Rapid and quantitative detection of respiratory viruses using surface-enhanced Raman spectroscopy and machine learning

Single-shot, receptor-free, rapid detection and classification of five respiratory viruses by machine learning integrated SERS sensing platform

A machine learning integrated SERS sensing platform is developed for a single-shot, receptor-free, rapid detection and classification of five respiratory viruses including Influenza A, Respiratory Syncytial Virus (RSV), Human Rhinoviruses (Rhino), and two variants of SARS-CoV-2 virus such as Omicron and Delta in clinical nasal and/or nasopharyngeal samples (CNS) in viral transport media (VTM). SERS sensor composed of Ag nano-sculptured thin film (nSTF) is fabricated by glancing angle deposition (GLAD) technique and possess a SERS enhancement factor of the order of 1011. Various machine learning (ML) algorithms like Random Forest Classifier (RF), Support Vector Machine (SVM), Logistic Regression (LR), k-Nearest Neighbor (KNN), and Multilayer Perceptron (MLP) are trained on SERS spectra dataset of CNS for classification of the viruses. MLP shows the best performance for the analysis and classification of complex SERS spectra with a 5-fold validation accuracy of 97.61 ± 0.30 %, test accuracy 97.47 %, sensitivity 97 %, precision 97 %, and specificity 99 %. The SERS sensor integrated with ML has a rapid response of 11 minutes, which makes it appropriate for practical implementations in clinical environments, speeding up virus detection and efficient management of respiratory viral infections.

Extracting True Virus SERS Spectra and Augmenting Data for Improved Virus Classification and Quantification

Surface-enhanced Raman spectroscopy (SERS) is a transformative tool for infectious disease diagnostics, offering rapid and sensitive species identification. However, background spectra in biological samples complicate analyte peak detection, increase the limit of detection, and hinder data augmentation. To address these challenges, we developed a deep learning framework utilizing dual neural networks to extract true virus SERS spectra and estimate concentration coefficients in water for 12 different respiratory viruses. The extracted spectra showed a high similarity to those obtained at the highest viral concentration, validating their accuracy. Using these spectra and the derived concentration coefficients, we augmented spectral data sets across varying virus concentrations in water. XGBoost models trained on these augmented data sets achieved overall classification and concentration prediction accuracy of 92.3% with a coefficient of determination (R2) > 0.95. Additionally, the extracted spectra and coefficients were used to augment data sets in saliva backgrounds. When tested against real virus-in-saliva spectra, the augmented spectra-trained XGBoost models achieved 91.9% accuracy in classification and concentration prediction with R2 > 0.9, demonstrating the robustness of the approach. By delivering clean and uncontaminated spectra, this methodology can significantly improve species identification, differentiation, and quantification and advance SERS-based detection and diagnostics.

The application of machine learning in clinical microbiology and infectious diseases

With the development of artificial intelligence(AI) in computer science and statistics, it has been further applied to the medical field. These applications include the management of infectious diseases, in which machine learning has created inroads in clinical microbiology, radiology, genomics, and the analysis of electronic health record data. Especially, the role of machine learning in microbiology has gradually become prominent, and it is used in etiological diagnosis, prediction of antibiotic resistance, association between human microbiome characteristics and complex host diseases, prognosis judgment, and prevention and control of infectious diseases. Machine learning in the field of microbiology mainly adopts supervised learning and unsupervised learning, involving algorithms from classification and regression to clustering and dimensionality reduction. This Review explains crucial concepts in machine learning for unfamiliar readers, describes machine learning's current applications in clinical microbiology and infectious diseases, and summarizes important approaches clinicians must be aware of when evaluating research using machine learning.

Gradient Nanostructures and Machine Learning Synergy for Robust Quantitative Surface-Enhanced Raman Scattering

Surface-Enhanced Raman Scattering (SERS) holds significant promise for trace-level molecular detection but faces challenges in achieving reliable quantitative analysis due to signal variability caused by non-uniform "hot spots" and external factors. To address these limitations, a novel SERS platform based on gradient nanostructures is developed using shadow sphere lithography, enabling the acquisition of diverse spectral features from a single analyte concentration under identical conditions. The gradient design minimizes fabrication variability and enhances spectral diversity, while the machine learning (ML) model trained on the multi-spectral dataset significantly outperformed traditional single-spectrum approaches, with the test Mean Squared Error (MSE) reduced by 84.8% and the coefficient of determination (R2) improved by 61.2%. This strategy captures subtle spectral variations, improving the precision, robustness, and reproducibility of SERS-based quantification, paving the way for its reliable application in real-world scenarios.

