Comparative Analysis of Machine Learning Algorithms on Surface Enhanced Raman Spectra of Clinical Staphylococcus Species

An extensive review on infectious disease diagnosis using machine learning techniques and next generation sequencing: State-of-the-art and perspectives

Infectious diseases, including tuberculosis (TB), HIV/AIDS, and emerging pathogens like COVID-19 pose severe global health challenges due to their rapid spread and significant morbidity and mortality rates. Next-generation sequencing (NGS) and machine learning (ML) have emerged as transformative technologies for enhancing disease diagnosis and management.

OBJECTIVE

This review aims to explore integrating ML techniques with NGS for diagnosing infectious diseases, highlighting their effectiveness and identifying existing challenges.

METHODS

A comprehensive literature review spanning the past decade was conducted using reputable databases, including IEEE Xplore, PubMed, Scopus, SpringerLink, and Science Direct. Research papers, articles, and conference proceedings meeting stringent quality criteria were analysed to assess the performance of ML algorithms applied to NGS and metagenomic NGS (mNGS) data.

RESULTS

The findings reveal that ML algorithms, such as deep neural networks (DNNs), support vector machines (SVM), and K-nearest neighbours (KNN), achieve high accuracy rates, often exceeding 95 %, in diagnosing infectious diseases. Deep learning methods excel in genomic and metagenomic data analysis, while traditional algorithms like Gaussian mixture models (GMM) also demonstrate robust classification capabilities. Challenges include reliance on single data types and difficulty distinguishing closely related pathogens.

CONCLUSION

The integration of ML and NGS significantly advances infectious disease diagnosis, offering rapid and precise detection capabilities. Addressing current limitations can further enhance the effectiveness of these technologies, ultimately improving global public health outcomes.

Comparison of Raman spectroscopy with mass spectrometry for sequence typing of Acinetobacter baumannii strains: a single-center study

The rapid sequence typing (ST) of bacterial strains is crucial for effective nosocomial infection control and mitigating the spread of nosocomial pathogens, e.g., Acinetobacter baumannii. While accurate in identifying A. baumannii strains, current typing methods are often impractical in clinical settings due to their time-consuming nature. This study developed a novel approach, combining surface-enhanced Raman spectroscopy (SERS) with machine-learning (ML) algorithms, to construct predictive models for A. baumannii sequence typing based on SERS spectra. The objective was to assess the feasibility of this integrated method for efficient sequence typing of A. baumannii strains. Clinically isolated A. baumannii strains (N = 267) were collected from a single hospital between 2013 and 2023. Based on multilocus sequence typing, 39 STs of A. baumannii were identified. Then, a SERS spectral database for all these strains was constructed, and predictive models based on eight ML algorithms were developed to predict SERS signals to determine their STs, among which the support vector machine (SVM) model had the best performance (fivefold cross-validation = 99.74%). The typing capacity of the SERS-SVM method was compared with that of matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF) for A. baumannii sequence typing, confirming the superiority of SERS-SVM over MALDI-TOF mass spectrometer. This pilot study lays the groundwork for employing the SERS-ML method to rapidly identify A. baumannii strain types in clinical laboratories, aiding in controlling bacterial pathogen transmission. Further studies are warranted to evaluate its potential in nosocomial surveillance systems, especially for rapidly identifying outbreaks within hospitals.

IMPORTANCE

The rapid and accurate sequence typing (ST) of bacterial pathogens is pivotal in controlling transmission within healthcare settings. Acinetobacter baumannii infection, known for its high transmissibility and drug resistance, presents a major challenge in nosocomial infection control. In this study, surface-enhanced Raman spectroscopy (SERS) was used to differentiate A. baumannii strains with distinct STs based on unique Raman spectral profiles. We then constructed and compared eight machine-learning models on SERS spectra to quickly identify bacterial STs. The results showed that the support vector machine model outperformed matrix-assisted laser desorption/ionization time-of-flight mass spectrometer in determining A. baumannii STs. This approach enables rapid identification of A. baumannii variants with different STs, supporting the early detection and control of nosocomial infections by this multidrug-resistant pathogen.

DeepRaman: Implementing surface-enhanced Raman scattering together with cutting-edge machine learning for the differentiation and classification of bacterial endotoxins

To classify raw SERS Raman spectra from biological materials, we propose DeepRaman, a new architecture inspired by the Progressive Fourier Transform and integrated with the scalogram transformation approach. Unlike standard machine learning approaches such as PCA, LDA, SVM, RF, GBM etc, DeepRaman functions independently, requiring no human interaction, and can be used to much smaller datasets than traditional CNNs. Performance of DeepRaman on 14 endotoxins bacteria and on a public data achieved an extraordinary accuracy of 99 percent. This provides exact endotoxin classification and has tremendous potential for accelerated medical diagnostics and treatment decision-making in cases of pathogenic infections.

Background

Bacterial endotoxin, a lipopolysaccharide exuded by bacteria during their growth and infection process, serves as a valuable biomarker for bacterial identification. It is a vital component of the outer membrane layer in Gram-negative bacteria. By employing silver nanorod-based array substrates, surface-enhanced Raman scattering (SERS) spectra were obtained for two separate datasets: Eleven endotoxins produced by bacteria, each having an 8.75 pg average detection quantity per measurement, and three controls chitin, lipoteichoic acid (LTA), bacterial peptidoglycan (PGN), because their structures differ greatly from those of LPS.

Objective

This study utilized various classical machine learning techniques, such as support vector machines, k-nearest neighbors, and random forests, in conjunction with a modified deep learning approach called DeepRaman. These algorithms were employed to distinguish and categorize bacterial endotoxins, following appropriate spectral pre-processing, which involved novel filtering techniques and advanced feature extraction methods.

Result

Most traditional machine learning algorithms achieved distinction accuracies of over 99 percent, whereas DeepRaman demonstrated an exceptional accuracy of 100 percent. This method offers precise endotoxin classification and holds significant potential for expedited medical diagnoses and therapeutic decision-making in cases of pathogenic infections.

Conclusion

We present the effectiveness of DeepRaman, an innovative architecture inspired by the Progressive Fourier Transform and integrated with the scalogram transformation method, in classifying raw SERS Raman spectral data from biological specimens with unparalleled accuracy relative to conventional machine learning algorithms. Notably, this Convolutional Neural Network (CNN) operates autonomously, requiring no human intervention, and can be applied with substantially smaller datasets than traditional CNNs. Furthermore, it exhibits remarkable proficiency in managing challenging baseline scenarios that often lead to failures in other techniques, thereby promoting the broader clinical adoption of Raman spectroscopy.

Recent Advances in Surface-Enhanced Raman Scattering for Pathogenic Bacteria Detection: A Review

Bacterial infection is one of the common infectious diseases in clinical practice, and the research on efficient detection of bacteria has attracted much attention in recent years. Currently, the traditional detection methods of bacteria are mainly based on cell culturing, microscopic examination, and molecular biology techniques, all of which have the disadvantages of complex operation and time-consuming. Surface-enhanced Raman spectroscopy (SERS) technology has shown prominent advantages in bacterial detection and identification because of the merit of high-sensitivity, fast detection and unique molecular fingerprint spectrum. This paper mainly investigates and discusses the application of SERS in bacterial detection, and systematically reviews the progress of SERS applications, including nano-enhanced dielectric materials of SERS, signal amplification of SERS labeled molecules, and the integration of SERS with microfluidic technology. Finally, the paper analyzes the challenges associated with the application of SERS in bacterial detection and offers insights into future development trends.

