Detection of NS1 from SERS spectra using K-NN integrated with PCA

NS1 is said to be responsible for the reproduction of RNA virus of the flaviviridae family, which is the cause of variants of Encephalitis, Yellow Fever and Dengue Fever. As an antigen, it can be detected in the blood of an infected person, from or before the onset of the symptoms. This makes it a biomarker for early detection of these diseases recently. The K-NN is a non-parametric method that shows strong capability in pattern recognition, classification and machine learning. Here, the K-NN classifier is used to distinguish SERS spectra of the salivary adulterated NS1 samples from the controlled samples. Since the features of SERS spectra is of high dimension, the K-NN classifier is preceded by the PCA to remove the redundant features and noise with Scree Test criterion. The performance of the PCA K-NN classifier is then investigated, using K-values between 1 and 19. The best performance, i.e. accuracy, precision, sensitivity and specificity of 100%, is found with K-value of one to three.