Potential of ATR-FTIR–Chemometrics in Covid-19: Disease Recognition

Abstract

The COVID-19 pandemic has caused major disturbances to human health and economy on a global scale. Although vaccination campaigns and important advances in treatments have been developed, an early diagnosis is still crucial. While PCR is the golden standard for diagnosing SARS-CoV-2 infection, rapid and low-cost techniques such as ATR-FTIR followed by multivariate analyses, where dimensions are reduced for obtaining valuable information from highly complex data sets, have been investigated. Most dimensionality reduction techniques attempt to discriminate and create new combinations of attributes prior to the classification stage; thus, the user needs to optimize a wealth of parameters before reaching reliable and valid outcomes. In this work, we developed a method for evaluating SARS-CoV-2 infection and COVID-19 disease severity on infrared spectra of sera, based on a rather simple feature selection technique (correlation-based feature subset selection). Dengue infection was also evaluated for assessing whether selectivity toward a different virus was possible with the same algorithm, although independent models were built for both viruses. High sensitivity (94.55%) and high specificity (98.44%) were obtained for assessing SARS-CoV-2 infection with our model; for severe COVID-19 disease classification, sensitivity is 70.97% and specificity is 94.95%; for mild disease classification, sensitivity is 33.33% and specificity is 94.64%; and for dengue infection assessment, sensitivity is 84.27% and specificity is 94.64%.

Two-trace two-dimensional correlation spectra (2T2D-COS) analysis using FTIR spectra to monitor the immune response by COVID-19

“…It is a cost-effective, minimally invasive, or non-invasive bio-spectroscopic technique developed as an excellent diagnostic tool [4]. FTIR spectra with chemometrics analysis help discriminate the molecular changes in the COVID-19 population successfully [9][10][11].…”

Detection of People Positive to COVID-19 through ATR-FTIR Spectra Analysis of Saliva using Machine Learning

“…The intersection of the same bonds of all sample components has made it difficult to use this clinical diagnosis technique because of the need for complex mathematical models to find a specific spectral behavior attributable to pathology. To deal with this problem, some researchers have already coupled FTIR with machine learning in order to characterize populations with SARS-CoV-2 [14] [15] [16] [17] [18] .…”

“…Although their study focused only on the female population during pregnancy and analyzing blood samples, authors of [15] , report an accuracy greater than 90 % in the characterization of 37 samples of participating patients considering a model based on the C5.0 single decision tree algorithm and deep neural network approach. Similar to [15] , the authors of [16] , analyze serum samples of 249 patients through ATR-FTIR and multivariate linear regression model (MLRM), allowing to report sensitivity and specificity values of 94.55 % and 98.44 % respectively. Analyzing sera samples from 82 patients, the authors of [17] , propose a mathematical model based on Partial least squares and discriminant analysis (PLS-DA).…”