around the world have engaged in various efforts, and they have proposed a lot of systems and solutions for tracking, monitoring, and predicting confirmed cases and deaths from Covid-19. Mathematical models help to analyze and understand the evolution of the disease, but understanding the disease was not enough, it was necessary to understand the problem in a quantitative way to lead the decision-making during the pandemic. Several initiatives have made use of Artificial Intelligence, and models were designed using machine learning algorithms with features for temporal and spatio-temporal investigation and prediction of cases of Covid-19. Among the algorithms used are Support Vector Machine (SVM), Random Forest, Multilayer Perceptron (MLP), Graph Neural Networks (GNNs), Ecological Niche Models (ENMs), Long-Short Term Memory Networks (LSTM), linear regression, and others. And these had good results, and to analyze them, the Root Mean Squared Error (RMSE), Log Root Mean Squared Error (RMSLE), correlation coefficient, and others were used as metrics. Covid-19 presents a huge problem to public health worldwide, so it is of utmost importance to investigate it, and with these two approaches it is possible to track not only how the disease evolves but also to know which areas are at risk. And these solutions can help in supporting decision-making by health managers to make the best decisions for the disease that is in the outbreak. This chapter aims to present a literature review and a brief contribution to the use of machine learning methods for temporal and spatio-temporal prediction of Covid-19, using Brazil and its federative units as a case study. From canonical methods to deep networks and hybrid committee-based, approaches will be investigated. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Rabies in a postpandemic world: resilient reservoirs, redoubtable riposte, recurrent roadblocks, and resolute recidivism

Rabies is an ancient disease. Two centuries since Pasteur, fundamental progress occurred in virology, vaccinology, and diagnostics—and an understanding of pathobiology and epizootiology of rabies in testament to One Health—before common terminological coinage. Prevention, control, selective elimination, and even the unthinkable—occasional treatment—of this zoonosis dawned by the twenty-first century. However, in contrast to smallpox and rinderpest, eradication is a wishful misnomer applied to rabies, particularly post-COVID-19 pandemic. Reasons are minion. Polyhostality encompasses bats and mesocarnivores, but other mammals represent a diverse spectrum of potential hosts. While rabies virus is the classical member of the genus, other species of lyssaviruses also cause the disease. Some reservoirs remain cryptic. Although global, this viral encephalitis is untreatable and often ignored. As with other neglected diseases, laboratory-based surveillance falls short of the notifiable ideal, especially in lower- and middle-income countries. Calculation of actual burden defaults to a flux within broad health economic models. Competing priorities, lack of defined, long-term international donors, and shrinking local champions challenge human prophylaxis and mass dog vaccination toward targets of 2030 for even canine rabies impacts. For prevention, all licensed vaccines are delivered to the individual, whether parenteral or oral–essentially ‘one and done'. Exploiting mammalian social behaviors, future ‘spreadable vaccines' might increase the proportion of immunized hosts per unit effort. However, the release of replication-competent, genetically modified organisms selectively engineered to spread intentionally throughout a population raises significant biological, ethical, and regulatory issues in need of broader, transdisciplinary discourse. How this rather curious idea will evolve toward actual unconventional prevention, control, or elimination in the near term remains debatable. In the interim, more precise terminology and realistic expectations serve as the norm for diverse, collective constituents to maintain progress in the field.

Recognising the potential of neglected tropical disease programmes as a platform for pandemic preparedness: the Ascend experience.

Living in an increasingly interconnected world, epidemics and pandemics are increasingly likely to be a vista for the future. This, coupled with the likely devastating effects of climate change, means that humanitarian crises are likely to increase. Now, more than ever before, is the time to scale up investment in prevention and preparedness strategies, and to review our current approaches to delivering health services, including those that address neglected tropical diseases. The Ascend West and Central Africa programme has illustrated the importance of innovation, multisector partnerships, resilience and the opportunity for change.

Forging Ahead the Repositioning of Multitargeted Drug Ivermectin.

With the advent of ivermectin, tremendous improvement in public health has been observed, especially in the treatment of onchocerciasis and lymphatic filariasis that created chaos mostly in rural, sub-Saharan Africa and Latin American countries. The discovery of ivermectin became a boon to millions of people that had suffered in the pandemic and still hold its pharmacological potential against these. Ivermectin continued to surprise scientists because of its notable role in the treatment of various other tropical diseases (Chagas, leishmaniasis, worm infections, etc.) and is viewed as the safest drug with the least toxic effects. The current review highlights its role in unexplored avenues towards forging ahead of the repositioning of this multitargeted drug in cancer, viral (the evaluation of the efficacy of ivermectin against SARS-Cov-2 is under investigation) and bacterial infection and malaria. This article also provides a glimpse of regulatory considerations of drug repurposing and current formulation strategies. Due to its broad-spectrum activity, multitargeted nature and promising efforts are put towards the repurposing of this drug throughout the field of medicine. This single drug originated from a microbe, changed the face of global health by proving its unmatched success and progressive efforts continue in maintaining its bequestnin the management of global health by decreasing the burden of various diseases worldwide.

Characterization of tungiasis infection and morbidity using thermography in Kenya revealed higher disease burden during COVID-19 school closures.

BACKGROUND: Tungiasis is a neglected tropical skin disease caused by the sand flea Tunga penetrans. Female fleas penetrate the skin, particularly at the feet, and cause severe inflammation. This study aimed to characterize disease burden in two highly affected regions in Kenya, to test the use of thermography to detect tungiasis-associated inflammation and to create a new two-level classification of disease severity suitable for mapping, targeting, and monitoring interventions. METHODS: From February 2020 to April 2021, 3532 pupils age 8-14 years were quasi-randomly selected in 35 public primary schools and examined for tungiasis and associated symptoms. Of the infected pupils, 266 were quasi-randomly selected and their households visited, where an additional 1138 family members were examined. Inflammation was assessed using infra-red thermography. A Clinical score was created combining the number of locations on the feet with acute and chronic symptoms and infra-red hotspots. RESULTS: The overall prevalence of tungiasis among all the school pupils who were randomly selected during survey rounds 1 and 3 was 9.3% [95% confidence interval (CI): 8.4-10.3]. Based on mixed effects logistic models, the odds of infection with tungiasis among school pupils was three times higher in Kwale (coastal Kenya) than in Siaya [western Kenya; adjusted odds ratio (aOR) = 0.36, 95% CI: 0.18-0.74]; three times higher in males than in females (aOR = 3.0, 95% CI: 2.32-3.91) and three times lower among pupils sleeping in a house with a concrete floor (aOR = 0.32, 95% CI: 0.24-0.44). The odds of finding an infected person among the household population during surveys before the COVID-19 pandemic was a third (aOR = 0.32, 95% CI: 0.19-0.53) of that when schools were closed due to COVID-19 restrictions and approximately half (aOR = 0.44, 95% CI: 0.29-0.68) in surveys done after school re-opening (round 3). Infection intensity was positively correlated with inflammation as measured by thermography (Spearman's rho = 0.68, P < 0.001) and with the clinical score (rho = 0.86, P < 0.001). Based on the two-level classification, severe cases were associated with a threefold higher level of pain (OR = 2.99, 95% CI: 2.02-4.43) and itching (OR = 3.31, 95% CI: 2.24-4.89) than mild cases. CONCLUSIONS: Thermography was a valuable addition for assessing morbidity and the proposed two-level classification of disease severity clearly separated patients with mild and severe impacts. The burden of tungiasis was considerably higher in households surveyed during COVID-19 restrictions suggesting underlying risks are found in the home environment more than in school.