Deep Learning-Assisted Surface-Enhanced Raman Scattering for Rapid Bacterial Identification.

Bloodstream infection (BSI) is characterized by the presence of viable microorganisms in the bloodstream and may induce systemic immune responses. Early and appropriate antibiotic usage is crucial to effectively treating BSI. However, conventional culture-based microbiological diagnostics are time-consuming and cannot provide timely bacterial identification for subsequent antimicrobial susceptibility test (AST) and clinical decision-making. To address this issue, modern microbiological diagnostics have been developed, such as surface-enhanced Raman scattering (SERS), which is a sensitive, label-free, and quick bacterial detection method measuring specific bacterial metabolites. In this study, we aim to integrate a new deep learning (DL) method, Vision Transformer (ViT), with bacterial SERS spectral analysis to build the SERS-DL model for rapid identification of Gram type, species, and resistant strains. To demonstrate the feasibility of our approach, we used 11,774 SERS spectra obtained directly from eight common bacterial species in clinical blood samples without artificial introduction as the training dataset for the SERS-DL model. Our results showed that ViT achieved excellent identification accuracy of 99.30% for Gram type and 97.56% for species. Moreover, we employed transfer learning by using the Gram-positive species identifier as a pre-trained model to perform the antibiotic-resistant strain task. The identification accuracy of methicillin-resistant and -susceptible Staphylococcus aureus (MRSA and MSSA) can reach 98.5% with only 200-dataset requirement. In summary, our SERS-DL model has great potential to provide a quick clinical reference to determine the bacterial Gram type, species, and even resistant strains, which can guide early antibiotic usage in BSI.

An antibiotic concentration gradient microfluidic device integrating surface-enhanced Raman spectroscopy for multiplex antimicrobial susceptibility testing.

Antimicrobial susceptibility testing (AST) is a key measure in clinical microbiology laboratories to enable appropriate antimicrobial administration. During an AST, the determination of the minimum inhibitory concentration (MIC) is an important step in which the bacterial responses to an antibiotic at a series of concentrations obtained in separate bacterial growth chambers or sites are compared. However, the preparation of different antibiotic concentrations is time-consuming and labor-intensive. In this paper, we present a microfluidic device that generates a concentration gradient for antibiotics that is produced by diffusion in the laminar flow regime along a series of lateral microwells to encapsulate bacteria for antibiotic treatment. All the AST preparation steps (including bacterium loading, antibiotic concentration generation, buffer washing, and isolated bacterial growth with an antibiotic) can be performed in a single chip. The viable bacterial cells in each microwell after the antibiotic treatment are then quantified by their surface-enhanced Raman scattering (SERS) signals that are acquired after placing a uniform SERS-active substrate in contact with all the microwells. For proof-of-concept, we demonstrated the AST performance of this system on ampicillin (AMP)-susceptible and -resistant E. coli strains. Compared with the parameters for conventional AST methods, the AST procedure based on this chip requires only 20 µL of bacteria solution and 5 h of operation time. This result indicates that this integrated system can greatly shorten and simplify the tedious and labor-intensive procedures required for current standard AST methods.