Prognostic Model of ICU Admission Risk in Patients with COVID-19 Infection Using Machine Learning.

With the onset of the COVID-19 pandemic, the number of critically sick patients in intensive care units (ICUs) has increased worldwide, putting a burden on ICUs. Early prediction of ICU requirement is crucial for efficient resource management and distribution. Early-prediction scoring systems for critically ill patients using mathematical models are available, but are not generalized for COVID-19 and Non-COVID patients. This study aims to develop a generalized and reliable prognostic model for ICU admission for both COVID-19 and non-COVID-19 patients using best feature combination from the patient data at admission. A retrospective cohort study was conducted on a dataset collected from the pulmonology department of Moscow City State Hospital between 20 April 2020 and 5 June 2020. The dataset contains ten clinical features for 231 patients, of whom 100 patients were transferred to ICU and 131 were stable (non-ICU) patients. There were 156 COVID positive patients and 75 non-COVID patients. Different feature selection techniques were investigated, and a stacking machine learning model was proposed and compared with eight different classification algorithms to detect risk of need for ICU admission for both COVID-19 and non-COVID patients combined and COVID patients alone. C-reactive protein (CRP), chest computed tomography (CT), lung tissue affected (%), age, admission to hospital, and fibrinogen parameters at hospital admission were found to be important features for ICU-requirement risk prediction. The best performance was produced by the stacking approach, with weighted precision, sensitivity, F1-score, specificity, and overall accuracy of 84.45%, 84.48%, 83.64%, 84.47%, and 84.48%, respectively, for both types of patients, and 85.34%, 85.35%, 85.11%, 85.34%, and 85.35%, respectively, for COVID-19 patients only. The proposed work can help doctors to improve management through early prediction of the risk of need for ICU admission of patients during the COVID-19 pandemic, as the model can be used for both types of patients.

Alzheimer's Disease: An Update and Insights Into Pathophysiology.

Alzheimer's disease (AD) is an irreversible brain disorder associated with slow, progressive loss of brain functions mostly in older people. The disease processes start years before the symptoms are manifested at which point most therapies may not be as effective. In the hippocampus, the key proteins involved in the JAK2/STAT3 signaling pathway, such as p-JAK2-Tyr1007 and p-STAT3-Tyr705 were found to be elevated in various models of AD. In addition to neurons, glial cells such as astrocytes also play a crucial role in the progression of AD. Without having a significant effect on tau and amyloid pathologies, the JAK2/STAT3 pathway in reactive astrocytes exhibits a behavioral impact in the experimental models of AD. Cholinergic atrophy in AD has been traced to a trophic failure in the NGF metabolic pathway, which is essential for the survival and maintenance of basal forebrain cholinergic neurons (BFCN). In AD, there is an alteration in the conversion of the proNGF to mature NGF (mNGF), in addition to an increase in degradation of the biologically active mNGF. Thus, the application of exogenous mNGF in experimental studies was shown to improve the recovery of atrophic BFCN. Furthermore, it is now coming to light that the FGF7/FGFR2/PI3K/Akt signaling pathway mediated by microRNA-107 is also involved in AD pathogenesis. Vascular dysfunction has long been associated with cognitive decline and increased risk of AD. Vascular risk factors are associated with higher tau and cerebral beta-amyloid (Aß) burden, while synergistically acting with Aß to induce cognitive decline. The apolipoprotein E4 polymorphism is not just one of the vascular risk factors, but also the most prevalent genetic risk factor of AD. More recently, the research focus on AD shifted toward metabolisms of various neurotransmitters, major and minor nutrients, thus giving rise to metabolomics, the most important "omics" tool for the diagnosis and prognosis of neurodegenerative diseases based on an individual's metabolome. This review will therefore proffer a better understanding of novel signaling pathways associated with neural and glial mechanisms involved in AD, elaborate potential links between vascular dysfunction and AD, and recent developments in "omics"-based biomarkers in AD.

The Anti-Viral and Anti-Inflammatory Properties of Edible Bird's Nest in Influenza and Coronavirus Infections: From Pre-Clinical to Potential Clinical Application.

Edible bird's nest (BN) is a Chinese traditional medicine with innumerable health benefits, including anti-viral, anti-inflammatory, neuroprotective, and immunomodulatory effects. A small number of studies have reported the anti-viral effects of EBN against influenza infections using in vitro and in vivo models, highlighting the importance of sialic acid and thymol derivatives in their therapeutic effects. At present, studies have reported that EBN suppresses the replicated virus from exiting the host cells, reduces the viral replication, endosomal trafficking of the virus, intracellular viral autophagy process, secretion of pro-inflammatory cytokines, reorient the actin cytoskeleton of the infected cells, and increase the lysosomal degradation of viral materials. In other models of disease, EBN attenuates oxidative stress-induced cellular apoptosis, enhances proliferation and activation of B-cells and their antibody secretion. Given the sum of its therapeutic actions, EBN appears to be a candidate that is worth further exploring for its protective effects against diseases transmitted through air droplets. At present, anti-viral drugs are employed as the first-line defense against respiratory viral infections, unless vaccines are available for the specific pathogens. In patients with severe symptoms due to exacerbated cytokine secretion, anti-inflammatory agents are applied. Treatment efficacy varies across the patients, and in times of a pandemic like COVID-19, many of the drugs are still at the experimental stage. In this review, we present a comprehensive overview of anti-viral and anti-inflammatory effects of EBN, chemical constituents from various EBN preparation techniques, and drugs currently used to treat influenza and novel coronavirus infections. We also aim to review the pathogenesis of influenza A and coronavirus, and the potential of EBN in their clinical application. We also describe the current literature in human consumption of EBN, known allergenic or contaminant presence, and the focus of future direction on how these can be addressed to further improve EBN for potential clinical application.

COVID-19 and Hypertension: The What, the Why, and the How.

It has been a year since the coronavirus disease 2019 (COVID-19) was declared pandemic and wreak havoc worldwide. Despite meticulous research has been done in this period, there are still much to be learn from this novel coronavirus. Globally, observational studies have seen that majority of the patients with COVID-19 have preexisting hypertension. This raises the question about the possible relationship between COVID-19 and hypertension. This review summarizes the current understanding of the link between hypertension and COVID-19 and its underlying mechanisms.