Identification of Staphylococcus aureus, Enterococcus faecium, Klebsiella pneumoniae, Pseudomonas aeruginosa and Acinetobacter baumannii from Raman spectra by Artificial Intelligent Raman Detection and Identification System (AIRDIS) with machine learning

BACKGROUND

Rapid and accurate identification of bacteria is required in order to develop effective treatment strategies. Traditional culture-based methods are time-consuming, while MALDI-TOF MS is expensive. The Raman spectroscopy, due to its relatively cost-effectiveness, offers a promising alternative for bacterial identification. However, its clinical utility still requires further validation.

METHODS

In this study, the artificial intelligent Raman detection and identification system (AIRDIS) was implemented to identify bacterial species, including Staphylococcus aureus (n = 1290), Enterococcus faecium (n = 1020), Klebsiella pneumoniae (n = 1366), Pseudomonas aeruginosa (n = 1067), and Acinetobacter baumannii (n = 811). Raman spectra were collected, preprocessed, and analyzed by machine learning (ML).

RESULTS

After training on 24,420 Raman spectra from 1221 isolates and testing on 4333 isolates, the AIRDIS demonstrated an area under the curve (AUC) of 0.99 for Gram classification, with accuracies of 97.64 % for Gram-positive bacteria and 98.86 % for Gram-negative bacteria. Spectral differences between Gram-positive and Gram-negative bacteria were linked to structural variations in their cell walls, such as peptidoglycan and lipopolysaccharides. At the species level, S. aureus, E. faecium, K. pneumoniae, P. aeruginosa, and A. baumannii were identified with high accuracy, ranging from 94.76 % to 96.88 %, with all species achieving an AUC of 0.99.

CONCLUSIONS

Validation with a large number of clinical isolates demonstrated Raman spectroscopy combined with ML excels in identification of five bacterial species associated with multidrug resistance. This finding confirms the clinical utility of the system while laying a solid foundation for the future development of antimicrobial resistance prediction models.

Study of interaction in dual-species biofilm of Candida glabrata and Klebsiella pneumoniae co-isolated from peripheral venous catheter using Raman characterization mapping and machine learning algorithms

Polymicrobial biofilm infections, especially associated with medical devices such as peripheral venous catheters, are challenging in clinical settings for treatment and management. In this study, we examined the mixed biofilm formed by Candida glabrata and Klebsiella pneumoniae, which were co-isolated from the same peripheral venous catheter. Our results revealed that C. glabrata can form mixed biofilms with K. pneumoniae in vitro on peripheral venous catheters and the bottom of microplate wells, as confirmed by scanning electron microscopy. Additionally, using Raman mapping, we showed the distribution of both species in mono- and dual-species biofilms and suggested the type of microbial interaction in this polymicrobial biofilm. Finally, with the assistance of appropriate machine learning (ML) algorithms, based on identified peaks of bacteria, yeast, catheter, and Microplate mapping spectra, we develop a dedicated Raman database to detect the presence of these elements in an unknown spectrum in the future.

Application of Raman Spectroscopy in Non-Invasive Analysis of the Gut Microbiota and Its Impact on Gastrointestinal Health

The gut microbiota, a complex community of microorganisms, plays a crucial role in gastrointestinal (GI) health, influencing digestion, metabolism, immune function, and the gut-brain axis. Dysbiosis, or an imbalance in microbiota composition, is associated with GI disorders, including irritable bowel syndrome (IBS), inflammatory bowel disease (IBD), and colorectal cancer (CRC). Conventional microbiota analysis methods, such as next-generation sequencing (NGS) and nuclear magnetic resonance (NMR), provide valuable insights but are often expensive, time-consuming, and destructive. Raman spectroscopy (RS) is a non-invasive, cost-effective, and highly sensitive alternative. This analytical technique relies on inelastic light scattering to generate molecular "fingerprints", enabling real-time, marker-free analysis of microbiota composition and metabolic activity. This review explores the principles, sample preparation techniques, and advancements in RS, including surface-enhanced Raman spectroscopy (SERS), for microbiota research. RS facilitates identifying microbial species, analysing key metabolites like short-chain fatty acids (SCFA), and monitoring microbiota responses to dietary and therapeutic interventions. The comparative analysis highlights RS's advantages over conventional techniques, such as the minimal sample preparation, real-time capabilities, and non-destructive nature. The integration of RS with machine learning enhances its diagnostic potential, enabling biomarker discovery and personalised treatment strategies for GI disorders. Challenges, including weak Raman signals and spectral complexity, are discussed alongside emerging solutions. As RS technology advances, mainly through portable spectrometers and AI integration, its clinical application in microbiota diagnostics and personalised medicine is poised to transform GI healthcare, bridging microbiota research with practical therapeutic strategies.

Identification of structural stability and fragility of mouse liver glycogen via label-free Raman spectroscopy coupled with convolutional neural network algorithm

Glycogen structure is closely associated with its physiological functions. Previous studies confirmed that liver glycogen structure had two dominant states: mainly stable during the day and largely fragile at night. However, the diurnal change of glycogen structure is impaired, with dominant fragility in diseased conditions such as diabetes mellitus and liver fibrosis. Therefore, the persistent structural fragility of glycogen particles could be a potential molecular-level pathological biomarker for early screening of certain liver diseases. However, the current method for identifying glycogen structural stability and fragility suffers from sophisticated procedures and reliance on expensive instruments, which demands developing novel methods for rapidly discriminating the two types of glycogen particles. This study applied surface-enhanced Raman spectroscopy (SERS) to generate SERS spectra of glycogen samples, revealing distinct structural differences between fragile and stable glycogen particles. Machine learning models were then constructed to predict the structural states of unknown glycogen samples via SERS spectra, according to which the convolutional neural network (CNN) model achieved the best discrimination capacity. Taken together, the SERS technique coupled with the CNN model can identify stable and fragile liver glycogen samples, facilitating the application of glycogen structural fragility as a biomarker in diagnosing liver diseases.

TinyML-Raman: A novel IoT based field-deployable spectra analysis for accurate identification of pharmaceuticals and trace dye-pesticide mixtures from facile SERS method

BACKGROUND

Upcoming inexpensive, compact Internet of Things (IoT) microcontrollers i.e., tiny-machine learning (TinyML) takes the ML driven Raman spectroscopy one step ahead for realization of more affordable and highly compact field deployable instruments. Further, lack of large spectral datasets and need for numerous specialized SERS substrates impede the development of various ML-based surface enhanced Raman spectroscopy (SERS) applications. The aim is to introduce TinyML analysis on wide range of spectra classes using customized dataset obtained with low-cost SERS. In this regard, it is vital to establish an optimum ML model and efficient data handling methodology for low memory TinyML units.

RESULTS

We introduce a novel TinyML methodology for accurate classification of large spectra classes with smartphone assistance for data communication and results visualization. To generate large customized spectral dataset, we present a facile, micro-drop SERS using Au colloids and reusable grooved Al substrates. The results demonstrated that memory efficient 8-bit data quantization based convolutional neural network is effective for accurate identification of 22 different spectra classes of trace dye-pesticide mixtures and pharmaceuticals. In this novel quantized data analysis on significantly varied intensity and complex variation spectra classes i.e., many individual, binary-mixtures and some with varied compositions, data normalization is shown to be powerful for improving ML classification accuracy from about 55 % to >99.5 %. Its robustness is demonstrated using inter-instrument driven data variations such as spectral shifts, high noise, and abscissa-flip, with five-fold cross validation of model performance. In addition, on-site quantification of analyte through spectral intensity is also demonstrated.

