Presidential Interdisciplinary Seed Grants
Nanotechnology and Machine Learning Based Rapid Infectious Disease Diagnostics
Nanotechnology and Machine Learning Based Rapid Infectious Disease Diagnostics
The development of a rapid, portable, and cost-effective point-of-care method to detect the viruses and bacteria infection in patients, such as severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2) or other infectious viruses, is essential to mitigate epidemic and pandemic diseases. The goal of this proposal is to develop a diagnostic method based on nano-optics (surface enhanced Raman scattering, SERS) and machine learning techniques. Our preliminary results show that such a combination can deliver direct and differential detection of important respiratory viruses within 20 minutes. We will use 14 virus samples as well as spiked body fluid (saliva, nasal swab, etc.) samples to collect sufficient SERS spectra to develop the optimized machine learning model and validate the model. The detection strategies will be confirmed using clinic samples from unidentified volunteer patient specimens isolated from the Microbiology Lab in Piedmont Athens Regional Hospital as well as UGA Tifton Veterinary Diagnostic and Investigational Laboratory. The proposed strategy is a very general strategy to combine a novel detection technique with big data technology and can have a profound implication in various diagnostic applications.
Team Lead
Yiping Zhao
Physics and Astronomy
zhaoy@uga.edu
Team Members
Ralph Tripp
Department of Infectious Diseases
Xianyan Chen
Department of Statistics
Hemant Naikare
Department of Infectious Diseases
Suzanne Morrison
N/A