Urine collection by sodium alginate/CMC composite self-calibrating aerogel SERS platform for accurate screening and staging of chronic kidney disease

Chronic kidney disease (CKD), characterized by structural or functional renal abnormalities, poses substantial health risks. With a global prevalence nearing 13 %, fewer than 10 % of affected individuals are aware of their condition. Early-stage CKD frequently goes undetected due to the lack of specific symptoms and the high costs and logistical challenges associated with traditional blood testing. This study introduces an anionic, ultrasensitive aerogel SERS platform (CS-Ag@4-mbn), constructed from sodium alginate and carboxymethyl cellulose, optimized for efficient biomarker capture and rapid urinary analysis. The CS-Ag@4-mbn platform demonstrates an exceptional R6G adsorption capacity of 2.67 × 10-6 mol/g and a detection limit of 8.81 × 10-11 M, underscoring its advanced SERS recognition performance. Furthermore, the integration of an internal standard signal within the CS-Ag@4-mbn system reduces potential errors and facilitates dataset correction. To interpret the acquired SERS data, five machine learning algorithms-PCA, SVM, DT, KNN, and RF-were employed, successfully constructing models to differentiate CKD stages (healthy and stages IV). These models achieved accuracy rates of up to 100 % in training and 97.58 % in testing, even without urine pre-processing, highlighting the platform's potential for non-invasive, early-stage CKD screening and diagnosis.

Multiplex Detection and Quantification of Virus Co-Infections Using Label-free Surface-Enhanced Raman Spectroscopy and Deep Learning Algorithms

Multiple respiratory viruses can concurrently or sequentially infect the respiratory tract, making their identification crucial for diagnosis, treatment, and disease management. We present a label-free diagnostic platform integrating surface-enhanced Raman scattering (SERS) with deep learning for rapid, quantitative detection of respiratory virus coinfections. Using sensitive silica-coated silver nanorod array substrates, over 1.2 million SERS spectra are collected from 11 viruses, nine two-virus mixtures, and four three-virus mixtures at various concentrations in saliva. A deep learning model, MultiplexCR, is developed to simultaneously predict virus species and concentrations from SERS spectra. It achieves an impressive 98.6% accuracy in classifying virus coinfections and a mean absolute error of 0.028 for concentration regression. In blind tests, the model demonstrates consistent high accuracy and precise concentration predictions. This SERS-MultiplexCR platform completes the entire detection process in just 15 min, offering significant potential for rapid, point-of-care diagnostics in infection detection, as well as applications in food safety and environmental monitoring.

Identification of SERS Fingerprints for Diagnosis and Staging of Liver Injury

Acute liver injury is a common hepatic condition that, without timely diagnosis and treatment, can easily progress to life-threatening liver failure. Identifying key biomolecular changes in the pathogenesis of liver injury is critical for the precise diagnosis of hepatic injury. In this study, we identified novel molecular fingerprints associated with hepatic injury using artificial intelligence-assisted Surface-enhanced Raman spectroscopy (SERS) technology. By intravenous injection of PEG-modified Au nanoparticles, which efficiently accumulate in the liver, these nanoparticles act as in vivo computed tomography contrast agents, specifically delineating the three-dimensional structure of normal and injured liver tissues. Additionally, as a Raman-enhanced substrate, gold nanoparticles allow for the analysis of SERS signals in liver tissues enriched with these nanoparticles. Leveraging artificial intelligence technology, we achieved a classification accuracy of 96.45% for different degrees of liver injury. Molecular spectral analysis revealed that the ratio of the 1437-1000 cm-1 signal could serve as an SERS fingerprint correlated with hepatic injury. The integrated information system provides a valuable tool for the precise diagnosis of liver diseases.

Raman Spectral Feature Enhancement Framework for Complex Multiclassification Tasks

Raman spectroscopy enables label-free clinical diagnosis in a single step. However, identifying an individual carrying a specific disease from people with a multi-disease background is challenging. To address this, we developed a Raman spectral implicit feature augmentation with a Raman Intersection, Union, and Subtraction augmentation strategy (RIUS). RIUS expands the data set without requiring additional labeled data by leveraging set operations at the feature level, significantly enhancing model performance across various applications. On a challenging 30-class bacterial classification task, RIUS demonstrated a substantial improvement, increasing the accuracy of ResNet by 2.1% and that of SE-ResNet by 1.4%, achieving accuracies of 85.7% and 87.1%, respectively, on the Bacteria-ID-4 Data set, where RIUS improved ResNet and SE-ResNet accuracies by 13.6% and 14.5%, respectively, with only ten samples per category. When the sample size was reduced, accuracy gains increased to 31.7% and 38.3%, demonstrating the method's robustness across different sample volumes. Compared to basic augmentation, our method exhibited superior performance across various sample volumes and demonstrated exceptional adaptability to different levels of complexity. RIUS exhibited superior performance, particularly in complex settings. Moreover, cluster analysis validated the effectiveness of the implicit feature augmentation module and the consistency between theoretical design and experimental results. We further validated our approach using clinical serum samples from 70 breast cancer patients and 70 controls, achieving an AUC of 0.94 and a sensitivity of 92.9%. Our approach enhances the potential for precisely identifying diseases in complex settings and offers plug-and-play enhancement for existing classification models.