SIGNIFICANCE

This study opens up a new approach of ML analysis towards realization of next generation field deployable analytical instruments maintaining data privacy. It presents a detailed procedure of quantized spectral data analysis and its implementation in TinyML, attractive for various users and instrument manufacturers. The presented innovative computer-free ML analysis can be employed in all types of spectrometers, meeting the common goal of Raman spectroscopy i.e., accurate identification of complex spectra classes.

Identification of surface-enhanced Raman spectroscopy using hybrid transformer network

Surface-enhanced Raman Spectroscopy (SERS) is extensively implemented in drug detection due to its sensitivity and non-destructive nature. Deep learning methods, which are represented by convolutional neural network (CNN), have been widely applied in identifying the spectra from SERS for powerful learning ability. However, the local receptive field of CNN limits the feature extraction of sequential spectra for suppressing the analysis results. In this study, a hybrid Transformer network, TMNet, was developed to identify SERS spectra by integrating the Transformer encoder and the multi-layer perceptron. The Transformer encoder can obtain precise feature representations of sequential spectra with the aid of self-attention, and the multi-layer perceptron efficiently transforms the representations to the final identification results. TMNet performed excellently, with identification accuracies of 99.07% for the spectra of hair containing drugs and 97.12% for those of urine containing drugs. For the spectra with additive white Gaussian, baseline background, and mixed noises, TMNet still exhibited the best performance among all the methods. Overall, the proposed method can accurately identify SERS spectra with outstanding noise resistance and excellent generalization and holds great potential for the analysis of other spectroscopy data.

RamanCluster: A deep clustering-based framework for unsupervised Raman spectral identification of pathogenic bacteria

Raman spectroscopy serves as a powerful and reliable tool for the characterization of pathogenic bacteria. The integration of Raman spectroscopy with artificial intelligence techniques to rapidly identify pathogenic bacteria has become paramount for expediting disease diagnosis. However, the development of prevailing supervised artificial intelligence algorithms is still constrained by costly and limited well-annotated Raman spectroscopy datasets. Furthermore, tackling various high-dimensional and intricate Raman spectra of pathogenic bacteria in the absence of annotations remains a formidable challenge. In this paper, we propose a concise and efficient deep clustering-based framework (RamanCluster) to achieve accurate and robust unsupervised Raman spectral identification of pathogenic bacteria without the need for any annotated data. RamanCluster is composed of a novel representation learning module and a machine learning-based clustering module, systematically enabling the extraction of robust discriminative representations and unsupervised Raman spectral identification of pathogenic bacteria. The extensive experimental results show that RamanCluster has achieved high accuracy on both Bacteria-4 and Bacteria-6, with ACC values of 77 % and 74.1 %, NMI values of 75 % and 73 %, as well as AMI values of 74.6 % and 72.6 %, respectively. Furthermore, compared with other state-of-the-art methods, RamanCluster exhibits the superior accuracy on handling various complicated pathogenic bacterial Raman spectroscopy datasets, including situations with strong noise and a wide variety of pathogenic bacterial species. Additionally, RamanCluster also demonstrates commendable robustness in these challenging scenarios. In short, RamanCluster has a promising prospect in accelerating the development of low-cost and widely applicable disease diagnosis in clinical medicine.

From Data to Decisions: Leveraging Artificial Intelligence and Machine Learning in Combating Antimicrobial Resistance - a Comprehensive Review

The emergence of drug-resistant bacteria poses a significant challenge to modern medicine. In response, Artificial Intelligence (AI) and Machine Learning (ML) algorithms have emerged as powerful tools for combating antimicrobial resistance (AMR). This review aims to explore the role of AI/ML in AMR management, with a focus on identifying pathogens, understanding resistance patterns, predicting treatment outcomes, and discovering new antibiotic agents. Recent advancements in AI/ML have enabled the efficient analysis of large datasets, facilitating the reliable prediction of AMR trends and treatment responses with minimal human intervention. ML algorithms can analyze genomic data to identify genetic markers associated with antibiotic resistance, enabling the development of targeted treatment strategies. Additionally, AI/ML techniques show promise in optimizing drug administration and developing alternatives to traditional antibiotics. By analyzing patient data and clinical outcomes, these technologies can assist healthcare providers in diagnosing infections, evaluating their severity, and selecting appropriate antimicrobial therapies. While integration of AI/ML in clinical settings is still in its infancy, advancements in data quality and algorithm development suggest that widespread clinical adoption is forthcoming. In conclusion, AI/ML holds significant promise for improving AMR management and treatment outcome.

Surface-Enhanced Raman Spectroscopy Sensor Integrated with Ag@ZIF-8@Au Core-Shell-Shell Nanowire Membrane for Enrichment, Ultrasensitive Detection, and Inactivation of Bacteria in the Environment

A core-shell-shell sandwich material is developed with silver nanowires as the core, ZIF-8 as an inner shell, and gold nanoparticles as the outer shell, namely, Ag@ZIF-8@Au nanowires (AZA-NW). Then, the synthesized AZA-NW is transformed into a surface-enhanced Raman spectroscopy (SERS) sensor (named M-AZA) by the vacuum filtration method and used to enrich, detect, and inactivate traces of bacteria in the environment. The M-AZA sensor has three main functions: (1) trace bacteria are effectively enriched, with an enrichment efficiency of 91.4%; (2) ultrasensitive detection of trace bacteria is realized, with a minimum detectable concentration of 1 × 101 CFU/mL; (3) bacteria are effectively killed up to 92.4%. The shell thickness of ZIF-8 (5-75 nm) is controlled by adjusting the synthesis conditions. At an optimum shell thickness of 15 nm, the effect of gold nanoparticles and ZIF-8 shell on the sensor's stability, SERS activity, and antibacterial performance is investigated. The simulation of the SERS sensor using the finite difference time domain (FDTD) method is consistent with the experimental results, theoretically demonstrating the role of the gold nanoparticles and the ZIF-8 shell. The sensor also shows excellent stability, safety, and generalizability. The campus water sample is then tested on-site by the M-AZA SERS sensor, indicating its potential for practical applications.

High-performance grating-like SERS substrate based on machine learning for ultrasensitive detection of Zexie-Baizhu decoction

Rapid, universal and accurate identification of chemical composition changes in multi-component traditional Chinese medicine (TCM) decoction is a necessary condition for elucidating the effectiveness and mechanism of pharmacodynamic substances in TCM. In this paper, SERS technology, combined with grating-like SERS substrate and machine learning method, was used to establish an efficient and sensitive method for the detection of TCM decoction. Firstly, the grating-like substrate prepared by magnetron sputtering technology was served as a reliable SERS sensor for the identification of TCM decoction. The enhancement factor (EF) of 4-ATP probe molecules was as high as 1.90 × 107 and the limit of detection (LOD) was as low as 1 × 10-10 M. Then, SERS technology combined with support vector machine (SVM), decision tree (DT), Naive Bayes (NB) and other machine learning algorithms were used to classify and identify the three TCM decoctions, and the classification accuracy rate was as high as 97.78 %. In summary, it is expected that the proposed method combining SERS and machine learning method will have a high development in the practical application of multi-component analytes in TCM.

