SERS-based biosensor for Alzheimer disease evaluation through the fast analysis of human serum

Unveiling brain disorders using liquid biopsy and Raman spectroscopy

Brain disorders, including neurodegenerative diseases (NDs) and traumatic brain injury (TBI), present significant challenges in early diagnosis and intervention. Conventional imaging modalities, while valuable, lack the molecular specificity necessary for precise disease characterization. Compared to the study of conventional brain tissues, liquid biopsy, which focuses on blood, tear, saliva, and cerebrospinal fluid (CSF), also unveils a myriad of underlying molecular processes, providing abundant predictive clinical information. In addition, liquid biopsy is minimally- to non-invasive, and highly repeatable, offering the potential for continuous monitoring. Raman spectroscopy (RS), with its ability to provide rich molecular information and cost-effectiveness, holds great potential for transformative advancements in early detection and understanding the biochemical changes associated with NDs and TBI. Recent developments in Raman enhancement technologies and advanced data analysis methods have enhanced the applicability of RS in probing the intricate molecular signatures within biological fluids, offering new insights into disease pathology. This review explores the growing role of RS as a promising and emerging tool for disease diagnosis in brain disorders, particularly through the analysis of liquid biopsy. It discusses the current landscape and future prospects of RS in the diagnosis of brain disorders, highlighting its potential as a non-invasive and molecularly specific diagnostic tool.

Unlocking Preclinical Alzheimer's: A Multi-Year Label-Free In Vitro Raman Spectroscopy Study Empowered by Chemometrics

Alzheimer's disease is a progressive neurodegenerative disorder, the early detection of which is crucial for timely intervention and enrollment in clinical trials. However, the preclinical diagnosis of Alzheimer's encounters difficulties with gold-standard methods. The current definitive diagnosis of Alzheimer's still relies on expensive instrumentation and post-mortem histological examinations. Here, we explore label-free Raman spectroscopy with machine learning as an alternative to preclinical Alzheimer's diagnosis. A special feature of this study is the inclusion of patient samples from different cohorts, sampled and measured in different years. To develop reliable classification models, partial least squares discriminant analysis in combination with variable selection methods identified discriminative molecules, including nucleic acids, amino acids, proteins, and carbohydrates such as taurine/hypotaurine and guanine, when applied to Raman spectra taken from dried samples of cerebrospinal fluid. The robustness of the model is remarkable, as the discriminative molecules could be identified in different cohorts and years. A unified model notably classifies preclinical Alzheimer's, which is particularly surprising because of Raman spectroscopy's high sensitivity regarding different measurement conditions. The presented results demonstrate the capability of Raman spectroscopy to detect preclinical Alzheimer's disease for the first time and offer invaluable opportunities for future clinical applications and diagnostic methods.

Machine learning-assisted serum SERS strategy for rapid and non-invasive screening of early cystic echinococcosis

Early and accurate diagnosis of cystic echinococcosis (CE) with existing technologies is still challenging. Herein, we proposed a novel strategy based on the combination of label-free serum surface-enhanced Raman scattering (SERS) spectroscopy and machine learning for rapid and non-invasive diagnosis of early-stage CE. Specifically, by establishing early- and middle-stage mouse models, the corresponding CE-infected and normal control serum samples were collected, and silver nanoparticles (AgNPs) were utilized as the substrate to obtain SERS spectra. The early- and middle-stage discriminant models were developed using a support vector machine, with diagnostic accuracies of 91.7% and 95.7%, respectively. Furthermore, by analyzing the serum SERS spectra, some biomarkers that may be related to early CE were found, including purine metabolites and protein-related amide bands, which was consistent with other biochemical studies. Thus, our findings indicate that label-free serum SERS analysis is a potential early-stage CE detection method that is promising for clinical translation.

Applications of Raman spectroscopy in the diagnosis and monitoring of neurodegenerative diseases

Raman scattering is an inelastic light scattering that occurs in a manner reflective of the molecular vibrations of molecular structures and chemical conditions in a given sample of interest. Energy changes in the scattered light can be assessed to determine the vibration mode and associated molecular and chemical conditions within the sample, providing a molecular fingerprint suitable for sample identification and characterization. Raman spectroscopy represents a particularly promising approach to the molecular analysis of many diseases owing to clinical advantages including its instantaneous nature and associated high degree of stability, as well as its ability to yield signal outputs corresponding to a single molecule type without any interference from other molecules as a result of its narrow peak width. This technology is thus ideally suited to the simultaneous assessment of multiple analytes. Neurodegenerative diseases represent an increasingly significant threat to global public health owing to progressive population aging, imposing a severe physical and social burden on affected patients who tend to develop cognitive and/or motor deficits beginning between the ages of 50 and 70. Owing to a relatively limited understanding of the etiological basis for these diseases, treatments are lacking for the most common neurodegenerative diseases, which include Alzheimer's disease, Parkinson's disease, Huntington's disease, and amyotrophic lateral sclerosis. The present review was formulated with the goal of briefly explaining the principle of Raman spectroscopy and discussing its potential applications in the diagnosis and evaluation of neurodegenerative diseases, with a particular emphasis on the research prospects of this novel technological platform.

