Application of Raman spectroscopy in the detection of hepatitis B virus infection

Surface-enhanced Raman spectroscopy for the characterization of filtrate portions of hepatitis B blood serum samples using 100 kDa ultra filtration devices

The blood serum of patients infected by the Hepatitis B virus contains high molecular weight fractions and low molecular weight fractions (LMWF) of biomarker proteins of the disease. The LMWF including the associated peptidome and metabolome, is recognized as a critical molecular population with high potential for research on disease-associated biomarkers. This fraction of biomarkers can be suppressed by HMWF, proteins such as albumin, and immunoglobulins hence difficult to be detected. The purpose of this study is to separate HMWF) and LMWF using 100 kDa centrifugal filtration devices resulting in two parts including residue (HMWF) and filtrate parts (LMWF) of blood serum followed by the analysis of the later part employing surface-enhanced Raman spectroscopy (SERS). This strategy can enhance this optical technique's capability to characterize the biochemical changes caused by the infection of HBV and the diagnosis of the disease. The silver nanoparticles (Ag-NPs) were employed as a SERS substrate to distinguish between filtrate parts of the blood serum of HBV patients and healthy individuals based on their specific SERS peaks. The SERS spectral features associated with the filtrate parts of HBV patients' blood serum are well differentiated from the healthy volunteers. Principle component analysis (PCA) was applied on the SERS spectral data sets of HBV patients and healthy individuals and found extremely beneficial for the classification of their SERS spectral groups. Moreover, partial least square regression analysis (PLSR) has shown excellent performance in the quantitative analysis of the viral load values of the HBV patients using their SERS spectral data sets.

Validation of optimised intracranial spectroscopic probe for instantaneous in-situ monitoring and classification of traumatic brain injury

The development of an optical interface to directly distinguish the brain tissue's biochemistry is the next step in understanding traumatic brain injury (TBI) pathophysiology and the best and most appropriate treatment in cases where in-hospital intracranial access is required. Despite TBI being a globally leading cause of morbidity and mortality in patients under 40, there is still a lack of objective diagnostical tools. Further, given its pathophysiological complexity the majority of treatments provided are purely symptomatic without standardized therapeutic targets. Our tailor-engineered prototype of the intracranial Raman spectroscopy probe (Intra-RSP) is designed to bridge the gap and provide real-time spectroscopic insights to monitor TBI and its evolution as well as identify patient-specific molecular targets for timely intervention. Raman spectroscopy being rapid, label-free and non-destructive, renders it an ideal portable diagnostics tool. In combination with our in-house developed software, using machine learning algorithms for multivariate analysis, the Intra-RSP is shown to accurately differentiate simulated TBI conditions in rat brains from the healthy controls, directly from the brain surface as well as through the rat's skull. Using clinically pre-established methods of cranial entry, the Intra-RSP can be inserted into a 2-piece optimised cranial bolt with integrated focussing and correctly identify a sample in real-life conditions with an accuracy >80 %. To further validate the Intra-RSP's efficiency as a TBI monitoring device, rat brains mildly damaged from inflicted spinal cord injury were found to be correctly classified with 94.5 % accuracy. Through optimization and rigorous in-vivo validation, the Intra-RSP prototype is envisioned to seamlessly integrate into existing standards of neurological care, serving as a minimally invasive, in-situ neuromonitoring tool. This transformative approach has the potential to revolutionize the landscape of neurological care by providing clinicians with unprecedented insights into the nature of brain injuries and fostering targeted, timely and effective therapeutic interventions.

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.

A Raman spectroscopy based chemometric approach to predict the derived cetane number of hydrocarbon jet fuels and their mixtures

Fuel ignition quality, measured in the form of Derived Cetane Number (DCN), is an important part of integrating fuels, including sustainable aviation fuels, in compression ignition engines. DCN has been correlated with simulated and/or real spectroscopic measurements as well as other physical and chemical properties, but rarely have these correlations developed into a pathway to application. One application of the correlations is the use of miniaturized onboard fuel sensors that could assist, by using predicted DCN, in real-time feedforward engine control. To aid in the application of developing such DCN fuel sensors, Raman spectra coupled with chemometrics and a selection of influential spectral features were investigated. In this study, the Raman spectra were obtained from a database that included jet fuels, jet fuel mixtures, pure hydrocarbon components, and their weighted mixtures. The resulting Raman spectral database from the experimental measurements included spectra of components that span a wide range of DCNs and covered all the expected chemical functional groups present in a standard jet fuel. Chemometric models were developed to associate Raman spectra with DCN in subsets of the spectral range to aid in sensor miniaturization. The models were tested on jet fuels such as National Jet Fuel Combustion Program fuels designated A-1, A-2, and A-3 along with mixtures of jet fuels that spanned a wide range of DCN, simulating fuels that could represent real-world scenarios. An Artificial Neural Network (ANN) model trained on the fingerprint region (500 cm-1 - 1800 cm-1) of the Raman spectra was able to capture the non-linearity of the association between the Raman spectra and DCN with a test R2 score of 0.926, a test MSE of 3.61, and a test MPE of 3.41. Around 97 % of the unseen test samples were predicted within 10 % of the DCN measured with an Ignition Quality Tester. One hundred features of the fingerprint region influencing DCN predictions in the optimal ANN model were extracted using a Global Surrogate (GS) model. A reduced ANN model trained on only these one hundred features performed slightly better with a test R2 score of 0.935, test MSE of 3.19, test MPE of 3.20 and with the entire set of unseen test samples predicted within 10 % of the measured DCN. For assessing applicability of real-time and online DCN sensing, the Raman spectrometer was integrated with a flow cell capable of allowing measurements of DCN in flowing fuel samples and included the optimal ANN model of the fingerprint region and the 100-feature GS-ANN model on a Raspberry Pi computer. A number of unseen F-24/alcohol-to-jet fuel mixtures composed of unknown volumes were tested using the flow cell for DCN, and all of these samples were predicted within 10 % of the measured DCN.

