Single-shot, receptor-free, rapid detection and classification of five respiratory viruses by machine learning integrated SERS sensing platform.
Journal:
Biosensors & bioelectronics
PMID:
40139050
Abstract
A machine learning integrated SERS sensing platform is developed for a single-shot, receptor-free, rapid detection and classification of five respiratory viruses including Influenza A, Respiratory Syncytial Virus (RSV), Human Rhinoviruses (Rhino), and two variants of SARS-CoV-2 virus such as Omicron and Delta in clinical nasal and/or nasopharyngeal samples (CNS) in viral transport media (VTM). SERS sensor composed of Ag nano-sculptured thin film (nSTF) is fabricated by glancing angle deposition (GLAD) technique and possess a SERS enhancement factor of the order of 10. Various machine learning (ML) algorithms like Random Forest Classifier (RF), Support Vector Machine (SVM), Logistic Regression (LR), k-Nearest Neighbor (KNN), and Multilayer Perceptron (MLP) are trained on SERS spectra dataset of CNS for classification of the viruses. MLP shows the best performance for the analysis and classification of complex SERS spectra with a 5-fold validation accuracy of 97.61 ± 0.30 %, test accuracy 97.47 %, sensitivity 97 %, precision 97 %, and specificity 99 %. The SERS sensor integrated with ML has a rapid response of 11 minutes, which makes it appropriate for practical implementations in clinical environments, speeding up virus detection and efficient management of respiratory viral infections.