Raman spectroscopy based screening of IgG positive and negative sera for dengue virus infection

Abstract

A quantitative analysis for the screening of immunoglobulin-G (IgG) positive human sera samples is presented for the dengue virus infection. The regression model was developed using 79 samples while 20 samples were used to test the performance of the model. The R-square (r 2 ) value of 0.91 was found through a leave-one-sample-out cross validation method, which shows the validity of this model. This model incorporates the molecular changes associated with IgG. Molecular analysis based on regression coefficients revealed that myristic acid, coenzyme-A, alanine, arabinose, arginine, vitamin C, carotene, fumarate, galactosamine, glutamate, lactic acid, stearic acid, tryptophan and vaccenic acid are positively correlated with IgG; while amide III, collagen, proteins, fatty acids, phospholipids and fucose are negatively correlated. For blindly tested samples, an excellent agreement has been found between the model predicted, and the clinical values of IgG. The parameters, which include sensitivity, specificity, accuracy and the area under the receiver operator characteristic curve, are found to be 100%, 83.3%, 95% and 0.99, respectively, which confirms the high quality of the model.

Diagnosis of dengue virus infection using spectroscopic images and deep learning

“…It has been extensively used for the detection of hepatitis C virus (HCV) ( Naseer et al, 2019b ), hepatitis B virus (HBV) ( Tong et al, 2019 ; Ali et al, 2021 ; Saleem et al, 2020 ), malaria fever ( Naseer et al, 2019a ) human immunodeficiency virus (HIV) ( Lee et al, 2015 ), tuberculosis (TB) ( Stöckel et al, 2017 ) and DENV infections ( Mahmood et al, 2018 ). For the diagnosis of DENV infection, different multivariate algorithms are employed including principal component analysis (PCA) 20 partial least square regression (PLSR) ( Bilal et al, 2017 ), support vector machine (SVM) ( Khan et al, 2016 ) and random forest algorithms ( Khan et al, 2017 ).…”

Optical diagnosis of hepatitis B virus infection in blood plasma using Raman spectroscopy and chemometric techniques

“…Therefore, in order to improve the diagnostic capability for infectious diseases, new, reliable, online, and economical methods are needed to be developed for diagnosis and for monitoring the progression of infection. In this regard, different research studies have been reported on the development of diagnostic algorithms using spectroscopic approaches such as Raman spectroscopy in combination with multivariate analysis including machine learning approaches such as support vector machine (SVM), 24,25,28 artificial neural network (ANN), 29 principal component analysis (PCA), 16,18 and partial least squares regression (PLSR) 15,27,30 …”

“…13 Each molecule has a unique scattering patron, which serves as a fingerprint and hence identification entity for a particular molecule or compound in a mixture. In recent years, Raman spectra of blood serum samples were used to diagnose many types of infectious diseases, including dengue virus infection, [14][15][16] hepatitis C, 17,18 typhoid and malaria fever, [19][20][21] HIV infection, 22 tuberculosis, 23 and HBV infection. [24][25][26][27] Therefore, in order to improve the diagnostic capability for infectious diseases, new, reliable, online, and economical methods are needed to be developed for diagnosis and for monitoring the progression of infection.…”

“…In this regard, different research studies have been reported on the development of diagnostic algorithms using spectroscopic approaches such as Raman spectroscopy in combination with multivariate analysis including machine learning approaches such as support vector machine (SVM), 24,25,28 artificial neural network (ANN), 29 principal component analysis (PCA), 16,18 and partial least squares regression (PLSR). 15,27,30 During recent years, four studies have been reported on the detection of HBV infection in blood sera using Raman spectroscopy. [24][25][26][27] Khan et al 24 used SVM algorithm on the Raman spectra of diseased and healthy samples and compared diagnostic accuracy for different polynomial kernel.…”