On the feasibility of Vis-NIR spectroscopy and machine learning for real time SARS-CoV-2 detection

The pandemic caused by Covid-19 is still present around the world. Despite advances in combating the disease, such as vaccine development, identifying infected individuals is still essential to optimize the control of human-to-human transmission of the virus. The main technique for detecting the virus is the RT-PCR method, which, despite its high relative cost, has a high accuracy in detecting the coronavirus. Given this, a method capable of performing the identification quickly, accurately, and inexpensively is necessary. Thus, this work aimed to analyze the feasibility of a new technique for identifying SARS-CoV-2 through the use of optical spectroscopy in the visible and near-infrared range (Vis-NIR) combined with machine learning algorithms. Spectral signals were obtained from nasopharyngeal swab samples previously analyzed using the RT-PCR method. The specimens were provided by the Molecular Diagnosis Laboratory of Covid-19 at Univasf. A total of 314 samples were analyzed, comprising 42 testing positive and 272 testing negative for Covid-19. Digital signal processing techniques, such as Savitzky-Golay filters and statistical methods were used to eliminate spurious elements from the original data and extract relevant features. Supervised machine learning algorithms such as SVM, Random Forest, and Naive Bayes classifiers were used to perform automatic sample identification. To evaluate the performance of the models, a 5-fold cross-validation technique was applied. With the proposed methodology, it was possible to achieve an accuracy of 75%, a sensitivity of 80%, and a specificity of 70%, in addition to an area under the ROC curve of 0.81, in the identification of nasopharyngeal swab samples from previously diagnosed individuals. From these results, it was possible to conclude that Vis-NIR spectroscopy is a promising, fast and relatively low cost technique to identify the SARS-CoV-2.

Harnessing of Artificial Intelligence for the Diagnosis and Prevention of Hospital-Acquired Infections: A Systematic Review

Healthcare-associated infections (HAIs) are the most common adverse events in healthcare and constitute a major global public health concern. Surveillance represents the foundation for the effective prevention and control of HAIs, yet conventional surveillance is costly and labor intensive. Artificial intelligence (AI) and machine learning (ML) have the potential to support the development of HAI surveillance algorithms for the understanding of HAI risk factors, the improvement of patient risk stratification as well as the prediction and timely detection and prevention of infections. AI-supported systems have so far been explored for clinical laboratory testing and imaging diagnosis, antimicrobial resistance profiling, antibiotic discovery and prediction-based clinical decision support tools in terms of HAIs. This review aims to provide a comprehensive summary of the current literature on AI applications in the field of HAIs and discuss the future potentials of this emerging technology in infection practice. Following the PRISMA guidelines, this study examined the articles in databases including PubMed and Scopus until November 2023, which were screened based on the inclusion and exclusion criteria, resulting in 162 included articles. By elucidating the advancements in the field, we aim to highlight the potential applications of AI in the field, report related issues and shortcomings and discuss the future directions.

Raman Spectroscopy Spectral Fingerprints of Biomarkers of Traumatic Brain Injury

Traumatic brain injury (TBI) affects millions of people of all ages around the globe. TBI is notoriously hard to diagnose at the point of care, resulting in incorrect patient management, avoidable death and disability, long-term neurodegenerative complications, and increased costs. It is vital to develop timely, alternative diagnostics for TBI to assist triage and clinical decision-making, complementary to current techniques such as neuroimaging and cognitive assessment. These could deliver rapid, quantitative TBI detection, by obtaining information on biochemical changes from patient's biofluids. If available, this would reduce mis-triage, save healthcare providers costs (both over- and under-triage are expensive) and improve outcomes by guiding early management. Herein, we utilize Raman spectroscopy-based detection to profile a panel of 18 raw (human, animal, and synthetically derived) TBI-indicative biomarkers (N-acetyl-aspartic acid (NAA), Ganglioside, Glutathione (GSH), Neuron Specific Enolase (NSE), Glial Fibrillary Acidic Protein (GFAP), Ubiquitin C-terminal Hydrolase L1 (UCHL1), Cholesterol, D-Serine, Sphingomyelin, Sulfatides, Cardiolipin, Interleukin-6 (IL-6), S100B, Galactocerebroside, Beta-D-(+)-Glucose, Myo-Inositol, Interleukin-18 (IL-18), Neurofilament Light Chain (NFL)) and their aqueous solution. The subsequently derived unique spectral reference library, exploiting four excitation lasers of 514, 633, 785, and 830 nm, will aid the development of rapid, non-destructive, and label-free spectroscopy-based neuro-diagnostic technologies. These biomolecules, released during cellular damage, provide additional means of diagnosing TBI and assessing the severity of injury. The spectroscopic temporal profiles of the studied biofluid neuro-markers are classed according to their acute, sub-acute, and chronic temporal injury phases and we have further generated detailed peak assignment tables for each brain-specific biomolecule within each injury phase. The intensity ratios of significant peaks, yielding the combined unique spectroscopic barcode for each brain-injury marker, are compared to assess variance between lasers, with the smallest variance found for UCHL1 (σ2 = 0.000164) and the highest for sulfatide (σ2 = 0.158). Overall, this work paves the way for defining and setting the most appropriate diagnostic time window for detection following brain injury. Further rapid and specific detection of these biomarkers, from easily accessible biofluids, would not only enable the triage of TBI, predict outcomes, indicate the progress of recovery, and save healthcare providers costs, but also cement the potential of Raman-based spectroscopy as a powerful tool for neurodiagnostics.

