학술논문

Classification of Respiratory Syncytial Virus and Sendai Virus Using Portable Near-Infrared Spectroscopy and Chemometrics
Document Type
Periodical
Source
IEEE Sensors Journal IEEE Sensors J. Sensors Journal, IEEE. 23(9):9981-9989 May, 2023
Subject
Signal Processing and Analysis
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Robotics and Control Systems
Viruses (medical)
Coronaviruses
Standards
Reflectivity
Influenza
Training
Sea measurements
Chemometrics
classification
near-infrared spectroscopy (NIRS)
partial least-squares discriminant analysis (PLS-DA)
respiratory syncytial virus (RSV)
Sendai virus (SeV)
Language
ISSN
1530-437X
1558-1748
2379-9153
Abstract
There is evidence that it may be possible to detect viruses and viral infection optically using techniques such as Raman and infrared (IR) spectroscopy and hence open the possibility of rapid identification of infected patients. However, high-resolution Raman and IR spectroscopy instruments are laboratory-based and require skilled operators. The use of low-cost portable or field-deployable instruments employing similar optical approaches would be highly advantageous. In this work, we use chemometrics applied to low-resolution near-IR (NIR) reflectance/absorbance spectra to investigate the potential for simple low-cost virus detection suitable for widespread societal deployment. We present the combination of near-IR spectroscopy (NIRS) and chemometrics to distinguish two respiratory viruses, respiratory syncytial virus (RSV), the principal cause of severe lower respiratory tract infections in infants worldwide, and Sendai virus (SeV), a prototypic paramyxovirus. Using a low-cost and portable spectrometer, three sets of RSV and SeV spectra, dispersed in phosphate-buffered saline (PBS) medium or Dulbecco’s modified eagle medium (DMEM), were collected in long- and short-term experiments. The spectra were preprocessed and analyzed by partial least-squares discriminant analysis (PLS-DA) for virus type and concentration classification. Moreover, the virus type/concentration separability was visualized in a low-dimensional space through data projection. The highest virus-type classification accuracy obtained in PBS and DMEM is 85.8% and 99.7%, respectively. The results demonstrate the feasibility of using portable NIR spectroscopy as a valuable tool for rapid, on- site, and low-cost virus prescreening for RSV and SeV with the further possibility of extending this to other respiratory viruses such as SARS-CoV-2.