Over the past year, the world's attention has focused on combating COVID-19 disease, but the other threat waiting at the door—antimicrobial resistance should not be forgotten. Although making the diagnosis rapidly and accurately is crucial in preventing antibiotic resistance development, bacterial identification techniques include some challenging processes. To address this challenge, we proposed a deep neural network (DNN) that can discriminate antibiotic-resistant bacteria using surface-enhanced Raman spectroscopy (SERS). Stacked autoencoder (SAE)-based DNN was used for the rapid identification of methicillin-resistant Staphylococcus aureus (MRSA) and methicillin-sensitive S. aureus (MSSA) bacteria using a label-free SERS technique. The performance of the DNN was compared with traditional classifiers. Since the SERS technique provides high signal-to-noise ratio (SNR) data, some subtle differences were found between MRSA and MSSA in relative band intensities. SAE-based DNN can learn features from raw data and classify them with an accuracy of 97.66%. Moreover, the model discriminates bacteria with an area under curve (AUC) of 0.99. Compared to traditional classifiers, SAE-based DNN was found superior in accuracy and AUC values. The obtained results are also supported by statistical analysis. These results demonstrate that deep learning has great potential to characterize and detect antibiotic-resistant bacteria by using SERS spectral data.

To combat antibiotic resistance, it is extremely important to select the right antibiotic by performing rapid diagnosis of pathogens. Traditional techniques require complicated sample preparation and time-consuming processes which are not suitable for rapid diagnosis. To address this problem, we used surface-enhanced Raman spectroscopy combined with machine learning techniques for rapid identification of methicillin-resistant and methicillin-sensitive Gram-positive Staphylococcus aureus strains and Gram-negative Legionella pneumophila (control group). A total of 10 methicillin-resistant S. aureus (MRSA), 3 methicillin-sensitive S. aureus (MSSA) and 6 L. pneumophila isolates were used. The obtained spectra indicated high reproducibility and repeatability with a high signal to noise ratio. Principal component analysis (PCA), hierarchical cluster analysis (HCA), and various supervised classification algorithms were used to discriminate both S. aureus strains and L. pneumophila. Although there were no noteworthy differences between MRSA and MSSA spectra when viewed with the naked eye, some peak intensity ratios such as 732/958, 732/1333, and 732/1450 proved that there could be a significant indicator showing the difference between them. The k-nearest neighbors (kNN) classification algorithm showed superior classification performance with 97.8% accuracy among the traditional classifiers including support vector machine (SVM), decision tree (DT), and naïve Bayes (NB). Our results indicate that SERS combined with machine learning can be used for the detection of antibiotic-resistant and susceptible bacteria and this technique is a very promising tool for clinical applications.

Surface-enhanced Raman scattering (SERS) is a powerful technique for characterization of biological samples. SERS spectra from healthy brain tissue and tumors are obtained by sudden freezing of tissue in liquid nitrogen and crashing and mixing it with a concentrated silver colloidal suspension. The acquired spectra from tissues show significant spectral differences that can be used to identify whether it is from a healthy region or tumor. The most significant change on SERS spectra from the healthy/peripheral brain tissue to tumor is the increase of the ratio of the peaks at around 723 to 655 cm⁻¹. In addition, the spectral changes indicate that the protein content in tumors increases compared to the peripheral/healthy tissue as observed with tumor invasion. The preliminary results show that SERS spectra can be used for a quick diagnosis due to the simplicity of the sample preparation and the speed of the spectral acquisition.