Raman spectral pattern recognition of breast cancer: A machine learning strategy based on feature fusion and adaptive hyperparameter optimization

Raman spectroscopy, as a kind of molecular vibration spectroscopy, provides abundant information for measuring components and molecular structure in the early detection and diagnosis of breast cancer. Currently, portable Raman spectrometers have simplified and made equipment application more affordable, albeit at the cost of sacrificing the signal-to-noise ratio (SNR). Consequently, this necessitates a higher recognition rate from pattern recognition algorithms. Our study employs a feature fusion strategy to reduce the dimensionality of high-dimensional Raman spectra and enhance the discriminative information between normal tissues and tumors. In the conducted random experiment, the classifier achieved a performance of over 96% for all three average metrics: accuracy, sensitivity, and specificity. Additionally, we propose a multi-parameter serial encoding evolutionary algorithm (MSEA) and integrate it into the Adaptive Local Hyperplane K-nearest Neighbor classification algorithm (ALHK) for adaptive hyperparameter optimization. The implementation of serial encoding tackles the predicament of parallel optimization in multi-hyperparameter vector problems. To bolster the convergence of the optimization algorithm towards a global optimal solution, an exponential viability function is devised for nonlinear processing. Moreover, an improved elitist strategy is employed for individual selection, effectively eliminating the influence of probability factors on the robustness of the optimization algorithm. This study further optimizes the hyperparameter space through sensitivity analysis of hyperparameters and cross-validation experiments, leading to superior performance compared to the ALHK algorithm with manual hyperparameter configuration.

Simple, Fast and Convenient Magnetic Bead-Based Sample Preparation for Detecting Viruses via Raman-Spectroscopy

We introduce a magnetic bead-based sample preparation scheme for enabling the Raman spectroscopic differentiation of severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2)-positive and -negative samples. The beads were functionalized with the angiotensin-converting enzyme 2 (ACE2) receptor protein, which is used as a recognition element to selectively enrich SARS-CoV-2 on the surface of the magnetic beads. The subsequent Raman measurements directly enable discriminating SARS-CoV-2-positive and -negative samples. The proposed approach is also applicable for other virus species when the specific recognition element is exchanged. A series of Raman spectra were measured on three types of samples, namely SARS-CoV-2, Influenza A H1N1 virus and a negative control. For each sample type, eight independent replicates were considered. All of the spectra are dominated by the magnetic bead substrate and no obvious differences between the sample types are apparent. In order to address the subtle differences in the spectra, we calculated different correlation coefficients, namely the Pearson coefficient and the Normalized cross correlation coefficient. By comparing the correlation with the negative control, differentiating between SARS-CoV-2 and Influenza A virus is possible. This study provides a first step towards the detection and potential classification of different viruses with the use of conventional Raman spectroscopy.

Raman and fourier transform infrared spectroscopy techniques for detection of coronavirus (COVID-19): a mini review

Coronavirus pandemic has been a huge jeopardy to human health in various systems since it outbroke, early detection and prevention of further escalation has become a priority. The current popular approach is to collect samples using the nasopharyngeal swab method and then test for RNA using the real-time polymerase chain reaction, which suffers from false-positive results and a longer diagnostic time scale. Alternatively, various optical techniques, namely, optical sensing, spectroscopy, and imaging shows a great promise in virus detection. In this mini review, we briefly summarize the development progress of vibrational spectroscopy techniques and its applications in the detection of SARS-CoV family. Vibrational spectroscopy techniques such as Raman spectroscopy and infrared spectroscopy received increasing appreciation in bio-analysis for their speediness, accuracy and cost-effectiveness in detection of SARS-CoV. Further, an account of emerging photonics technologies of SARS-CoV-2 detection and future possibilities is also explained. The progress in the field of vibrational spectroscopy techniques for virus detection unambiguously show a great promise in the development of rapid photonics-based devices for COVID-19 detection.

Intelligent convolution neural network-assisted SERS to realize highly accurate identification of six pathogenic Vibrio

Based on label-free SERS technology, the relationship between the Raman signals of pathogenic Vibrio microorganisms and purine metabolites was analyzed in detail. A deep learning CNN model was successfully developed, achieving a high accuracy rate of 99.7% in the identification of six typical pathogenic Vibrio species within 15 minutes, providing a new method for pathogen identification.

Raman Scattering-Based Optical Sensing Of Chronic Liver Diseases

Chronic liver diseases (CLDs) are a major public health problem. Despite the progress achieved in fighting against viral hepatitis, the emergence of non-alcoholic fatty liver disease might pose a serious challenge to the public's health in the coming decades. Medical management of CLDs represents a substantial burden on the public health infrastructures. The health care cost of these diseases is an additional burden that weighs heavily on the economies of developing countries. Effective management of CLDs requires the adoption of reliable and cost-effective screening and diagnosing methods to ensure early detection and accurate clinical assessment of these diseases. Vibrational spectroscopies have emerged as universal analytical methods with promising applications in various industrial and biomedical fields. These revolutionary analytical techniques rely on analyzing the interaction between a light beam and the test sample to generate a spectral fingerprint. This latter is defined by the analyte's chemical structure and the molecular vibrations of its functional groups. Raman spectroscopy and surface-enhanced Raman spectroscopy have been used in combination with various chemometric tests to diagnose a wide range of malignant, metabolic and infectious diseases. The aim of the current review is to cast light on the use of these optical sensing methods in the diagnosis of CLDs. The vast majority of research works that investigated the potential application of these spectroscopic techniques in screening and detecting CLDs were discussed here. The advantages and limitations of these modern analytical methods, as compared with the routine and gold standard diagnostic approaches, were also reviewed in details.

Accuracy of Raman spectroscopy in the diagnosis of Alzheimer's disease

Objective

To systematically evaluate the accuracy of Raman spectroscopy in the diagnosis of Alzheimer's disease.

Methods

Databases including Web of Science, PubMed, The Cochrane Library, EMbase, CBM, CNKI, Wan Fang Data, and VIP were electronically searched for studies on Raman spectroscopy in diagnosis of Alzheimer's disease from inception to November 2022. Two reviewers independently screened the literature, extracted data, and assessed the risk of bias in the included studies. Then, meta-analysis was performed using Meta-Disc1.4 and Stata 16.0 software.