Open-set deep learning-enabled single-cell Raman spectroscopy for rapid identification of airborne pathogens in real-world environments

Pathogenic bioaerosols are critical for outbreaks of airborne disease; however, rapidly and accurately identifying pathogens directly from complex air environments remains highly challenging. We present an advanced method that combines open-set deep learning (OSDL) with single-cell Raman spectroscopy to identify pathogens in real-world air containing diverse unknown indigenous bacteria that cannot be fully included in training sets. To test and further enhance identification, we constructed the Raman datasets of aerosolized bacteria. Through optimizing OSDL algorithms and training strategies, Raman-OSDL achieves 93% accuracy for five target airborne pathogens, 84% accuracy for untrained air bacteria, and 36% reduction in false positive rates compared to conventional close-set algorithms. It offers a high detection sensitivity down to 1:1000. When applied to real air containing >4600 bacterial species, our method accurately identifies single or multiple pathogens simultaneously within an hour. This single-cell tool advances rapidly surveilling pathogens in complex environments to prevent infection transmission.

Rapid and accurate bacteria identification through deep-learning-based two-dimensional Raman spectroscopy

Surface-enhanced Raman spectroscopy (SERS) offers a distinctive vibrational fingerprint of the molecules and has led to widespread applications in medical diagnosis, biochemistry, and virology. With the rapid development of artificial intelligence (AI) technology, AI-enabled Raman spectroscopic techniques, as a promising avenue for biosensing applications, have significantly boosted bacteria identification. By converting spectra into images, the dataset is enriched with more detailed information, allowing AI to identify bacterial isolates with enhanced precision. However, previous studies usually suffer from a trade-off between high-resolution spectrograms for high-accuracy identification and short training time for data processing. Here, we present an efficient bacteria identification strategy that combines deep learning models with a spectrogram encoding algorithm based on wavelet packet transform and Gramian angular field techniques. In contrast to the direct analysis of raw Raman spectra, our approach utilizes wavelet packet transform techniques to compress the spectra by a factor of 1/15, while concurrently maintaining state-of-the-art accuracy by amplifying the subtle differences via Gramian angular field techniques. The results demonstrate that our approach can achieve a 99.64 % and a 90.55 % identification accuracy for two types of bacterial isolates and thirty types of bacterial isolates, respectively, while a 90 % reduction in training time compared to the conventional methods. To verify the model's stability, Gaussian noises were superimposed on the testing dataset, showing a specific generalization ability and superior performance. This algorithm has the potential for integration into on-site testing protocols and is readily updatable with new bacterial isolates. This study provides profound insights and contributes to the current understanding of spectroscopy, paving the way for accurate and rapid bacteria identification in diverse applications of environment monitoring, food safety, microbiology, and public health.

Precision classification and quantitative analysis of bacteria biomarkers via surface-enhanced Raman spectroscopy and machine learning

The SERS spectra of six bacterial biomarkers, 2,3-DHBA, 2,5-DHBA, Pyocyanin, lipoteichoic acid (LTA), Enterobactin, and β-carotene, of various concentrations, were obtained from silver nanorod array substrates, and the spectral peaks and the corresponding vibrational modes were identified to classify different spectra. The spectral variations in three different concentration regions due to various reasons have imposed a challenge to use classic calibration curve methods to quantify the concentration of biomarkers. Depending on baseline removal strategy, i.e., local or global baseline removal, the calibration curve differed significantly. With the aid of convolutional neural network (CNN), a two-step process was established to classify and quantify biomarker solutions based on SERS spectra: using a specific CNN model, a remarkable differentiation and classification accuracy of 99.99 % for all six biomarkers regardless of the concentration can be achieved. After classification, six regression CNN models were established to predict the concentration of biomarkers, with coefficient of determination R2 > 0.97 and mean absolute error (MAE) < 0.27. The feature of important calculations indicates the high classification and quantification accuracies were due to the intrinsic spectral features in SERS spectra. This study showcases the synergistic potential of SERS and advanced machine learning algorithms and holds significant promise for bacterial infection diagnostics.

Rapid identification and quantitative analysis of malachite green in fish via SERS and 1D convolutional neural network

Rapid and quantitative detection of malachite green (MG) in aquaculture products is very important for safety assurance in food supply. Here, we develop a point-of-care testing (POCT) platform that combines a flexible and transparent surface-enhanced Raman scattering (SERS) substrate with deep learning network for achieving rapid and quantitative detection of MG in fish. The flexible and transparent SERS substrate was prepared by depositing silver (Ag) film on the polydimethylsiloxane (PDMS) film using laser molecular beam epitaxy (LMBE) technique. The wrinkled Ag NPs@PDMS film exhibits high SERS activity, excellent reproducibility and good mechanical stability. Additionally, the fast in situ detection of MG residues onfishscales was achieved by using the wrinkled Ag NPs/PDMS film and a portable Raman spectrometer, with a minimum detectable concentration of 10-6 M. Subsequently, a one-dimensional convolutional neural network (1D CNN) model was constructed for rapid quantification of MG concentration. The results demonstrated that the 1D CNN quantitative analysis model possessed superior predictive performance, with a coefficient of determination (R2) of 0.9947 and a mean squared error (MSE) of 0.0104. The proposed POCT platform, integrating a transparent flexible SERS substrate, a portable Raman spectrometer and a 1D CNN model, provides an efficient strategy for rapid identification and quantitative analysis of MG in fish.

