Noninvasive Diagnostic for COVID-19 from Saliva Biofluid via FTIR Spectroscopy and Multivariate Analysis

Abstract

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused the worst global health crisis in living memory. The reverse transcription polymerase chain reaction (RT-qPCR) is considered the gold standard diagnostic method, but it exhibits limitations in the face of enormous demands. We evaluated a mid-infrared (MIR) data set of 237 saliva samples obtained from symptomatic patients (138 COVID-19 infections diagnosed via RT-qPCR). MIR spectra were evaluated via unsupervised random forest (URF) and classification models. Linear discriminant analysis (LDA) was applied following the genetic algorithm (GA-LDA), successive projection algorithm (SPA-LDA), partial least squares (PLS-DA), and a combination of dimension reduction and variable selection methods by particle swarm optimization (PSO-PLS-DA). Additionally, a consensus class was used. URF models can identify structures even in highly complex data. Individual models performed well, but the consensus class improved the validation performance to 85% accuracy, 93% sensitivity, 83% specificity, and a Matthew’s correlation coefficient value of 0.69, with information at different spectral regions. Therefore, through this unsupervised and supervised framework methodology, it is possible to better highlight the spectral regions associated with positive samples, including lipid (∼1700 cm –1 ), protein (∼1400 cm –1 ), and nucleic acid (∼1200–950 cm –1 ) regions. This methodology presents an important tool for a fast, noninvasive diagnostic technique, reducing costs and allowing for risk reduction strategies.

Potential of vibrational spectroscopy coupled with machine learning as a non-invasive diagnostic method for COVID-19

“…They evaluated a mid-infrared dataset of saliva samples obtained from symptomatic patients using unsupervised and supervised strategy. This method presents an important tool for a fast, noninvasive diagnostic technique, reducing costs and allowing for infection risk reduction [51] . Du et al proposed a method based on Raman spectroscopy combined with generative adversarial network and multiclass SVM to classify foodborne pathogenic bacteria.…”

An integrated analysis and comparison of serum, saliva and sebum for COVID-19 metabolomics

“…Whilst these cutaneous and oral symptoms have been widely reported, their metabolic causes are unknown. Furthermore, whilst blood-based metabolomic changes have been well-described, investigation of COVID-19 induced changes in the skin lipidome and the salivary metabolome have to date been few in number and restricted to untargeted mass spectrometry methods or infra-red spectroscopy studies that do not provide full identification of biomarkers 16 – 18 .…”

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

“…Banerjee et al investigated the potential of ATR-FTIR as a rapid blood test for assessing the severity of COVID-19 disease using PLS-DA, where results showed a specificity of 69.2% and a sensitivity of 94.1%. 58 Nascimento et al 22 evaluated IR spectra by unsupervised random forest (URF) model and, after class assignment by correlation to RT-qPCR, selected variables by several algorithms such as SPA (successive projection algorithm), GA, and PSO (particle swarm optimization), followed by classification models such as SPA-LDA, GA-LDA, PLS-DA, and PSO–PLS-DA in order to obtain a consensus class with a sensitivity of 93% and a specificity of 83% for separating SARS-CoV-2 negative from positive patients. Machine learning methods (random forest, standard C5.0 single decision tree algorithm, and DNN (deep neural networks)) following ATR-FTIR analysis of sera were successfully used by Guleken et al 23 for identifying spectral differences between moderately and severely ill COVID-19 positive pregnant women.…”