Identification of Mycobacterium tuberculosis Resistance to Common Antibiotics: An Overview of Current Methods and Techniques

Multidrug-resistant tuberculosis (MDR-TB) is an essential cause of tuberculosis treatment failure and death of tuberculosis patients. The rapid and reliable profiling of Mycobacterium tuberculosis (MTB) drug resistance in the early stage is a critical research area for public health. Then, most traditional approaches for detecting MTB are time-consuming and costly, leading to the inappropriate therapeutic schedule resting on the ambiguous information of MTB drug resistance, increasing patient economic burden, morbidity, and mortality. Therefore, novel diagnosis methods are frequently required to meet the emerging challenges of MTB drug resistance distinguish. Considering the difficulty in treating MDR-TB, it is urgently required for the development of rapid and accurate methods in the identification of drug resistance profiles of MTB in clinical diagnosis. This review discussed recent advances in MTB drug resistance detection, focusing on developing emerging approaches and their applications in tangled clinical situations. In particular, a brief overview of antibiotic resistance to MTB was present, referred to as intrinsic bacterial resistance, consisting of cell wall barriers and efflux pumping action and acquired resistance caused by genetic mutations. Then, different drug susceptibility test (DST) methods were described, including phenotype DST, genotype DST and novel DST methods. The phenotype DST includes nitrate reductase assay, RocheTM solid ratio method, and liquid culture method and genotype DST includes fluorescent PCR, GeneXpert, PCR reverse dot hybridization, ddPCR, next-generation sequencing and gene chips. Then, novel DST methods were described, including metabolism testing, cell-free DNA probe, CRISPR assay, and spectral analysis technique. The limitations, challenges, and perspectives of different techniques for drug resistance are also discussed. These methods significantly improve the detection sensitivity and accuracy of multidrug-resistant tuberculosis (MRT) and can effectively curb the incidence of drug-resistant tuberculosis and accelerate the process of tuberculosis eradication.

Rapid discrimination of four Salmonella enterica serovars: A performance comparison between benchtop and handheld Raman spectrometers

Foodborne illnesses, particularly those caused by Salmonella enterica with its extensive array of over 2600 serovars, present a significant public health challenge. Therefore, prompt and precise identification of S. enterica serovars is essential for clinical relevance, which facilitates the understanding of S. enterica transmission routes and the determination of outbreak sources. Classical serotyping methods via molecular subtyping and genomic markers currently suffer from various limitations, such as labour intensiveness, time consumption, etc. Therefore, there is a pressing need to develop new diagnostic techniques. Surface-enhanced Raman spectroscopy (SERS) is a non-invasive diagnostic technique that can generate Raman spectra, based on which rapid and accurate discrimination of bacterial pathogens could be achieved. To generate SERS spectra, a Raman spectrometer is needed to detect and collect signals, which are divided into two types: the expensive benchtop spectrometer and the inexpensive handheld spectrometer. In this study, we compared the performance of two Raman spectrometers to discriminate four closely associated S. enterica serovars, that is, S. enterica subsp. enterica serovar dublin, enteritidis, typhi and typhimurium. Six machine learning algorithms were applied to analyse these SERS spectra. The support vector machine (SVM) model showed the highest accuracy for both handheld (99.97%) and benchtop (99.38%) Raman spectrometers. This study demonstrated that handheld Raman spectrometers achieved similar prediction accuracy as benchtop spectrometers when combined with machine learning models, providing an effective solution for rapid, accurate and cost-effective identification of closely associated S. enterica serovars.

Recent advances in surface enhanced Raman spectroscopy for bacterial pathogen identifications

BACKGROUND

The rapid and reliable detection of pathogenic bacteria at an early stage is a highly significant research field for public health. However, most traditional approaches for pathogen identification are time-consuming and labour-intensive, which may cause physicians making inappropriate treatment decisions based on an incomplete diagnosis of patients with unknown infections, leading to increased morbidity and mortality. Therefore, novel methods are constantly required to face the emerging challenges of bacterial detection and identification. In particular, Raman spectroscopy (RS) is becoming an attractive method for rapid and accurate detection of bacterial pathogens in recent years, among which the newly developed surface-enhanced Raman spectroscopy (SERS) shows the most promising potential.

AIM OF REVIEW

Recent advances in pathogen detection and diagnosis of bacterial infections were discussed with focuses on the development of the SERS approaches and its applications in complex clinical settings.

KEY SCIENTIFIC CONCEPTS OF REVIEW

The current review describes bacterial classification using surface enhanced Raman spectroscopy (SERS) for developing a rapid and more accurate method for the identification of bacterial pathogens in clinical diagnosis. The initial part of this review gives a brief overview of the mechanism of SERS technology and development of the SERS approach to detect bacterial pathogens in complex samples. The development of the label-based and label-free SERS strategies and several novel SERS-compatible technologies in clinical applications, as well as the analytical procedures and examples of chemometric methods for SERS, are introduced. The computational challenges of pre-processing spectra and the highlights of the limitations and perspectives of the SERS technique are also discussed.Taken together, this systematic review provides an overall summary of the SERS technique and its application potential for direct bacterial diagnosis in clinical samples such as blood, urine and sputum, etc.

Unraveling surface-enhanced Raman spectroscopy results through chemometrics and machine learning: principles, progress, and trends

Surface-enhanced Raman spectroscopy (SERS) has gained increasing attention because it provides rich chemical information and high sensitivity, being applicable in many scientific fields including medical diagnosis, forensic analysis, food control, and microbiology. Although SERS is often limited by the lack of selectivity in the analysis of samples with complex matrices, the use of multivariate statistics and mathematical tools has been demonstrated to be an efficient strategy to circumvent this issue. Importantly, since the rapid development of artificial intelligence has been promoting the implementation of a wide variety of advanced multivariate methods in SERS, a discussion about the extent of their synergy and possible standardization becomes necessary. This critical review comprises the principles, advantages, and limitations of coupling SERS with chemometrics and machine learning for both qualitative and quantitative analytical applications. Recent advances and trends in combining SERS with uncommonly used but powerful data analysis tools are also discussed. Finally, a section on benchmarking and tips for selecting the suitable chemometric/machine learning method is included. We believe this will help to move SERS from an alternative detection strategy to a general analytical technique for real-life applications.

Detection of 1-OHPyr in human urine using SERS with injection under wet liquid-liquid self-assembled films of β-CD-coated gold nanoparticles and deep learning

1-Hydroxypyrene (1-OHPyr), a typical hydroxylated polycyclic aromatic hydrocarbon (OH-PAH), has been commonly regarded as a urinary biomarker for assessing human exposure and health risks of PAHs. Herein, a fast and sensitive method was developed for the determination of 1-OHPyr in urine using surface-enhanced Raman spectroscopy (SERS) combined with deep learning (DL). After emulsification, urinary 1-OHPyr was separated using simple liquid-liquid extraction. Gold nanoparticles with β-cyclodextrin (β-CD@AuNPs) were synthesized, and homogeneous and ordered β-CD@AuNP films were prepared through a liquid-liquid interface self-assembly process. The separated 1-OHPyr was injected under wet assembled films for SERS detection. Concentration as low as 0.05 μg mL^-1 of 1-OHPyr in urine could still be detected, and the relative standard deviation was 5.5 %, and this was ascribed to the adsorption of β-CD and the high-probability contact between 1-OHPyr molecules and the nanogap of assembled films under the action of capillary force. Meanwhile, a convolutional neural network (CNN), a classical DL network architecture, was adopted to build the prediction model, and the model was further simplified by genetic algorithm (GA). CNN combined with a GA obtained optimized results with determination coefficient and a root mean square error of prediction sets of 0.9639 and 0.6327, respectively, outperforming other models. Overall, the proposed method achieves fast and accurate detection of 1-OHPyr in urine, improves the assessment human exposure to PAHs and is expected to have applications in the analysis of other OH-PAHs in complex environments.