Innovative and versatile surface-enhanced Raman spectroscopy-inspired approaches for viral detection leading to clinical applications: A review

The evolution of analytical techniques has opened the possibilities of accurate analyte detection through a straightforward method and short acquisition time, leading towards their applicability to identify medical conditions. Surface-enhanced Raman spectroscopy (SERS) has long been proven effective for rapid detection and relies on SERS spectra that are unique to each specific analyte. However, the complexity of viruses poses challenges to SERS and hinders further progress in its practical applications. The principle of SERS revolves around the interaction among substrate, analyte, and Raman laser, but most studies only emphasize the substrate, especially label-free methods, and the synergy among these factors is often ignored. Therefore, issues related to reproducibility and consistency of results, which are crucial for medical diagnosis and are the main highlights of this review, can be understood and largely addressed when considering these interactions. Viruses are composed of multiple surface components and can be detected by label-free SERS, but the presence of non-target molecules in clinical samples interferes with the detection process. Appropriate spectral data processing workflow also plays an important role in the interpretation of results. Furthermore, integrating machine learning into data processing can account for changes brought about by the presence of non-target molecules when analyzing spectral features to accurately group the data, for example, whether the sample corresponds to a positive or negative patient, and whether a virus variant or multiple viruses are present in the sample. Subsequently, advances in interdisciplinary fields can bring SERS closer to practical applications.

Influenza viruses and SARS-CoV-2 diagnosis via sensitive testing methods in clinical application

The identification of influenza viruses and SARS-CoV-2 has garnered increasing attention due of their longstanding global menace to human life and health. The point-of-care test is a potential approach for identifying influenza viruses and SARS-CoV-2 in clinical settings, leading to timely discovery, documentation, and treatment. The primary difficulties encountered with conventional detection techniques for influenza viruses and SARS-CoV-2 are the limited or inadequate ability to identify the presence of the viruses, the lack of speed, precision, accuracy, sensitivity, and specificity, often resulting in a failure to promptly notify disease control authorities. Recently, point-of-care test methods, along with nucleic acid amplification, optics, electrochemistry, lateral/vertical flow, and minimization, have been demonstrated the characteristics of reliability, sensitivity, specificity, stability, and portability. A point-of-care test offers promising findings in the early detection of influenza viruses and SARS-CoV-2 in both scientific research and practical use. In this review, we will go over the principles, advantages, limitations, and real-world applications of point-of-care diagnostics. The significance of constraints of detection, throughput, sensitivity, and specificity in the analysis of clinical samples in settings with restricted resources is underscored. This discussion concludes with their prospects and challenges.

Rapid and label-free influenza A virus subtyping using surface-enhanced Raman spectroscopy with incident-wavelength analysis

Early virus identification is a key component of both patient treatment and epidemiological monitoring. In the case of influenza A virus infections, where the detection of subtypes associated with bird flu in humans could lead to a pandemic, rapid subtype-level identification is important. Surface-enhanced Raman spectroscopy coupled with machine learning can be used to rapidly detect and identify viruses in a label-free manner. As there is a range of available excitation wavelengths for performing Raman spectroscopy, we must choose the best one to permit discrimination between highly similar subtypes of a virus. We show that the spectra produced by influenza A subtypes H1N1 and H3N2 exhibit a higher degree of dissimilarity when using 785 nm excitation wavelength in comparison with 532 nm excitation wavelength. Furthermore, the cross-validated area under the curve (AUC) for identification was higher for the 785 nm excitation, reaching 0.95 as compared to 0.86 for 532 nm. Ultimately, this study suggests that exciting with a 785 nm wavelength is better able to differentiate two closely related influenza viruses and likely can extend to other closely related pathogens.

Advancing SERS as a quantitative technique: challenges, considerations, and correlative approaches to aid validation

Surface-enhanced Raman scattering (SERS) remains a significant area of research since it's discovery 50 years ago. The surface-based technique has been used in a wide variety of fields, most prominently in chemical detection, cellular imaging and medical diagnostics, offering high sensitivity and specificity when probing and quantifying a chosen analyte or monitoring nanoparticle uptake and accumulation. However, despite its promise, SERS is mostly confined to academic laboratories and is not recognised as a gold standard analytical technique. This is due to the variations that are observed in SERS measurements, mainly caused by poorly characterised SERS substrates, lack of universal calibration methods and uncorrelated results. To convince the wider scientific community that SERS should be a routinely used analytical technique, the field is now focusing on methods that will increase the reproducibility of the SERS signals and how to validate the results with more well-established techniques. This review explores the difficulties experienced by SERS users, the methods adopted to reduce variation and suggestions of best practices and strategies that should be adopted if one is to achieve absolute quantification.

