Saliva-based detection of COVID-19 infection in a real-world setting using reagent-free Raman spectroscopy and machine learning

Abstract

. Significance: The primary method of COVID-19 detection is reverse transcription polymerase chain reaction (RT-PCR) testing. PCR test sensitivity may decrease as more variants of concern arise and reagents may become less specific to the virus. Aim: We aimed to develop a reagent-free way to detect COVID-19 in a real-world setting with minimal constraints on sample acquisition. The machine learning (ML) models involved could be frequently updated to include spectral information about variants without needing to develop new reagents. Approach: We present a workflow for collecting, preparing, and imaging dried saliva supernatant droplets using a non-invasive, label-free technique—Raman spectroscopy—to detect changes in the molecular profile of saliva associated with COVID-19 infection. Results: We used an innovative multiple instance learning-based ML approach and droplet segmentation to analyze droplets. Amongst all confounding factors, we discriminated between COVID-positive and COVID-negative individuals yielding receiver operating coefficient curves with an area under curve (AUC) of 0.8 in both males (79% sensitivity and 75% specificity) and females (84% sensitivity and 64% specificity). Taking the sex of the saliva donor into account increased the AUC by 5%. Conclusion: These findings may pave the way for new rapid Raman spectroscopic screening tools for COVID-19 and other infectious diseases.

Optimization of Real-Time PCR Conditions for COVID-19 Diagnosis with Logix Smart Reagent™

“…Optimizing the total volume of 5 μl in 3 positive samples, positive control, and negative control indicates the presence of detected fluorescence signals. Based on fluorescence signals detected in figure 1 showing that all three positive-control on the amplification of the RdRP gene detected the presence of SARS-CoV-2 virus in the sample used (Kobayashi et al, 2021) (Ember et al, 2022) Figure 1 shows that negative control fluorescence signal and positive control were also detected at 5μl. On positive control with amplification of the RdRP gene shows a value of Cq 29,04 while amplification of the RNase-P gene offers a Cq-value is 24,57.…”

“…In addition to the SARS and MERS outbreaks in 2002 and 2012, the current Covid-19 explosion is also caused by this virus. The spread of the disease due to the SARS-CoV-2 virus is so fast with an easy transmission mechanism through the splash of saliva (droplets) and then into the respiratory tract through The mucus glands and then enters the respiratory tract (Ember et al, 2022). In addition, transmission can also be through the air aerosols inhaled into the respiratory tract.…”

“…The difference between droplets and aerosols is in the size of the particles. Droplet particle sizes are greater than or equal to 5 microns, while aerosols are less than 5μm (Ember et al, 2022).…”

Spectroscopic methods for COVID-19 detection and early diagnosis

“…As mentioned previously, increased blood levels of cysteine, alanine, aspartic acid, succinic acid, and lactic acid were seen after infection with COVID-19 [35], besides angiotensin-converting enzyme II (ACE2), which was significantly expressed in oral epithelial cells of patients [36]. Raman spectroscopy could possibly detect ACE2, by tracking the changes in intensity, width or shifts of Raman peaks [39]. Carlomagno et al [16] used surface enhanced Raman spectroscopy (SERS) as a novel method for detecting current (COV +) and previous SARS-CoV-2 infections (COV-) in saliva.…”

“…Raman spectroscopy is a nondestructive analytical method that offers information about the molecular composition of the materials analyzed with only a little quantity of sample and allows diagnosis in a matter of minutes with the right statistical and computational tools [38]. Raman spectroscopy may be used to identify biomolecular characteristics in biological materials, such as lipids, proteins, nucleic acids, and amino acids [39]. Raman spectroscopy, which is based on the principle of inelastic light scattering [40], has been used to identify HIV, dengue fever, and a variety of biomarkers, and could possibly overcome practical issues with mass testing as a point-of-care device [41][42][43].…”