Evaluation of the antibacterial activity of gallic acid anchored phthalocyanine-doped silica nanoparticles towards Escherichia coli and Staphylococcus aureus biofilms and planktonic cells

In this work, we have described the synthesis of phthalocyanine complexes Zn(II) tetrakis 4-(5-formylpyridin-2-yl)oxy) phthalocyanine (2), Zn(II) tetrakis-1-butyl-4-(2-(6- (tetra-phenoxy)pyridin-3-yl) vinyl)pyridin-1-ium phthalocyanine (3) and Zn(II) tetrakis 1-butyl-5-(2-(1-butylpyridin-1-ium-4-yl)vinyl)-2-(tetra-phenoxy)pyridin-1-ium phthalocyanine (4). The effect of a varying number of charges when the Pc complexes are alone or grafted in gallic acid (GA) tagged silica nanoparticles on photodynamic antimicrobial chemotherapy (PACT) is investigated toward Staphylococcus aureus (S.aureus) and Escherichia coli (E.coli) in both planktonic and biofilm forms. Complex 4, bearing a total of 8 cationic charges, displayed the highest activity with log CFU values of 8.60 and 6.42 against E.coli and S.aureus biofilms, respectively. The surface stability of E.coli and S.aureus biofilms in the presence of 4 and its conjugate was analysed using cyclic voltammetry. Scanning electron microscopy (SEM) and Raman spectra are also used to study the conformational and biochemical changes within biofilm upon subjecting them to PACT.

Rapid discrimination of Shigella spp. and Escherichia coli via label-free surface enhanced Raman spectroscopy coupled with machine learning algorithms

Shigella and enterotoxigenic Escherichia coli (ETEC) are major bacterial pathogens of diarrheal disease that is the second leading cause of childhood mortality globally. Currently, it is well known that Shigella spp., and E. coli are very closely related with many common characteristics. Evolutionarily speaking, Shigella spp., are positioned within the phylogenetic tree of E. coli. Therefore, discrimination of Shigella spp., from E. coli is very difficult. Many methods have been developed with the aim of differentiating the two species, which include but not limited to biochemical tests, nucleic acids amplification, and mass spectrometry, etc. However, these methods suffer from high false positive rates and complicated operation procedures, which requires the development of novel methods for accurate and rapid identification of Shigella spp., and E. coli. As a low-cost and non-invasive method, surface enhanced Raman spectroscopy (SERS) is currently under intensive study for its diagnostic potential in bacterial pathogens, which is worthy of further investigation for its application in bacterial discrimination. In this study, we focused on clinically isolated E. coli strains and Shigella species (spp.), that is, S. dysenteriae, S. boydii, S. flexneri, and S. sonnei, based on which SERS spectra were generated and characteristic peaks for Shigella spp., and E. coli were identified, revealing unique molecular components in the two bacterial groups. Further comparative analysis of machine learning algorithms showed that, the Convolutional Neural Network (CNN) achieved the best performance and robustness in bacterial discrimination capacity when compared with Random Forest (RF) and Support Vector Machine (SVM) algorithms. Taken together, this study confirmed that SERS paired with machine learning could achieve high accuracy in discriminating Shigella spp., from E. coli, which facilitated its application potential for diarrheal prevention and control in clinical settings.

Rapid Prediction of Multidrug-Resistant Klebsiella pneumoniae through Deep Learning Analysis of SERS Spectra

Klebsiella pneumoniae is listed by the WHO as a priority pathogen of extreme importance that can cause serious consequences in clinical settings. Due to its increasing multidrug resistance all over the world, K. pneumoniae has the potential to cause extremely difficult-to-treat infections. Therefore, rapid and accurate identification of multidrug-resistant K. pneumoniae in clinical diagnosis is important for its prevention and infection control. However, the limitations of conventional and molecular methods significantly hindered the timely diagnosis of the pathogen. As a label-free, noninvasive, and low-cost method, surface-enhanced Raman scattering (SERS) spectroscopy has been extensively studied for its application potentials in the diagnosis of microbial pathogens. In this study, we isolated and cultured 121 K. pneumoniae strains from clinical samples with different drug resistance profiles, which included polymyxin-resistant K. pneumoniae (PRKP; n = 21), carbapenem-resistant K. pneumoniae, (CRKP; n = 50), and carbapenem-sensitive K. pneumoniae (CSKP; n = 50). For each strain, a total of 64 SERS spectra were generated for the enhancement of data reproducibility, which were then computationally analyzed via the convolutional neural network (CNN). According to the results, the deep learning model CNN plus attention mechanism could achieve a prediction accuracy as high as 99.46%, with robustness score of 5-fold cross-validation at 98.87%. Taken together, our results confirmed the accuracy and robustness of SERS spectroscopy in the prediction of drug resistance of K. pneumoniae strains with the assistance of deep learning algorithms, which successfully discriminated and predicted PRKP, CRKP, and CSKP strains. IMPORTANCE This study focuses on the simultaneous discrimination and prediction of Klebsiella pneumoniae strains with carbapenem-sensitive, carbapenem-resistant, and polymyxin-resistant phenotypes. The implementation of CNN plus an attention mechanism makes the highest prediction accuracy at 99.46%, which confirms the diagnostic potential of the combination of SERS spectroscopy with the deep learning algorithm for antibacterial susceptibility testing in clinical settings.

Advances in surface-enhanced Raman spectroscopy technology for detection of foodborne pathogens

Rapid control and prevention of diseases caused by foodborne pathogens is one of the existing food safety regulatory issues faced by various countries and has received wide attention from all sectors of society. The development of rapid and reliable detection methods for foodborne pathogens remains a hot research area for food safety and public health because of the limitations of complex steps, time-consuming, low sensitivity, or poor selectivity of commonly used methods. Surface-enhanced Raman spectroscopy (SERS), as a novel spectroscopic technique, has the advantages of high sensitivity, selectivity, rapid and nondestructive detection and has exhibited broad application prospects in the determination of pathogenic bacteria. In this study, the enhancement mechanisms of SERS are briefly introduced, then the characteristics and properties of liquid-phase, rigid solid-phase, and flexible solid-phase are categorized. Furthermore, a comprehensive review of the advances in label-free or label-based SERS strategies and SERS-compatible techniques for the detection of foodborne pathogens is provided, and the advantages and disadvantages of these methods are reviewed. Finally, the current challenges of SERS technology applied in practical applications are listed, and the possible development trends of SERS in the field of foodborne pathogens detection in the future are discussed.