Rapid Detection of SARS-CoV-2 Variants Using an Angiotensin-Converting Enzyme 2-Based Surface-Enhanced Raman Spectroscopy Sensor Enhanced by CoVari Deep Learning Algorithms

An integrated approach combining surface-enhanced Raman spectroscopy (SERS) with a specialized deep learning algorithm to rapidly and accurately detect and quantify SARS-CoV-2 variants is developed based on an angiotensin-converting enzyme 2 (ACE2)-functionalized AgNR@SiO2 array SERS sensor. SERS spectra with concentrations of different variants were collected using a portable Raman system. After appropriate spectral preprocessing, a deep learning algorithm, CoVari, is developed to predict both the viral variant species and concentrations. Using a 10-fold cross-validation strategy, the model achieves an average accuracy of 99.9% in discriminating between different virus variants and R2 values larger than 0.98 for quantifying viral concentrations of the three viruses, demonstrating the high quality of the detection. The limit of detection of the ACE2 SERS sensor is determined to be 10.472, 11.882, and 21.591 PFU/mL for SARS-CoV-2, SARS-CoV-2 B1, and CoV-NL63, respectively. The feature importance of virus classification and concentration regression in the CoVari algorithm are calculated based on a permutation algorithm, which showed a clear correlation to the biochemical origins of the spectra or spectral changes. In an unknown specimen test, classification accuracy can achieve >90% for concentrations larger than 781 PFU/mL, and the predicted concentrations consistently align with actual values, highlighting the robustness of the proposed algorithm. Based on the CoVari architecture and the output vector, this algorithm can be generalized to predict both viral variant species and concentrations simultaneously for a broader range of viruses. These results demonstrate that the SERS + CoVari strategy has the potential for rapid and quantitative detection of virus variants and potentially point-of-care diagnostic platforms.

Surface-Enhanced Raman Spectroscopy and Artificial Neural Networks for Detection of MXene Flakes' Surface Terminations

The properties of MXene flakes, a new class of two-dimensional materials, are strictly determined by their surface termination. The most common termination groups are oxygen-containing (=O or -OH) and fluorine (-F), and their relative ratio is closely related to flake stability and catalytic activity. The surface termination can vary significantly among MXene flakes depending on the preparation route and is commonly determined after flake preparation by using X-ray photoelectron spectroscopy (XPS). In this paper, as an alternative approach, we propose the combination of surface-enhanced Raman spectroscopy (SERS) and artificial neural networks (ANN) for the precise and reliable determination of MXene flakes' (Ti3C2Tx) surface chemistry. Ti3C2Tx flakes were independently prepared by three scientific groups and subsequently measured using three different Raman spectrometers, employing resonant excitation wavelengths. Manual analysis of the SERS spectra did not enable accurate determination of the flake surface termination. However, the combined SERS-ANN approach allowed us to determine the surface termination with a high accuracy. The reliability of the method was verified by using a series of independently prepared samples. We also paid special attention to how the results of the SERS-ANN method are affected by the flake stability and differences in the conditions of flake preparation and Raman measurements. This way, we have developed a universal technique that is independent of the above-mentioned parameters, providing the results with accuracy similar to XPS, but enhanced in terms of analysis time and simplicity.

Saliva-based detection of SARS-CoV-2: a bibliometric analysis of global research

Saliva has emerged as a promising noninvasive biofluid for the diagnosis of oral and systemic diseases, including viral infections. During the coronavirus disease 2019 (COVID-19) pandemic, a growing number of studies focused on saliva-based detection of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2). Taking advantage of the WoS core collection (WoSCC) and CiteSpace, we retrieved 1021 articles related to saliva-based detection of SARS-CoV-2 and conducted a comprehensive bibliometric analysis. We analyzed countries, institutions, authors, cited authors, and cited journals to summarize their contribution and influence and analyzed keywords to explore research hotspots and trends. From 2020 to 2021, research focused on viral transmission via saliva and verification of saliva as a reliable specimen, whereas from 2021 to the present, the focus of research has switched to saliva-based biosensors for SARS-CoV-2 detection. By far, saliva has been verified as a reliable specimen for SARS-CoV-2 detection, although a standardized procedure for saliva sampling and processing is needed. Studies on saliva-based detection of SARS-CoV-2 will promote the development of saliva-based diagnostics and biosensors for viral detection. Collectively, our findings could provide valuable information to help scientists perceive the basic knowledge landscapes on saliva-based detection of SARS-CoV-2, the past and current research hotspots, and future opportunities.

Machine learning-driven SERS fingerprinting of disintegrated viral components for rapid detection of SARS-CoV-2 in environmental dust

Surveillance of airborne viruses in crowded indoor spaces is crucial for managing outbreaks, as highlighted by the SARS-CoV-2 pandemic. However, the rapid and on-site detection of fast-mutating viruses, such as SARS-CoV-2, in complex environmental backgrounds remains challenging. Our study introduces a machine learning (ML)-driven surface-enhanced Raman spectroscopy (SERS) approach for detecting viruses within environmental dust matrices. By decomposing intact virions into individual structural components via a Raman-background-free lysis protocol and concentrating them into nanogap SERS hotspots, we significantly enhance the SERS signal intensity and fingerprint information density from viral structural components. Utilizing Principal Component Analysis (PCA), we establish a robust connection between the SERS data of these structural components and their biological sequences, laying a solid foundation for virus detection through SERS. Furthermore, we demonstrate reliable quantitative detection of SARS-CoV-2 using identified SARS-CoV-2 peaks at concentrations down to 102 pfu/ml through Gaussian Process Regression (GPR) and a digital SERS methodology. Finally, applying a Principal Component Analysis-Linear Discriminant Analysis (PCA-LDA) algorithm, we identify SARS-CoV-2, influenza A virus, and Zika virus within an environmental dust background with over 86% accuracy. Therefore, our ML-driven SERS approach holds promise for rapid environmental virus monitoring to manage future outbreaks.