Results

A total of eight studies were finally included. The pooled sensitivity of Raman spectroscopy was 0.86 [95% CI (0.80–0.91)], specificity was 0.87 [95% CI (0.79–0.92)], positive likelihood ratio was 5.50 [95% CI (3.55–8.51)], negative likelihood ratio was 0.17 [95% CI (0.09–0.34)], diagnosis odds ratio and area under the curve of SROC were 42.44 [95% CI (19.80–90.97)] and 0.931, respectively. Sensitivity analysis was carried out after each study was excluded one by one, and the results showed that pooled sensitivity and specificity had no significant change, indicating that the stability of the meta-analysis results was great.

Conclusions

Our findings indicated that Raman spectroscopy had high accuracy in the diagnosis of AD, though it still did not rule out the possibility of misdiagnosis and missed diagnosis. Limited by the quantity and quality of the included studies, the above conclusions need to be verified by more high-quality studies.

Serum Raman spectroscopy combined with convolutional neural network for rapid diagnosis of HER2-positive and triple-negative breast cancer

Breast cancer is common in women, and its number of patients ranks first among female malignant tumors. Breast cancer is highly heterogeneous, and different types of breast cancer have different biological behaviors and prognoses. Therefore, identifying the different types of breast cancer is of great help in formulating individualized treatment plans. Based on serum Raman spectroscopy and deep learning algorithms, we propose a fast and low-cost diagnosis method for screening triple-negative breast cancer, human epidermal growth factor receptor 2 (HER2)-positive breast cancer, and healthy controls. We collected 75 serum samples in this study, including 23 triple-negative breast cancers, 22 HER2-positive breast cancers, and 30 healthy controls. Using the preprocessed Raman spectra as the input of deep learning, three deep learning models, neural network language model (NNLM), bidirectional long-short-term memory network (BiLSTM), and convolutional neural network (CNN), were established, and the accuracy rates of the three models were 87.78%, 90.37%, and 91.11%, respectively. The experimental results demonstrate the feasibility of serum Raman spectroscopy combined with deep learning algorithms to diagnose breast cancer, which can be used as an effective auxiliary diagnosis method for breast cancer.

Recent Development in Plasmonic Nanobiosensors for Viral DNA/RNA Biomarkers

Recently, due to the coronavirus pandemic, the need for early diagnosis of infectious diseases, including viruses, is emerging. Though early diagnosis is essential to prevent infection and progression to severe illness, there are few technologies that accurately measure low concentrations of biomarkers. Plasmonic nanomaterials are attracting materials that can effectively amplify various signals, including fluorescence, Raman, and other optical and electromagnetic output. In this review, we introduce recently developed plasmonic nanobiosensors for measuring viral DNA/RNA as potential biomarkers of viral diseases. In addition, we discuss the future perspective of plasmonic nanobiosensors for DNA/RNA detection. This review is expected to help the early diagnosis and pathological interpretation of viruses and other diseases.

Characterizing viral samples using machine learning for Raman and absorption spectroscopy

Machine learning methods can be used as robust techniques to provide invaluable information for analyzing biological samples in pharmaceutical industries, such as predicting the concentration of viral particles of interest in biological samples. Here, we utilized both convolutional neural networks (CNNs) and random forests (RFs) to predict the concentration of the samples containing measles, mumps, rubella, and varicella-zoster viruses (ProQuad®) based on Raman and absorption spectroscopy. We prepared Raman and absorption spectra data sets with known concentration values, then used the Raman and absorption signals individually and together to train RFs and CNNs. We demonstrated that both RFs and CNNs can make predictions with R2 values as high as 95%. We proposed two different networks to jointly use the Raman and absorption spectra, where our results demonstrated that concatenating the Raman and absorption data increases the prediction accuracy compared to using either Raman or absorption spectrum alone. Additionally, we further verified the advantage of using joint Raman-absorption with principal component analysis. Furthermore, our method can be extended to characterize properties other than concentration, such as the type of viral particles.

Development of multivariate classification models for the diagnosis of dengue virus infection

The dengue virus (DENV) infection is a worldwide cause of serious illness and death. Early and efficient prediction of disease may help in proper medical management to control disease. Keeping this in view, multivariate classification models by combining with Raman spectroscopy have been developed for the diagnosis of DENV infection in human blood sera. For study design, a statistical analysis is performed to select the sample size for training of models. Total 1240 Raman spectra have been acquired from 39 DENV infected and 23 healthy sera samples. Prior to model development, Raman spectra were examined using ANOVA test for significant differences present in the intensities of newly appeared Raman bands at 622, 645, 700, 746, 800, 814, 873, 890, 948, 1002, 1018, 1080, 1235, 1250, 1272, 1386, 1404, 1446, 1609 and 1645 cm^-1. The significant differences and characteristic patterns of Raman bands induced by disease played decisive role and are exploited for development of multivariate model. Classification models are developed by utilizing principal component analysis (PCA) to extract discriminant features from multidimensional Raman spectral dataset and followed by support vector machines (SVM) with Polynomial of 5, RBF, and liner kernels. The proposed model for this study is built using 10-fold cross validation technique and evaluated on independent dataset to demonstrate its robustness. PCA-SVM (poly-5) model successfully yielded high diagnostic accuracy of 99.52%, sensitivity of 99.75%, specificity of 99.09% for classification of unknown suspected samples. For comparison, PCA discriminant analysis (PCA-DA), partial least squares regression (PLSR) are PLS-DA have been compared. It is found that PCA-SVM (poly-5) approach is more effective and robust compared to other state-of-the-art approaches and it can be used for clinical prediction of DENV infection in human blood sera.