Raman spectroscopy combined with deep learning for rapid detection of melanoma at the single cell level

Melanoma is an aggressive and metastatic skin cancer caused by genetic mutations in melanocytes, and its incidence is increasing year by year. Understanding the gene mutation information of melanoma cases is very important for its precise treatment. The current diagnostic methods for melanoma include radiological, pharmacological, histological, cytological and molecular techniques, but the gold standard for diagnosis is still pathological biopsy, which is time consuming and destructive. Raman spectroscopy is a rapid, sensitive and nondestructive detection method. In this study, a total of 20,000 Surface-enhanced Raman scattering (SERS) spectra of melanocytes and melanoma cells were collected using a positively charged gold nanoparticles planar solid SERS substrate, and a classification network system based on convolutional neural networks (CNN) was constructed to achieve the classification of melanocytes and melanoma cells, wild-type and mutant melanoma cells and their drug resistance. Among them, the classification accuracy of melanocytes and melanoma cells was over 98%. Raman spectral differences between melanocytes and melanoma cells were analyzed and compared, and the response of cells to antitumor drugs were also evaluated. The results showed that Raman spectroscopy provided a basis for the medication of melanoma, and SERS spectra combined with CNN classification model realized classification of melanoma, which is of great significance for rapid diagnosis and identification of melanoma.

Machine learning-augmented surface-enhanced spectroscopy toward next-generation molecular diagnostics

The world today is witnessing the significant role and huge demand for molecular detection and screening in healthcare and medical diagnosis, especially during the outbreak of COVID-19. Surface-enhanced spectroscopy techniques, including Surface-Enhanced Raman Scattering (SERS) and Infrared Absorption (SEIRA), provide lattice and molecular vibrational fingerprint information which is directly linked to the molecular constituents, chemical bonds, and configuration. These properties make them an unambiguous, nondestructive, and label-free toolkit for molecular diagnostics and screening. However, new issues in molecular diagnostics, such as increasing molecular species, faster spread of viruses, and higher requirements for detection accuracy and sensitivity, have brought great challenges to detection technology. Advancements in artificial intelligence and machine learning (ML) techniques show promising potential in empowering SERS and SEIRA with rapid analysis and automatic data processing to jointly tackle the challenge. This review introduces the combination of ML and SERS/SEIRA by investigating how ML algorithms can be beneficial to SERS/SEIRA, discussing the general process of combining ML and SEIRA/SERS, highlighting the molecular diagnostics and screening applications based on ML-combined SEIRA/SERS, and providing perspectives on the future development of ML-integrated SEIRA/SERS. In general, this review offers comprehensive knowledge about the recent advances and the future outlook regarding ML-integrated SEIRA/SERS for molecular diagnostics and screening.

SERS-Based Biosensors Combined with Machine Learning for Medical Application

Surface-enhanced Raman spectroscopy (SERS) has shown strength in non-invasive, rapid, trace analysis and has been used in many fields in medicine. Machine learning (ML) is an algorithm that can imitate human learning styles and structure existing content with the knowledge to effectively improve learning efficiency. Integrating SERS and ML can have a promising future in the medical field. In this review, we summarize the applications of SERS combined with ML in recent years, such as the recognition of biological molecules, rapid diagnosis of diseases, developing of new immunoassay techniques, and enhancing SERS capabilities in semi-quantitative measurements. Ultimately, the possible opportunities and challenges of combining SERS with ML are addressed.

Nanomaterials meet surface-enhanced Raman scattering towards enhanced clinical diagnosis: a review

Surface-enhanced Raman scattering (SERS) is a very promising tool for the direct detection of biomarkers for the diagnosis of i.e., cancer and pathogens. Yet, current SERS strategies are hampered by non-specific interactions with co-existing substances in the biological matrices and the difficulties of obtaining molecular fingerprint information from the complex vibrational spectrum. Raman signal enhancement is necessary, along with convenient surface modification and machine-based learning to address the former issues. This review aims to describe recent advances and prospects in SERS-based approaches for cancer and pathogens diagnosis. First, direct SERS strategies for key biomarker sensing, including the use of substrates such as plasmonic, semiconductor structures, and 3D order nanostructures for signal enhancement will be discussed. Secondly, we will illustrate recent advances for indirect diagnosis using active nanomaterials, Raman reporters, and specific capture elements as SERS tags. Thirdly, critical challenges for translating the potential of the SERS sensing techniques into clinical applications via machine learning and portable instrumentation will be described. The unique nature and integrated sensing capabilities of SERS provide great promise for early cancer diagnosis or fast pathogens detection, reducing sanitary costs but most importantly allowing disease prevention and decreasing mortality rates.

Identification of Bacterial Pathogens at Genus and Species Levels through Combination of Raman Spectrometry and Deep-Learning Algorithms

The rapid and accurate identification of the causing agents during bacterial infections would greatly improve pathogen transmission, prevention, patient care, and medical treatments in clinical settings. Although many conventional and molecular methods have been proven to be efficient and reliable, some of them suffer technical biases and limitations that require the development and application of novel and advanced techniques. Recently, due to its cost affordability, noninvasiveness, and label-free feature, Raman spectroscopy (RS) is emerging as a potential technique for fast bacterial detection. However, the method is still hampered by many technical issues, such as low signal intensity, poor reproducibility, and standard data set insufficiency, among others. Thus, it should be cautiously claimed that Raman spectroscopy could provide practical applications in real-world settings. In order to evaluate the implementation potentials of Raman spectroscopy in the identification of bacterial pathogens, we investigated 30 bacterial species belonging to 9 different bacterial genera that were isolated from clinical samples via surfaced enhanced Raman spectroscopy (SERS). A total of 17,149 SERS spectra were harvested from a Raman spectrometer and were further analyzed via machine learning approaches, which showed that a convolutional neural network (CNN) deep learning algorithm achieved the highest prediction accuracy for recognizing pathogenic bacteria at both the genus and species levels. In summary, the SERS technique holds a promising potential for fast bacterial pathogen identification in clinical laboratories with the integration of machine learning algorithms, which might be further developed and sharpened for the direct identification and prediction of bacterial pathogens from clinical samples. IMPORTANCE In this study, we investigated 30 bacterial species belonging to 9 different bacterial genera that were isolated from clinical samples via surfaced enhanced Raman spectroscopy (SERS). A total of 17,149 SERS spectra were harvested from a Raman spectrometer and were further analyzed via machine learning approaches, the results of which showed that the convolutional neural network (CNN) deep learning algorithm could achieve the highest prediction accuracy for recognizing pathogenic bacteria at both the genus and species levels. Taken together, we concluded that the SERS technique held a promising potential for fast bacterial pathogen diagnosis in clinical laboratories with the integration of deep learning algorithms, which might be further developed and sharpened for the direct identification and prediction of bacterial pathogens from clinical samples.

Recent Progress in the Diagnosis of Staphylococcus in Clinical Settings

Staphylococci are mainly found on the skin or in the nose. These bacteria are typically friendly, causing no harm to healthy individuals or resulting in only minor issues that can go away on their own. However, under certain circumstances, staphylococcal bacteria could invade the bloodstream, affect the entire body, and lead to life-threatening problems like septic shock. In addition, antibiotic-resistant Staphylococcus is another issue because of its difficulty in the treatment of infections, such as the notorious methicillin-resistant Staphylococcus aureus (MRSA) which is resistant to most of the currently known antibiotics. Therefore, rapid and accurate diagnosis of Staphylococcus and characterization of the antibiotic resistance profiles are essential in clinical settings for efficient prevention, control, and treatment of the bacteria. This chapter highlights recent advances in the diagnosis of Staphylococci in clinical settings with a focus on the advanced technique of surface-enhanced Raman spectroscopy (SERS), which will provide a framework for the real-world applications of novel diagnostic techniques in medical laboratories via bench-top instruments and at the bedside through point-of-care devices.