Current Trends of Raman Spectroscopy in Clinic Settings: Opportunities and Challenges

Early clinical diagnosis, effective intraoperative guidance, and an accurate prognosis can lead to timely and effective medical treatment. The current conventional clinical methods have several limitations. Therefore, there is a need to develop faster and more reliable clinical detection, treatment, and monitoring methods to enhance their clinical applications. Raman spectroscopy is noninvasive and provides highly specific information about the molecular structure and biochemical composition of analytes in a rapid and accurate manner. It has a wide range of applications in biomedicine, materials, and clinical settings. This review primarily focuses on the application of Raman spectroscopy in clinical medicine. The advantages and limitations of Raman spectroscopy over traditional clinical methods are discussed. In addition, the advantages of combining Raman spectroscopy with machine learning, nanoparticles, and probes are demonstrated, thereby extending its applicability to different clinical phases. Examples of the clinical applications of Raman spectroscopy over the last 3 years are also integrated. Finally, various prospective approaches based on Raman spectroscopy in clinical studies are surveyed, and current challenges are discussed.

Unveiling practical considerations for reliable and standardized SERS measurements: lessons from a comprehensive review of oblique angle deposition-fabricated silver nanorod array substrates

Recently, there has been an exponential growth in the number of publications focusing on surface-enhanced Raman scattering (SERS), primarily driven by advancements in nanotechnology and the increasing demand for chemical and biological detection. While many of these publications have focused on the development of new substrates and detection-based applications, there is a noticeable lack of attention given to various practical issues related to SERS measurements and detection. This review aims to fill this gap by utilizing silver nanorod (AgNR) SERS substrates fabricated through the oblique angle deposition method as an illustrative example. The review highlights and addresses a range of practical issues associated with SERS measurements and detection. These include the optimization of SERS substrates in terms of morphology and structural design, considerations for measurement configurations such as polarization and the incident angle of the excitation laser, and exploration of enhancement mechanisms encompassing both intrinsic properties induced by the structure and materials, as well as extrinsic factors arising from wetting/dewetting phenomena and analyte size. The manufacturing and storage aspects of SERS substrates, including scalable fabrication techniques, contamination control, cleaning procedures, and appropriate storage methods, are also discussed. Furthermore, the review delves into device design considerations, such as well arrays, flow cells, and fiber probes, and explores various sample preparation methods such as drop-cast and immersion. Measurement issues, including the effect of excitation laser wavelength and power, as well as the influence of buffer, are thoroughly examined. Additionally, the review discusses spectral analysis techniques, encompassing baseline removal, chemometric analysis, and machine learning approaches. The wide range of AgNR-based applications of SERS, across various fields, is also explored. Throughout the comprehensive review, key lessons learned from collective findings are outlined and analyzed, particularly in the context of detailed SERS measurements and standardization. The review also provides insights into future challenges and perspectives in the field of SERS. It is our hope that this comprehensive review will serve as a valuable reference for researchers seeking to embark on in-depth studies and applications involving their own SERS substrates.

Rapid classification of SARS-CoV-2 variant strains using machine learning-based label-free SERS strategy

The spread of COVID-19 over the past three years is largely due to the continuous mutation of the virus, which has significantly impeded global efforts to prevent and control this epidemic. Specifically, mutations in the amino acid sequence of the surface spike (S) protein of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) have directly impacted its biological functions, leading to enhanced transmission and triggering an immune escape effect. Therefore, prompt identification of these mutations is crucial for formulating targeted treatment plans and implementing precise prevention and control measures. In this study, the label-free surface-enhanced Raman scattering (SERS) technology combined with machine learning (ML) algorithms provide a potential solution for accurate identification of SARS-CoV-2 variants. We establish a SERS spectral database of SARS-CoV-2 variants and demonstrate that a diagnostic classifier using a logistic regression (LR) algorithm can provide accurate results within 10 min. Our classifier achieves 100% accuracy for Beta (B.1.351/501Y.V2), Delta (B.1.617), Wuhan (COVID-19) and Omicron (BA.1) variants. In addition, our method achieves 100% accuracy in blind tests of positive and negative human nasal swabs based on the LR model. This method enables detection and classification of variants in complex biological samples. Therefore, ML-based SERS technology is expected to accurately discriminate various SARS-CoV-2 variants and may be used for rapid diagnosis and therapeutic decision-making.