Noninvasive cholangitis and cholangiocarcinoma screening based on serum Raman spectroscopy and support vector machine

The feasibility of serum Raman spectroscopy for rapid screening of cholangitis and cholangiocarcinoma (CCA) was explored Raman spectra were collected from 49 patients with cholangitis, 38 patients with CCA, and 55 healthy volunteers. Normalized mean Raman spectra and spectral attributions reveal disease-specific biomolecular differences. Support vector machine (SVM) was used to establish the two-way (cholangitis vs healthy, CCA vs healthy etc.) and 3-way (cholangitis vs CCA vs healthy) classification model, and leave-one-out cross-validation (LOOCV) was used to verify these models' performance. Based on the support vector machine algorithm, serum Raman spectroscopy could identify cholangitis and CCA. Its diagnostic sensitivity, and specificity were 89.80%, 94.55%, and 89.50%, 98.18%, respectively. This study demonstrates that label-free serum Raman spectroscopy analysis technique combined with SVM diagnostic algorithm has great potential for noninvasive cholangitis and CCA screening.

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.

Diagnosing COVID-19 in human serum using Raman spectroscopy

This study proposed the diagnosis of COVID-19 by means of Raman spectroscopy. Samples of blood serum from 10 patients positive and 10 patients negative for COVID-19 by RT-PCR RNA and ELISA tests were analyzed. Raman spectra were obtained with a dispersive Raman spectrometer (830 nm, 350 mW) in triplicate, being submitted to exploratory analysis with principal component analysis (PCA) to identify the spectral differences and discriminant analysis with PCA (PCA-DA) and partial least squares (PLS-DA) for classification of the blood serum spectra into Control and COVID-19. The spectra of both groups positive and negative for COVID-19 showed peaks referred to the basal constitution of the serum (mainly albumin). The difference spectra showed decrease in the peaks referred to proteins and amino acids for the group positive. PCA variables showed more detailed spectral differences related to the biochemical alterations due to the COVID-19 such as increase in lipids, nitrogen compounds (urea and amines/amides) and nucleic acids, and decrease of proteins and amino acids (tryptophan) in the COVID-19 group. The discriminant analysis applied to the principal component loadings (PC2, PC4, PC5, and PC6) could classify spectra with 87% sensitivity and 100% specificity compared to 95% sensitivity and 100% specificity indicated in the RT-PCR kit leaflet, demonstrating the possibilities of a rapid, label-free, and costless technique for diagnosing COVID-19 infection.

Diagnosis of dengue virus infection using spectroscopic images and deep learning

Dengue virus (DENV) infection is one of the major health issues and a substantial epidemic infectious human disease. More than two billion humans are living in dengue susceptible regions with annual infection mortality rate is about 5%-20%. At initial stages, it is difficult to differentiate dengue virus symptoms with other similar diseases. The main objective of this research is to diagnose dengue virus infection in human blood sera for better treatment and rehabilitation process. A novel and robust approach is proposed based on Raman spectroscopy and deep learning. In this regard, the ResNet101 deep learning model is modified by exploiting transfer learning (TL) concept on Raman spectroscopic data of human blood sera. Sample size was selected using standard statistical tests. The proposed model is evaluated on 2,000 Raman spectra images in which 1,200 are DENV-infected of human blood sera samples, and 800 are healthy ones. It offers 96.0% accuracy on testing data for DENV infection diagnosis. Moreover, the developed approach demonstrated minimum improvement of 6.0% and 7.0% in terms of AUC and Kappa index respectively over the other state-of-the-art techniques. The developed model offers superior performance to capture minute Raman spectral variations due to the better residual learning capability and generalization ability compared to others deep learning models. The developed model revealed that it might be applied for diagnosis of DENV infection to save precious human lives.

Rapid Biomarker Screening of Alzheimer's Disease by Interpretable Machine Learning and Graphene-Assisted Raman Spectroscopy

The study of Alzheimer's disease (AD), the most common cause of dementia, faces challenges in terms of understanding the cause, monitoring the pathogenesis, and developing early diagnoses and effective treatments. Rapid and accurate identification of AD biomarkers in the brain is critical to providing key insights into AD and facilitating the development of early diagnosis methods. In this work, we developed a platform that enables a rapid screening of AD biomarkers by employing graphene-assisted Raman spectroscopy and machine learning interpretation in AD transgenic animal brains. Specifically, we collected Raman spectra on slices of mouse brains with and without AD and used machine learning to classify AD and non-AD spectra. By contacting monolayer graphene with the brain slices, the accuracy was increased from 77% to 98% in machine learning classification. Further, using a linear support vector machine (SVM), we identified a spectral feature importance map that reveals the importance of each Raman wavenumber in classifying AD and non-AD spectra. Based on this spectral feature importance map, we identified AD biomarkers including Aβ and tau proteins and other potential biomarkers, such as triolein, phosphatidylcholine, and actin, which have been confirmed by other biochemical studies. Our Raman-machine learning integrated method with interpretability will facilitate the study of AD and can be extended to other tissues and biofluids and for various other diseases.

Label-Free Differentiation of Cancer and Non-Cancer Cells Based on Machine-Learning-Algorithm-Assisted Fast Raman Imaging

This paper proposes a rapid, label-free, and non-invasive approach for identifying murine cancer cells (B16F10 melanoma cancer cells) from non-cancer cells (C2C12 muscle cells) using machine-learning-assisted Raman spectroscopic imaging. Through quick Raman spectroscopic imaging, a hyperspectral data processing approach based on machine learning methods proved capable of presenting the cell structure and distinguishing cancer cells from non-cancer muscle cells without compromising full-spectrum information. This study discovered that biomolecular information-nucleic acids, proteins, and lipids-from cells could be retrieved efficiently from low-quality hyperspectral Raman datasets and then employed for cell line differentiation.

