ABSTRACT
The conventional methods used for the diagnostics of viral infection are either expensive and time-consuming or not accurate enough and dependent on consumable reagents. In the presence of pandemics, a fast and reagent-free solution is needed for mass screening. Recently, the diagnosis of viral infections using infrared spectroscopy has been reported as a fast and low-cost method. In this work a fast and low-cost solution for corona viral detection using infrared spectroscopy based on a compact micro-electro-mechanical systems (MEMS) device and artificial intelligence (AI) suitable for mass deployment is presented. Among the different variants of the corona virus that can infect people, 229E is used in this study due to its low pathogeny. The MEMS ATR-FTIR device employs a 6 reflections ZnSe crystal interface working in the spectral range of 2200-7000 cm-1. The virus was propagated and maintained in a medium for long enough time then cell supernatant was collected and centrifuged. The supernatant was then transferred and titrated using plaque titration assay. Positive virus samples were prepared with a concentration of 105 PFU/mL. Positive and negative control samples were applied on the crystal surface, dried using a heating lamp and the spectrum was captured. Principal component analysis and logistic regression were used as simple AI techniques. A sensitivity of about 90 % and a specificity of about 80 % were obtained demonstrating the potential detection of the virus based on the MEMS FTIR device. © 2023 SPIE.
ABSTRACT
Exhaled breath analysis is a promising noninvasive method for rapid diagnosis of diseases by detecting different types of volatile organic compounds (VOCs) that are used as biomarkers for early detection of various diseases such as lung cancer, diabetes, anemias, etc... and more recently COVID-19. Infrared spectroscopy seems to be a promising method for VOCs detection due to its ease of use, selectivity, and existence of compact low-cost devices. In this work, the use of Fourier transforms infrared (FTIR) spectrometer to analyze breath samples contained in a gas cell is investigated using deep learning and taking into account the practical performance limits of the spectrometer. Synthetic spectra are generated using infrared gas spectra databases to emulate real spectra resulted from a breath sample and train the neural network model (NNM). The dataset is generated in the spectral range of 2000 cm-1 to 6500 cm-1 and assuming a light-gas interaction length of 5 meters. The FTIR device performance is assumed with a signal-to-noise ratio (SNR) of 20,000:1 and a spectral resolution of 40 cm-1. The proposed NNM contains a locally connected and 4 fully connected layers. The concentrations of 9 biomarker gases in the exhaled breath are predicted with r2 score higher than 0.93, including carbon dioxide, water vapor, acetone, ethene, ammonia, methane, carbonyl sulfide, carbon monoxide and acetaldehyde demonstrating the possibility of detection. © 2021 IEEE.