Machine Learning for COVID-19 Determination Using Surface-Enhanced Raman Spectroscopy

The rapid, low cost, and efficient detection of SARS-CoV-2 virus infection, especially in clinical samples, remains a major challenge. A promising solution to this problem is the combination of a spectroscopic technique: surface-enhanced Raman spectroscopy (SERS) with advanced chemometrics based on machine learning (ML) algorithms. In the present study, we conducted SERS investigations of saliva and nasopharyngeal swabs taken from a cohort of patients (saliva: 175; nasopharyngeal swabs: 114). Obtained SERS spectra were analyzed using a range of classifiers in which random forest (RF) achieved the best results, e.g., for saliva, the precision and recall equals 94.0% and 88.9%, respectively. The results demonstrate that even with a relatively small number of clinical samples, the combination of SERS and shallow machine learning can be used to identify SARS-CoV-2 virus in clinical practice.

Performance of Classification Models of Toxins Based on Raman Spectroscopy Using Machine Learning Algorithms

Rapid and accurate detection of protein toxins is crucial for public health. The Raman spectra of several protein toxins, such as abrin, ricin, staphylococcal enterotoxin B (SEB), and bungarotoxin (BGT), have been studied. Multivariate scattering correction (MSC), Savitzky-Golay smoothing (SG), and wavelet transform methods (WT) were applied to preprocess Raman spectra. A principal component analysis (PCA) was used to extract spectral features, and the PCA score plots clustered four toxins with two other proteins. The k-means clustering results show that the spectra processed with MSC and MSC-SG methods have the best classification performance. Then, the two data types were classified using partial least squares discriminant analysis (PLS-DA) with an accuracy of 100%. The prediction results of the PCA and PLS-DA and the partial least squares regression model (PLSR) perform well for the fingerprint region spectra. The PLSR model demonstrates excellent classification and regression ability (accuracy = 100%, Rcv = 0.776). Four toxins were correctly classified with interference from two proteins. Classification models based on spectral feature extraction were established. This strategy shows excellent potential in toxin detection and public health protection. These models provide alternative paths for the development of rapid detection devices.

Identifying Surface-Enhanced Raman Spectra with a Raman Library Using Machine Learning

Since its discovery, surface-enhanced Raman spectroscopy (SERS) has shown outstanding promise of identifying trace amounts of unknown molecules in rapid, portable formats. However, the many different types of nanoparticles or nanostructured metallic SERS substrates created over the past few decades show substantial variability in the SERS spectra they provide. These inconsistencies have even raised speculation that substrate-specific SERS spectral libraries must be compiled for practical use of this type of spectroscopy. Here, we report a machine learning (ML) algorithm that can identify chemicals by matching their SERS spectra to those of a standard Raman spectral library. We use an approach analogous to facial recognition that utilizes feature extraction in the presence of multiple nuisance variables for spectral recognition. The key element is a metric we call "Characteristic Peak Similarity" (CaPSim) that focuses on the characteristic peaks in the SERS spectra. It has the flexibility to accommodate substrate-specific variability when quantifying the degree of similarity to a Raman spectrum. Analysis shows that CaPSim substantially outperforms existing spectral matching algorithms in terms of accuracy. This ML-based approach could greatly facilitate the spectroscopic identification of molecules in fieldable SERS applications.

Biosensors for waterborne virus detection: Challenges and strategies

Waterborne viruses that can be harmful to human health pose significant challenges globally, affecting health care systems and the economy. Identifying these waterborne pathogens is essential for preventing diseases and protecting public health. However, handling complex samples such as human and wastewater can be challenging due to their dynamic and complex composition and the ultralow concentration of target analytes. This review presents a comprehensive overview of the latest breakthroughs in waterborne virus biosensors. It begins by highlighting several promising strategies that enhance the sensing performance of optical and electrochemical biosensors in human samples. These strategies include optimizing bioreceptor selection, transduction elements, signal amplification, and integrated sensing systems. Furthermore, the insights gained from biosensing waterborne viruses in human samples are applied to improve biosensing in wastewater, with a particular focus on sampling and sample pretreatment due to the dispersion characteristics of waterborne viruses in wastewater. This review suggests that implementing a comprehensive system that integrates the entire waterborne virus detection process with high-accuracy analysis could enhance virus monitoring. These findings provide valuable insights for improving the effectiveness of waterborne virus detection, which could have significant implications for public health and environmental management.

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.

Diagnostics and analysis of SARS-CoV-2: current status, recent advances, challenges and perspectives

The disastrous spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has induced severe public healthcare issues and weakened the global economy significantly. Although SARS-CoV-2 infection is not as fatal as the initial outbreak, many infected victims suffer from long COVID. Therefore, rapid and large-scale testing is critical in managing patients and alleviating its transmission. Herein, we review the recent advances in techniques to detect SARS-CoV-2. The sensing principles are detailed together with their application domains and analytical performances. In addition, the advantages and limits of each method are discussed and analyzed. Besides molecular diagnostics and antigen and antibody tests, we also review neutralizing antibodies and emerging SARS-CoV-2 variants. Further, the characteristics of the mutational locations in the different variants with epidemiological features are summarized. Finally, the challenges and possible strategies are prospected to develop new assays to meet different diagnostic needs. Thus, this comprehensive and systematic review of SARS-CoV-2 detection technologies may provide insightful guidance and direction for developing tools for the diagnosis and analysis of SARS-CoV-2 to support public healthcare and effective long-term pandemic management and control.