Surface-enhanced Raman spectroscopic analysis of centrifugally filtered HBV serum samples

BACKGROUND

Raman spectroscopy is an effective tool for detecting and discriminating centrifugally filtered hepatitis B virus serum and centrifugally filtered  control serum.

OBJECTIVES

The purpose of current study is to separate high molecular weight fractions from low molecular weight fractions present hepatitis B serum to increase the disease diagnostic ability of surface enhanced Raman spectroscopy (SERS).

METHODS

Clinically diagnosed centrifugally filtered serum samples of hepatitis B patients are subjected for surface enhanced Raman spectroscopy (SERS) in comparison with centrifugally filtered serum samples of healthy individuals by using silver nanoparticles (Ag-NPs) as SERS substrates. Some SERS spectral features are solely observed in centrifugally filtered serum samples of hepatitis B and some SERS spectral are solely observed in centrifugally filtered serum samples of healthy individuals. The diagnostic ability of SERS is further enhanced with different statistical techniques like principal component analysis (PCA), partial least square discriminant analysis (PLS-DA) and partial least square regression analysis (PLSR) have applied.

RESULTS

The disease biomarkers of hepatitis B are more pronounced after their centrifugation as compared with uncentrifuged form. Statistical tools like principal component analysis (PCA) and partial least square discriminant analysis (PLS-DA) clearly differentiated centrifugally filtered serum samples of hepatitis B from centrifugally filtered serum samples of healthy individuals. Furthermore, partial least square regression analysis (PLSR) has been applied for predicting unknown viral load of centrifugally filtered serum sample of hepatitis B.

CONCLUSION

SERS technique along with chemometric tools have successfully differentiated centrifugally filtered serum samples of hepatitis B from centrifugally filtered serum samples of healthy individuals. The centrifugal filtration process has increased the differentiation accuracy of PLS-DA in terms of percentage 98% and regression accuracy of PLSR regression analysis in terms of RMSEP (0.30 IU/mL) of this diagnostic method as compared with that of uncentrifuged method.

Diagnosing COVID-19 in human serum using Raman spectroscopy

This study proposed the diagnosis of COVID-19 by means of Raman spectroscopy. Samples of blood serum from 10 patients positive and 10 patients negative for COVID-19 by RT-PCR RNA and ELISA tests were analyzed. Raman spectra were obtained with a dispersive Raman spectrometer (830 nm, 350 mW) in triplicate, being submitted to exploratory analysis with principal component analysis (PCA) to identify the spectral differences and discriminant analysis with PCA (PCA-DA) and partial least squares (PLS-DA) for classification of the blood serum spectra into Control and COVID-19. The spectra of both groups positive and negative for COVID-19 showed peaks referred to the basal constitution of the serum (mainly albumin). The difference spectra showed decrease in the peaks referred to proteins and amino acids for the group positive. PCA variables showed more detailed spectral differences related to the biochemical alterations due to the COVID-19 such as increase in lipids, nitrogen compounds (urea and amines/amides) and nucleic acids, and decrease of proteins and amino acids (tryptophan) in the COVID-19 group. The discriminant analysis applied to the principal component loadings (PC2, PC4, PC5, and PC6) could classify spectra with 87% sensitivity and 100% specificity compared to 95% sensitivity and 100% specificity indicated in the RT-PCR kit leaflet, demonstrating the possibilities of a rapid, label-free, and costless technique for diagnosing COVID-19 infection.

Raman spectroscopic analysis of skin as a diagnostic tool for Human African Trypanosomiasis

Human African Trypanosomiasis (HAT) has been responsible for several deadly epidemics throughout the 20th century, but a renewed commitment to disease control has significantly reduced new cases and motivated a target for the elimination of Trypanosoma brucei gambiense-HAT by 2030. However, the recent identification of latent human infections, and the detection of trypanosomes in extravascular tissues hidden from current diagnostic tools, such as the skin, has added new complexity to identifying infected individuals. New and improved diagnostic tests to detect Trypanosoma brucei infection by interrogating the skin are therefore needed. Recent advances have improved the cost, sensitivity and portability of Raman spectroscopy technology for non-invasive medical diagnostics, making it an attractive tool for gambiense-HAT detection. The aim of this work was to assess and develop a new non-invasive diagnostic method for T. brucei through Raman spectroscopy of the skin. Infections were performed in an established murine disease model using the animal-infective Trypanosoma brucei brucei subspecies. The skin of infected and matched control mice was scrutinized ex vivo using a confocal Raman microscope with 532 nm excitation and in situ at 785 nm excitation with a portable field-compatible instrument. Spectral evaluation and Principal Component Analysis confirmed discrimination of T. brucei-infected from uninfected tissue, and a characterisation of biochemical changes in lipids and proteins in parasite-infected skin indicated by prominent Raman peak intensities was performed. This study is the first to demonstrate the application of Raman spectroscopy for the detection of T. brucei by targeting the skin of the host. The technique has significant potential to discriminate between infected and non-infected tissue and could represent a unique, non-invasive diagnostic tool in the goal for elimination of gambiense-HAT as well as for Animal African Trypanosomiasis (AAT).

Human African Trypanosomiasis (HAT), also known as sleeping sickness, is a disease caused by the parasite Trypanosoma brucei and has been responsible for the death of millions of people across Africa in the 20^th century. It is also a major economic burden for countries endemic for trypanosomiasis, affecting livestock productivity in rural areas (Animal African Trypanosomiasis). A long-term international collaboration with the help of the World Health Organisation has resulted in the rate of human infection decreasing to less than 1000 new cases per year. However, the human disease continues to spread within remote villages. Current diagnosis is based on the detection of parasites in blood and serum samples, but this is challenging during chronic human infections with low or non-detectable parasitaemia. However, the recent discovery of extravascular skin-dwelling trypanosomes indicates that a reservoir of infection remains undetected, threatening the effort to eliminate the disease. In this study we have targeted the skin as a site for diagnosis using Raman spectroscopy and demonstrate that this method showed great promise in the laboratory, laying the foundation for field studies to examine its potential to strengthen current diagnostic strategies for detecting HAT cases.