Application of Microfluidics for Bacterial Identification

Bacterial infections continue to pose serious public health challenges. Though anti-bacterial therapeutics are effective remedies for treating these infections, the emergence of antibiotic resistance has imposed new challenges to treatment. Often, there is a delay in prescribing antibiotics at initial symptom presentation as it can be challenging to clinically differentiate bacterial infections from other organisms (e.g., viruses) causing infection. Moreover, bacterial infections can arise from food, water, or other sources. These challenges have demonstrated the need for rapid identification of bacteria in liquids, food, clinical spaces, and other environments. Conventional methods of bacterial identification rely on culture-based approaches which require long processing times and higher pathogen concentration thresholds. In the past few years, microfluidic devices paired with various bacterial identification methods have garnered attention for addressing the limitations of conventional methods and demonstrating feasibility for rapid bacterial identification with lower biomass thresholds. However, such culture-free methods often require integration of multiple steps from sample preparation to measurement. Research interest in using microfluidic methods for bacterial identification is growing; therefore, this review article is a summary of current advancements in this field with a focus on comparing the efficacy of polymerase chain reaction (PCR), loop-mediated isothermal amplification (LAMP), and emerging spectroscopic methods.

Machine Learning Enhanced Optical Spectroscopy for Disease Detection

Optical spectroscopy plays an important role in disease detection. Improving the sensitivity and specificity of spectral detection has great importance in the development of accurate diagnosis. The development of artificial intelligence technology provides a great opportunity to improve the detection accuracy through machine learning methods. In this Perspective, we focus on the combination of machine learning methods with the optical spectroscopy methods widely used for disease detection, including absorbance, fluorescence, scattering, FTIR, terahertz, etc. By comparing the spectral analysis with different machine learning methods, we illustrate that the support vector machine and convolutional neural network are most effective, which have potential to further improve the classification accuracy to distinguish disease subtypes if these machine learning methods are used. This Perspective broadens the scope of optical spectroscopy enhanced by machine learning and will be useful for the development of disease detection.

Rapid discrimination of glycogen particles originated from different eukaryotic organisms

There are many commercially available glycogen particles in the market due to their bioactive functions as food additive, drug carrier and natural moisturizer, etc. It would be beneficial to rapidly determine the origins of commercially-available glycogen particles, which could facilitate the establishment of quality control methodology for glycogen-containing products. With its non-destructive, label-free and low-cost features, surface enhanced Raman spectroscopy (SERS) is an attractive technique with high potential to discriminate chemical compounds in a rapid mode. In this study, we applied the combination of SERS technique and machine leaning algorithms on glycogen analysis, which successfully predicted the origins of glycogen particles from a variety of organisms with convolutional neural network (CNN) algorithm plus attention mechanism having the best computational performance (5-fold cross validation accuracy = 96.97 %). In sum, this is the first study focusing on the discrimination of commercial glycogen particles originated from different organisms, which holds the application potential in quality control of glycogen-containing products.

Analysis and comparison of machine learning methods for blood identification using single-cell laser tweezer Raman spectroscopy

Raman spectroscopy, a "fingerprint" spectrum of substances, can be used to characterize various biological and chemical samples. To allow for blood classification using single-cell Raman spectroscopy, several machine learning algorithms were implemented and compared. A single-cell laser optical tweezer Raman spectroscopy system was established to obtain the Raman spectra of red blood cells. The Boruta algorithm extracted the spectral feature frequency shift, reduced the spectral dimension, and determined the essential features that affect classification. Next, seven machine learning classification models are analyzed and compared based on the classification accuracy, precision, and recall indicators. The results show that support vector machines and artificial neural networks are the two most appropriate machine learning algorithms for single-cell Raman spectrum blood classification, and this finding provides essential guidance for future research studies.

Analyzing the serum of hemodialysis patients with end-stage chronic kidney disease by means of the combination of SERS and machine learning

The aim of this paper is a multivariate analysis of SERS characteristics of serum in hemodialysis patients, which includes constructing classification models (PLS-DA, CNN) by the presence/absence of end-stage chronic kidney disease (CKD) with dialysis and determining the most informative spectral bands for identifying dialysis patients by variable importance distribution. We found the spectral bands that are informative for detecting the hemodialysis patients: the 641 cm^-1, 724 cm^-1, 1094 cm^-1 and 1393 cm^-1 bands are associated with the degree of kidney function inhibition; and the 1001 cm^-1 band is able to demonstrate the distinctive features of hemodialysis patients with end-stage CKD.

Highly Accurate Identification of Bacteria's Antibiotic Resistance Based on Raman Spectroscopy and U-Net Deep Learning Algorithms

Bacterial pathogens especially antibiotic-resistant ones are a public health concern worldwide. To oppose the morbidity and mortality associated with them, it is critical to select an appropriate antibiotic by performing a rapid bacterial diagnosis. Using a combination of Raman spectroscopy and deep learning algorithms to identify bacteria is a rapid and reliable method. Nevertheless, due to the loss of information during training a model, some deep learning algorithms suffer from low accuracy. Herein, we modify the U-Net architecture to fit our purpose of classifying the one-dimensional Raman spectra. The proposed U-Net model provides highly accurate identification of the 30 isolates of bacteria and yeast, empiric treatment groups, and antimicrobial resistance, thanks to its capability to concatenate and copy important features from the encoder layers to the decoder layers, thereby decreasing the data loss. The accuracies of the model for the 30-isolate level, empiric treatment level, and antimicrobial resistance level tasks are 86.3, 97.84, and 95%, respectively. The proposed deep learning model has a high potential for not only bacterial identification but also for other diagnostic purposes in the biomedical field.

In situ identification of environmental microorganisms with Raman spectroscopy

Microorganisms in natural environments are crucial in maintaining the material and energy cycle and the ecological balance of the environment. However, it is challenging to delineate environmental microbes' actual metabolic pathways and intraspecific heterogeneity because most microorganisms cannot be cultivated. Raman spectroscopy is a culture-independent technique that can collect molecular vibration profiles from cells. It can reveal the physiological and biochemical information at the single-cell level rapidly and non-destructively in situ. The first part of this review introduces the principles, advantages, progress, and analytical methods of Raman spectroscopy applied in environmental microbiology. The second part summarizes the applications of Raman spectroscopy combined with stable isotope probing (SIP), fluorescence in situ hybridization (FISH), Raman-activated cell sorting and genomic sequencing, and machine learning in microbiological studies. Finally, this review discusses expectations of Raman spectroscopy and future advances to be made in identifying microorganisms, especially for uncultured microorganisms.

Classification of skin cancer using convolutional neural networks analysis of Raman spectra

BACKGROUND AND OBJECTIVE

Skin cancer is the most common malignancy in whites accounting for about one third of all cancers diagnosed per year. Portable Raman spectroscopy setups for skin cancer "optical biopsy" are utilized to detect tumors based on their spectral features caused by the comparative presence of different chemical components. However, low signal-to-noise ratio in such systems may prevent accurate tumors classification. Thus, there is a challenge to develop methods for efficient skin tumors classification.

METHODS

We compare the performance of convolutional neural networks and the projection on latent structures with discriminant analysis for discriminating skin cancer using the analysis of Raman spectra with a high autofluorescence background stimulated by a 785 nm laser. We have registered the spectra of 617 cases of skin neoplasms (615 patients, 70 melanomas, 122 basal cell carcinomas, 12 squamous cell carcinomas and 413 benign tumors) in vivo with a portable Raman setup and created classification models both for convolutional neural networks and projection on latent structures approaches. To check the classification models stability, a 10-fold cross-validation was performed for all created models. To avoid models overfitting, the data was divided into a training set (80% of spectral dataset) and a test set (20% of spectral dataset).

