Surface-Enhanced Raman Scattering Combined with Machine Learning for Rapid and Sensitive Detection of Anti-SARS-CoV-2 IgG.

Silva, Thais de Andrade; dos Santos, Gabriel Fernandes Souza; Prado, Adilson Ribeiro; Cavalieri, Daniel Cruz; Leal Junior, Arnaldo Gomes; Pereira, Flávio Garcia; Díaz, Camilo A. R.; Guimarães, Marco Cesar Cunegundes; Cassini, Servio Túlio Alves; Oliveira, Jairo Pinto de

This work reports an efficient method to detect SARS-CoV-2 antibodies in blood samples based on SERS combined with a machine learning tool. For this purpose, gold nanoparticles directly conjugated with spike protein were used in human blood samples to identify anti-SARS-CoV-2 antibodies. The comprehensive database utilized Raman spectra from all 594 blood serum samples. Machine learning investigations were carried out using the Scikit-Learn library and were implemented in Python, and the characteristics of Raman spectra of positive and negative SARS-CoV-2 samples were extracted using the Uniform Manifold Approximation and Projection (UMAP) technique. The machine learning models used were k-Nearest Neighbors (kNN), Support Vector Machine (SVM), Decision Trees (DTs), logistic regression (LR), and Light Gradient Boosting Machine (LightGBM). The kNN model led to a sensitivity of 0.943, specificity of 0.9275, and accuracy of 0.9377. This study showed that combining Raman spectroscopy and a machine algorithm can be an effective diagnostic method. Furthermore, we highlighted the advantages and disadvantages of each algorithm, providing valuable information for future research.

MACHINE learning; SUPPORT vector machines; RAMAN spectroscopy; K-nearest neighbor classification; GOLD nanoparticles; RAMAN scattering; SERS spectroscopy

Biosensors (2079-6374), 2024, Vol 14, Issue 11, p523

2079-6374

Academic Journal

10.3390/bios14110523