Roadmap on Universal Photonic Biosensors for Real-Time Detection of Emerging Pathogens

The COVID-19 pandemic has made it abundantly clear that the state-of-the-art biosensors may not be adequate for providing a tool for rapid mass testing and population screening in response to newly emerging pathogens. The main limitations of the conventional techniques are their dependency on virus-specific receptors and reagents that need to be custom-developed for each recently-emerged pathogen, the time required for this development as well as for sample preparation and detection, the need for biological amplification, which can increase false positive outcomes, and the cost and size of the necessary equipment. Thus, new platform technologies that can be readily modified as soon as new pathogens are detected, sequenced, and characterized are needed to enable rapid deployment and mass distribution of biosensors. This need can be addressed by the development of adaptive, multiplexed, and affordable sensing technologies that can avoid the conventional biological amplification step, make use of the optical and/or electrical signal amplification, and shorten both the preliminary development and the point-of-care testing time frames. We provide a comparative review of the existing and emergent photonic biosensing techniques by matching them to the above criteria and capabilities of preventing the spread of the next global pandemic.

Analysis of Raman Spectra by Using Deep Learning Methods in the Identification of Marine Pathogens

The need for efficient and accurate identification of pathogens in seafood and the environment has become increasingly urgent, given the current global pandemic. Traditional methods are not only time consuming but also lead to sample wastage. Here, we have proposed two new methods that involve Raman spectroscopy combined with a long short-term memory (LSTM) neural network and compared them with a method using a normal convolutional neural network (CNN). We used eight strains isolated from the marine organism Urechis unicinctus, including four kinds of pathogens. After the models were configured and trained, the LSTM methods that we proposed achieved average isolation-level accuracies exceeding 94%, not only meeting the requirement for identification but also indicating that the proposed methods were faster and more accurate than the normal CNN models. Finally, through a computational approach, we designed a loss function to explore the mechanism reflected by the Raman data, finding the Raman segments that most likely exhibited the characteristics of nucleic acids. These novel experimental results provide insights for developing additional deep learning methods to accurately analyze complex Raman data.

Characterization and prediction of viral loads of Hepatitis B serum samples by using surface-enhanced Raman spectroscopy (SERS)

BACKGROUND

Raman spectroscopy is a promising technique to analyze the body fluids for the purpose of non-invasive disease diagnosis.

OBJECTIVES

To develop a surface-enhanced Raman spectroscopy (SERS) based method for qualitative and quantitative analysis of hepatitis B viral (HBV) infection from blood serum samples.

METHODS

Clinically diagnosed hepatitis B virus (HBV) infected serum samples of patients of different levels of viral loads have been subjected for SERS analysis in comparison with the healthy ones by using silver nanoparticles (Ag NPs) based SERS substrates. The SERS measurements were performed on blood serum samples of 11 healthy and 32 clinically diagnosed HBV patients of different viral load levels of different exponentials including (10¹, 10² called as low level), (10³, 10⁴ called as medium level) and (10⁵, 10⁸ called as high level). Furthermore, multivariate data analysis techniques, Principal Component Analysis (PCA) and Partial Least Square Regression (PLSR) were also performed on SERS spectral data.

RESULTS

The SERS spectral features due to biochemical changes in HBV positive serum samples associated with the increasing viral loads were established which could be employed for HBV diagnostic purpose. PCA was found helpful for the differentiation between SERS spectral data of serum samples of different levels of HBV infection and healthy individuals. PLSR model developed with standard samples of known viral loads for predicting the viral loads of blind/unknown samples with 99% predicted accuracy.

CONCLUSION

SERS can be employed for qualitative and quantitative analysis of HBV infection from blood serum samples.

Onsite real-time detection of covid-like-virus transmission through air using spark-induced plasma spectroscopy

In March 2020, COVID-19 was officially classified as a pandemic and as a consequence people have adopted strenuous measures to prevent infection, such as the wearing of PPE and self-quarantining, with no knowledge of when the measures will no longer be necessary. Coronavirus has long been known to be non-infectious when airborne; however, studies are starting to show that the virus can infect through airborne transmission and can remain airborne for a significant period of time. In the present study, a spark-induced plasma spectroscopy was devised to characterize the air propagation of the virus in real-time. The risk of air propagation was evaluated in terms of changes in virus concentration with respect to distance traveled and measurement time. Thus, our study provides a benchmark for performing real-time detection of virus propagation and instantaneous monitoring of coronavirus in the air.

Rapid noninvasive screening of cerebral ischemia and cerebral infarction based on tear Raman spectroscopy combined with multiple machine learning algorithms

Researchers have established a classification model based on tear Raman spectroscopy combined with machine learning classification algorithms, which realizes rapid noninvasive classification of cerebral infarction and cerebral ischemia, which is of great significance for clinical medical diagnosis. Through spectral data analysis, it is found that there are differences in the content of tyrosine, phenylalanine, and carotenoids in the tears of patients with cerebral ischemia and patients with cerebral infarction. We try to establish a classification model for rapid noninvasive screening of cerebral infarction and cerebral ischemia through these differences. The experiment has four parts, including normalization, data enhancement, feature extraction, and data classification. The researchers combined three feature extraction methods with four machine classification models to build a total of 12 classification models. Integrating 8 classification criteria, the classification accuracy of all models is above 85%, especially PLS-PNN has achieved 100% accuracy and better running time. The experimental results show that tear Raman spectroscopy combined with machine learning classification model has a good effect on the screening of cerebral ischemia and cerebral infarction, which is conducive to the noninvasive and rapid clinical diagnosis of cerebrovascular diseases in the future.

