Search

Abstract The COVID-19 influenza emerged and proved to be fatal, causing millions of deaths worldwide. Vaccines were eventually discovered, effectively preventing the severe symptoms caused by the disease. However, some of the population (elderly and patients with comorbidities) are still vulnerable to severe symptoms such as breathlessness and chest pain. Identifying these patients in advance is imperative to prevent a bad prognosis. Hence, machine learning and deep learning algorithms have been used for early COVID-19 severity prediction using clinical and laboratory markers. The COVID-19 data was collected from two Manipal hospitals after obtaining ethical clearance. Multiple nature-inspired feature selection algorithms are used to choose the most crucial markers. A maximum testing accuracy of 95% was achieved by the classifiers. The predictions obtained by the classifiers have been demystified using five explainable artificial intelligence techniques (XAI). According to XAI, the most important markers are c-reactive protein, basophils, lymphocytes, albumin, D-Dimer and neutrophils. The models could be deployed in various healthcare facilities to predict COVID-19 severity in advance so that appropriate treatments could be provided to mitigate a severe prognosis. The computer aided diagnostic method can also aid the healthcare professionals and ease the burden on already suffering healthcare infrastructure.

The inclusion complex of diphenylamine (DPA) in 2-hydroxypropyl β-cyclodextrin (HP-β-CD) was synthesized by a co-precipitation method. The structure and molecular properties of the newly synthesized inclusion complex (DPA: HP-β-CD) were investigated along with a β-cyclodextrin (β-CD) inclusion complex (DPA: β-CD) using various analytical and theoretical methods. Phase solubility, absorption, fluorescence, Fourier transform-Infrared spectroscopy (FTIR), powder X-ray diffraction (PXRD) and scanning electron microscope (SEM) techniques were used to investigate the structural properties of the DPA before and after being encapsulated by the CDs (β-CD and HP-β-CD). Furthermore, the antioxidant and antibacterial activities were evaluated for DPA and the inclusion complexes (DPA: β-CD and DPA: HP-β-CD). The structure of the inclusion complexes was proposed based on the experimental results and their structural optimization was done using Becke's three parameter density functional theory using Lee-Yang-Parr's 3-21 G method in the gas phase. Then the various theoretical molecular properties, such as frontier molecular orbitals (FMO), molecular electrostatic potential map (MEP), Mulliken atomic charges, natural bond orbitals (NBO), electron localization function (ELF), localized orbital locator (LOL), quantum theory of atoms in a molecule (QTAIM) and noncovalent interactions—reduced density gradient (NCI-RDG) were studied for DPA and its inclusion complexes using the Gaussian 09 W software and Multiwfn 3.8 tool. [ABSTRACT FROM AUTHOR]