RESULTS

The results for different classification tasks demonstrate that the convolutional neural networks significantly (p<0.01) outperforms the projection on latent structures. For the convolutional neural networks implementation we obtained ROC AUCs of 0.96 (0.94 - 0.97; 95% CI), 0.90 (0.85-0.94; 95% CI), and 0.92 (0.87 - 0.97; 95% CI) for classifying a) malignant vs benign tumors, b) melanomas vs pigmented tumors and c) melanomas vs seborrheic keratosis respectively.

CONCLUSIONS

The performance of the convolutional neural networks classification of skin tumors based on Raman spectra analysis is higher or comparable to the accuracy provided by trained dermatologists. The increased accuracy with the convolutional neural networks implementation is due to a more precise accounting of low intensity Raman bands in the intense autofluorescence background. The achieved high performance of skin tumors classifications with convolutional neural networks analysis opens a possibility for wide implementation of Raman setups in clinical setting.

Rapid Discrimination of Clinically Important Pathogens Through Machine Learning Analysis of Surface Enhanced Raman Spectra

With its low-cost, label-free and non-destructive features, Raman spectroscopy is becoming an attractive technique with high potential to discriminate the causative agent of bacterial infections and bacterial infections per se. However, it is challenging to achieve consistency and accuracy of Raman spectra from numerous bacterial species and phenotypes, which significantly hinders the practical application of the technique. In this study, we analyzed surfaced enhanced Raman spectra (SERS) through machine learning algorithms in order to discriminate bacterial pathogens quickly and accurately. Two unsupervised machine learning methods, K-means Clustering (K-Means) and Agglomerative Nesting (AGNES) were performed for clustering analysis. In addition, eight supervised machine learning methods were compared in terms of bacterial predictions via Raman spectra, which showed that convolutional neural network (CNN) achieved the best prediction accuracy (99.86%) with the highest area (0.9996) under receiver operating characteristic curve (ROC). In sum, machine learning methods can be potentially applied to classify and predict bacterial pathogens via Raman spectra at general level.

Prospects of Surface-Enhanced Raman Spectroscopy for Biomarker Monitoring toward Precision Medicine

Future precision medicine will be undoubtedly sustained by the detection of validated biomarkers that enable a precise classification of patients based on their predicted disease risk, prognosis, and response to a specific treatment. Up to now, genomics, transcriptomics, and immunohistochemistry have been the main clinically amenable tools at hand for identifying key diagnostic, prognostic, and predictive biomarkers. However, other molecular strategies, including metabolomics, are still in their infancy and require the development of new biomarker detection technologies, toward routine implementation into clinical diagnosis. In this context, surface-enhanced Raman scattering (SERS) spectroscopy has been recognized as a promising technology for clinical monitoring thanks to its high sensitivity and label-free operation, which should help accelerate the discovery of biomarkers and their corresponding screening in a simpler, faster, and less-expensive manner. Many studies have demonstrated the excellent performance of SERS in biomedical applications. However, such studies have also revealed several variables that should be considered for accurate SERS monitoring, in particular, when the signal is collected from biological sources (tissues, cells or biofluids). This Perspective is aimed at piecing together the puzzle of SERS in biomarker monitoring, with a view on future challenges and implications. We address the most relevant requirements of plasmonic substrates for biomedical applications, as well as the implementation of tools from artificial intelligence or biotechnology to guide the development of highly versatile sensors.

Discrimination between Carbapenem-Resistant and Carbapenem-Sensitive Klebsiella pneumoniae Strains through Computational Analysis of Surface-Enhanced Raman Spectra: a Pilot Study

In clinical settings, rapid and accurate diagnosis of antibiotic resistance is essential for the efficient treatment of bacterial infections. Conventional methods for antibiotic resistance testing are time consuming, while molecular methods such as PCR-based testing might not accurately reflect phenotypic resistance. Thus, fast and accurate methods for the analysis of bacterial antibiotic resistance are in high demand for clinical applications. In this pilot study, we isolated 7 carbapenem-sensitive Klebsiella pneumoniae (CSKP) strains and 8 carbapenem-resistant Klebsiella pneumoniae (CRKP) strains from clinical samples. Surface-enhanced Raman spectroscopy (SERS) as a label-free and noninvasive method was employed for discriminating CSKP strains from CRKP strains through computational analysis. Eight supervised machine learning algorithms were applied for sample analysis. According to the results, all supervised machine learning methods could successfully predict carbapenem sensitivity and resistance in K. pneumoniae, with a convolutional neural network (CNN) algorithm on top of all other methods. Taken together, this pilot study confirmed the application potentials of surface-enhanced Raman spectroscopy in fast and accurate discrimination of Klebsiella pneumoniae strains with different antibiotic resistance profiles. IMPORTANCE With the low-cost, label-free, and nondestructive features, Raman spectroscopy is becoming an attractive technique with great potential to discriminate bacterial infections. In this pilot study, we analyzed surfaced-enhanced Raman spectroscopy (SERS) spectra via supervised machine learning algorithms, through which we confirmed the application potentials of the SERS technique in rapid and accurate discrimination of Klebsiella pneumoniae strains with different antibiotic resistance profiles.

Machine learning analysis of SERS fingerprinting for the rapid determination of Mycobacterium tuberculosis infection and drug resistance

•

Handheld Raman spectrometer is able to generate SERS spectra with sufficient quality for Mycobacterium tuberculosis detection.

•

It is feasible to accurately discriminate Mtb-positive sputum from Mtb-negative sputum through SERS spectrometry.

•

Pulmonary and extra-pulmonary Mtb strains were able to be accurately distinguished via SERS spectral analysis.

•

Profiling of antibiotic resistance of Mtb strains was successfully achieved through machine learning analysis of SERS spectra.

Over the past decades, conventional methods and molecular assays have been developed for the detection of tuberculosis (TB). However, these techniques suffer limitations in the identification of Mycobacterium tuberculosis (Mtb), such as long turnaround time and low detection sensitivity, etc., not even mentioning the difficulty in discriminating antibiotics-resistant Mtb strains that cause great challenges in TB treatment and prevention. Thus, techniques with easy implementation for rapid diagnosis of Mtb infection are in high demand for routine TB diagnosis. Due to the label-free, low-cost and non-invasive features, surface enhanced Raman spectroscopy (SERS) has been extensively investigated for its potential in bacterial pathogen identification. However, at current stage, few studies have recruited handheld Raman spectrometer to discriminate sputum samples with or without Mtb, separate pulmonary Mtb strains from extra-pulmonary Mtb strains, or profile Mtb strains with different antibiotic resistance characteristics. In this study, we recruited a set of supervised machine learning algorithms to dissect different SERS spectra generated via a handheld Raman spectrometer with a focus on deep learning algorithms, through which sputum samples with or without Mtb strains were successfully differentiated (5-fold cross-validation accuracy = 94.32%). Meanwhile, Mtb strains isolated from pulmonary and extra-pulmonary samples were effectively separated (5-fold cross-validation accuracy = 99.86%). Moreover, Mtb strains with different drug-resistant profiles were also competently distinguished (5-fold cross-validation accuracy = 99.59%). Taken together, we concluded that, with the assistance of deep learning algorithms, handheld Raman spectrometer has a high application potential for rapid point-of-care diagnosis of Mtb infections in future.