1. Rapid diagnosis of COVID-19 using FT-IR ATR spectroscopy and machine learning
- Author
-
Luis Felipe das Chagas e Silva de Carvalho, Paula Frizera Vassallo, Leonardo dos Santos, Wena Macarini, Matheus Muller, Leonardo Barbosa Leal, Wilson Barros Luiz, José Geraldo Mill, Marcelo Saito Nogueira, Valério Garrone Barauna, Raquel Lemos Pimentel, and Luciene Cristina Gastalho Campos
- Subjects
Oropharyngeal swab ,Multidisciplinary ,Coronavirus disease 2019 (COVID-19) ,business.industry ,Science ,Translational research ,Machine learning ,computer.software_genre ,Article ,Viral infection ,Attenuated total reflection ,Partial least squares regression ,Medicine ,Viral transport ,Artificial intelligence ,Biophotonics ,Fourier transform infrared spectroscopy ,Spectroscopy ,business ,computer ,Applied optics - Abstract
Early diagnosis of COVID-19 in suspected patients is essential for contagion control and damage reduction strategies. We investigated the applicability of attenuated total reflection (ATR) Fourier transform infrared (FTIR) spectroscopy associated with machine learning in oropharyngeal swab suspension fluid to predict COVID-19 positive samples. The study included samples of 243 patients from two Brazilian States. Samples were transported by using different viral transport mediums (liquid 1 or 2). Clinical COVID-19 diagnosis was performed by the RT-PCR. We built a classification model based on partial least squares (PLS) associated with cosine k-nearest neighbours (KNN). Our analysis led to 84% and 87% sensitivity, 66% and 64% specificity, and 76.9% and 78.4% accuracy for samples of liquids 1 and 2, respectively. Based on this proof-of-concept study, we believe this method could offer a simple, label-free, cost-effective solution for high-throughput screening of suspect patients for COVID-19 in health care centres and emergency departments.
- Published
- 2021