Fully connected neural network-based serum surface-enhanced Raman spectroscopy accurately identifies non-alcoholic steatohepatitis

BACKGROUND/PURPOSE OF THE STUDY

There is a need to find a standardized and low-risk diagnostic tool that can non-invasively detect non-alcoholic steatohepatitis (NASH). Surface enhanced Raman spectroscopy (SERS), which is a technique combining Raman spectroscopy (RS) with nanotechnology, has recently received considerable attention due to its potential for improving medical diagnostics. We aimed to investigate combining SERS and neural network approaches, using a liver biopsy dataset to develop and validate a new diagnostic model for non-invasively identifying NASH.

METHODS

Silver nanoparticles as the SERS-active nanostructures were mixed with blood serum to enhance the Raman scattering signals. The spectral data set was used to train the NASH classification model by a neural network primarily consisting of a fully connected residual module.

RESULTS

Data on 261 Chinese individuals with biopsy-proven NAFLD were included and a prediction model for NASH was built based on SERS spectra and neural network approaches. The model yielded an AUROC of 0.83 (95% confidence interval [CI] 0.70-0.92) in the validation set, which was better than AUROCs of both serum CK-18-M30 levels (AUROC 0.63, 95% CI 0.48-0.76, p = 0.044) and the HAIR score (AUROC 0.65, 95% CI 0.51-0.77, p = 0.040). Subgroup analyses showed that the model performed well in different patient subgroups.

CONCLUSIONS

Fully connected neural network-based serum SERS analysis is a rapid and practical tool for the non-invasive identification of NASH. The online calculator website for the estimated risk of NASH is freely available to healthcare providers and researchers ( http://www.pan-chess.cn/calculator/RAMAN_score ).

Asymmetric parameter enhancement in the split-ring cavity array for virus-like particle sensing

Quantitative detection of virus-like particles under a low concentration is of vital importance for early infection diagnosis and water pollution analysis. In this paper, a novel virus detection method is proposed using indirect polarization parametric imaging method combined with a plasmonic split-ring nanocavity array coated with an Au film and a quantitative algorithm is implemented based on the extended Laplace operator. The attachment of viruses to the split-ring cavity breaks the structural symmetry, and such asymmetry can be enhanced by depositing a thin gold film on the sample, which allows an asymmetrical plasmon mode with a large shift of resonance peak generated under transverse polarization. Correspondingly, the far-field scattering state distribution encoded by the attached virus exhibits a specific asymmetric pattern that is highly correlated to the structural feature of the virus. By utilizing the parametric image sinδ to collect information on the spatial photon state distribution and far-field asymmetry with a sub-wavelength resolution, the appearance of viruses can be detected. To further reduce the background noise and enhance the asymmetric signals, an extended Laplace operator method which divides the detection area into topological units and then calculates the asymmetric parameter is applied, enabling easier determination of virus appearance. Experimental results show that the developed method can provide a detection limit as low as 56 vp/150µL on a large scale, which has great potential in early virus screening and other applications.

Recent Trends in SERS-Based Plasmonic Sensors for Disease Diagnostics, Biomolecules Detection, and Machine Learning Techniques

Surface-enhanced Raman spectroscopy/scattering (SERS) has evolved into a popular tool for applications in biology and medicine owing to its ease-of-use, non-destructive, and label-free approach. Advances in plasmonics and instrumentation have enabled the realization of SERS's full potential for the trace detection of biomolecules, disease diagnostics, and monitoring. We provide a brief review on the recent developments in the SERS technique for biosensing applications, with a particular focus on machine learning techniques used for the same. Initially, the article discusses the need for plasmonic sensors in biology and the advantage of SERS over existing techniques. In the later sections, the applications are organized as SERS-based biosensing for disease diagnosis focusing on cancer identification and respiratory diseases, including the recent SARS-CoV-2 detection. We then discuss progress in sensing microorganisms, such as bacteria, with a particular focus on plasmonic sensors for detecting biohazardous materials in view of homeland security. At the end of the article, we focus on machine learning techniques for the (a) identification, (b) classification, and (c) quantification in SERS for biology applications. The review covers the work from 2010 onwards, and the language is simplified to suit the needs of the interdisciplinary audience.

Detection of A and B Influenza Viruses by Surface-Enhanced Raman Scattering Spectroscopy and Machine Learning

We demonstrate the possibility of applying surface-enhanced Raman spectroscopy (SERS) combined with machine learning technology to detect and differentiate influenza type A and B viruses in a buffer environment. The SERS spectra of the influenza viruses do not possess specific peaks that allow for their straight classification and detection. Machine learning technologies (particularly, the support vector machine method) enabled the differentiation of samples containing influenza A and B viruses using SERS with an accuracy of 93% at a concentration of 200 μg/mL. The minimum detectable concentration of the virus in the sample using the proposed approach was ~0.05 μg/mL of protein (according to the Lowry protein assay), and the detection accuracy of a sample with this pathogen concentration was 84%.