An efficient primary screening of COVID-19 by serum Raman spectroscopy

The outbreak of COVID-19 coronavirus disease around the end of 2019 has become a pandemic. The preferred method for COVID-19 detection is the real-time polymerase chain reaction (RT-PCR)-based technique; however, it also has certain limitations, such as sample-dependent procedures with a relatively high false negative ratio. We propose a safe and efficient method for screening COVID-19 based on Raman spectroscopy. A total of 177 serum samples are collected from 63 confirmed COVID-19 patients, 59 suspected cases, and 55 healthy individuals as a control group. Raman spectroscopy is adopted to analyze these samples, and a machine learning support-vector machine (SVM) method is applied to the spectrum dataset to build a diagnostic algorithm. Furthermore, 20 independent individuals, including 5 asymptomatic COVID-19 patients and 5 symptomatic COVID-19 patients, 5 suspected patients, and 5 healthy patients, were sampled for external validation. In these three groups-confirmed COVID-19, suspected, and healthy individuals-the distribution of statistically significant points of difference showed highly consistency for intergroups after repeated sampling processes. The classification accuracy between the COVID-19 cases and the suspected cases is 0.87 (95% confidence interval [CI]: 0.85-0.88), and the accuracy between the COVID-19 and the healthy controls is 0.90 (95% CI: 0.89-0.91), while the accuracy between the suspected cases and the healthy control group is 0.68 (95% CI: 0.67-0.73). For the independent test dataset, we apply the obtained SVM model to the classification of the independent test dataset to have all the results correctly classified. Our model showed that the serum-level classification results were all correct for independent test dataset. Our results suggest that Raman spectroscopy could be a safe and efficient technique for COVID-19 screening.

Recognition of chronic renal failure based on Raman spectroscopy and convolutional neural network

PURPOSE

Chronic renal failure (CRF) is a disease with a high morbidity rate that can develop into uraemia, resulting in a series of complications, such as dyspnoea, mental disorders, hypertension, and heart failure. CRF may be controlled clinically by drug intervention. Therefore, early diagnosis and control of the disease are of great significance for the treatment and prevention of chronic renal failure. Based on the complexity of CRF diagnosis, this study aims to explore a new rapid and noninvasive diagnostic method.

METHODS

In this experiment, the serum Raman spectra of samples from 47 patients with CRF and 53 normal subjects were obtained. In this study, Serum Raman spectra of healthy and CRF patients were identified by a Convolutional Neural Network (CNN) and compared with the results of identified by an Improved AlexNet. In addition, different amplitude of noise were added to the spectral data of the samples to explore the influence of a small random noise on the experimental results.

RESULTS

A CNN and an Improved AlexNet was used to classify the spectra, and the accuracy was 79.44 % and 95.22 % respectively. And the addition of noise did not significantly interfere with the classification accuracy.

CONCLUSION

The accuracy of CNN of this study can be as high as 95.22 %, which greatly improves its accuracy and reliability, compared to 89.7 % in the previous study. The results of this study show that the combination of serum Raman spectrum and CNN can be used in the diagnosis of CRF, and small random noise will not cause serious interference to the data analysis results.

Recent Advances of Hepatitis B Detection towards Paper-Based Analytical Devices

Hepatitis B virus (HBV) still remains a major global public health problem. One-half to one-third of the total HBV infected people died due to late detection of HBV. Serological antigen and viral HBV detections can help in the diagnosis, referral, and treatment of HBV. Available methods for HBV detection mostly used bulky instruments. Miniaturization of devices for HBV detection has been started by narrowing down the size of the devices. Several methods have also been proposed to increase the selectivity and sensitivity of the miniaturized methods, such as sandwich recognition of the biomarkers and the use of nano- to micro-sized materials. This review presents recent HBV detections in the last two decades from laboratory-based instruments towards microfluidic paper-based analytical devices (µPADs) for point-of-care testing (POCT) purposes. Early and routine analysis to detect HBV as early as possible could be achieved by POCT, especially for areas with limited access to a central laboratory and/or medical facilities.

Applicability of Raman spectroscopy on porcine parvovirus and porcine circovirus type 2 detection

Porcine parvovirus (PPV) is one of the major infectious causes of reproductive failure of swine. This disease is characterized by embryonic and fetal infection and death, responsible for important economic losses. PPV is also implicated as a trigger in the development of post-weaning multisystemic wasting syndrome (PMWS) caused by Porcine circovirus type 2 (PCV2). Their detection is PCR-based, which is quite sensitive and specific, but laborious, costly and time-demanding. Therefore, this study aimed to assess Raman spectroscopy (RS) as a diagnostic tool for PPV and PCV2 due to its label-free properties and unique ability to search and identify molecular fingerprints. Briefly, swine testis (ST) cells were inoculated with PPV or PCV2 and in vitro cultured (37 °C, 5% CO₂) for four days. Fixed cells were then submitted to RS investigation using a 633 nm laser. A total of 225 spectra centered at 1300 cm^-1 was obtained for each sample (5 spectra/cell; 15 cells/replicate; 3 replicates) of PPV-, PCV2-infected and uninfected (control) ST cells. Clear statistical discrimination between samples from both virus-infected cells was achieved with a Principal Component - Linear Discriminant Analysis (PCA-LDA) model, reaching sensitivity rates from 95.55% to 97.77%, respectively to PCV2- and PPV-infected cells. These results were then submitted to a Leave-One-Out (LOO) validation algorithm resulting in 99.97% of accuracy. Extensive band assignment was analyzed and compiled for better understanding of PPV and PCV2 virus-cell interaction, demonstrating that specific protein, lipids and DNA/RNA bands are the most important assignments related to discrimination of virus-infected from uninfected cells. In conclusion, these results represent promising bases for RS application on PCV2 and PPV detection for future diagnostic applications.

Towards development of a novel universal medical diagnostic method: Raman spectroscopy and machine learning

This review summarizes recent progress made using Raman spectroscopy and machine learning for potential universal medical diagnostic applications.