Advancing Brain Research through Surface-Enhanced Raman Spectroscopy (SERS): Current Applications and Future Prospects

Surface-enhanced Raman spectroscopy (SERS) has recently emerged as a potent analytical technique with significant potential in the field of brain research. This review explores the applications and innovations of SERS in understanding the pathophysiological basis and diagnosis of brain disorders. SERS holds significant advantages over conventional Raman spectroscopy, particularly in terms of sensitivity and stability. The integration of label-free SERS presents promising opportunities for the rapid, reliable, and non-invasive diagnosis of brain-associated diseases, particularly when combined with advanced computational methods such as machine learning. SERS has potential to deepen our understanding of brain diseases, enhancing diagnosis, monitoring, and therapeutic interventions. Such advancements could significantly enhance the accuracy of clinical diagnosis and further our understanding of brain-related processes and diseases. This review assesses the utility of SERS in diagnosing and understanding the pathophysiological basis of brain disorders such as Alzheimer's and Parkinson's diseases, stroke, and brain cancer. Recent technological advances in SERS instrumentation and techniques are discussed, including innovations in nanoparticle design, substrate materials, and imaging technologies. We also explore prospects and emerging trends, offering insights into new technologies, while also addressing various challenges and limitations associated with SERS in brain research.

A Review on Integrated ZnO-Based SERS Biosensors and Their Potential in Detecting Biomarkers of Neurodegenerative Diseases

Surface-enhanced Raman spectroscopy (SERS) applications in clinical diagnosis and spectral pathology are increasing due to the potential of the technique to bio-barcode incipient and differential diseases via real-time monitoring of biomarkers in fluids and in real-time via biomolecular fingerprinting. Additionally, the rapid advancements in micro/nanotechnology have a visible influence in all aspects of science and life. The miniaturization and enhanced properties of materials at the micro/nanoscale transcended the confines of the laboratory and are revolutionizing domains such as electronics, optics, medicine, and environmental science. The societal and technological impact of SERS biosensing by using semiconductor-based nanostructured smart substrates will be huge once minor technical pitfalls are solved. Herein, challenges in clinical routine testing are addressed in order to understand the context of how SERS can perform in real, in vivo sampling and bioassays for early neurodegenerative disease (ND) diagnosis. The main interest in translating SERS into clinical practice is reinforced by the practical advantages: portability of the designed setups, versatility in using nanomaterials of various matter and costs, readiness, and reliability. As we will present in this review, in the frame of technology readiness levels (TRL), the current maturity reached by semiconductor-based SERS biosensors, in particular that of zinc oxide (ZnO)-based hybrid SERS substrates, is situated at the development level TRL 6 (out of 9 levels). Three-dimensional, multilayered SERS substrates that provide additional plasmonic hot spots in the z-axis are of key importance in designing highly performant SERS biosensors for the detection of ND biomarkers.

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.

Biochemical Characterization of Human Salivary Extracellular Vesicles as a Valuable Source of Biomarkers

Extracellular vesicles (EVs) are natural nanoparticles secreted under physiological and pathological conditions. Thanks to their diagnostic potential, EVs are increasingly being studied as biomarkers of a variety of diseases, including neurological disorders. To date, most studies on EV biomarkers use blood as the source, despite different disadvantages that may cause an impure isolation of the EVs. In the present article, we propose the use of saliva as a valuable source of EVs that could be studied as biomarkers in an easily accessible biofluid. Using a comparable protocol for the isolation of EVs from both liquid biopsies, salivary EVs showed greater purity in terms of co-isolates (evaluated by nanoparticle tracking analysis and Conan test). In addition, Raman spectroscopy was used for the identification of the overall biochemical composition of EVs coming from the two different biofluids. Even considering the limited amount of EVs that can be isolated from saliva, the use of Raman spectroscopy was not hampered, and it was able to provide a comprehensive characterization of EVs in a high throughput and repeatable manner. Raman spectroscopy can thus represent a turning point in the application of salivary EVs in clinics, taking advantage of the simple method of collection of the liquid biopsy and of the quick, sensitive and label-free biophotonics-based approach.

Raman Spectroscopy as a Tool to Study the Pathophysiology of Brain Diseases

The Raman phenomenon is based on the spontaneous inelastic scattering of light, which depends on the molecular characteristics of the dispersant. Therefore, Raman spectroscopy and imaging allow us to obtain direct information, in a label-free manner, from the chemical composition of the sample. Since it is well established that the development of many brain diseases is associated with biochemical alterations of the affected tissue, Raman spectroscopy and imaging have emerged as promising tools for the diagnosis of ailments. A combination of Raman spectroscopy and/or imaging with tagged molecules could also help in drug delivery and tracing for treatment of brain diseases. In this review, we first describe the basics of the Raman phenomenon and spectroscopy. Then, we delve into the Raman spectroscopy and imaging modes and the Raman-compatible tags. Finally, we center on the application of Raman in the study, diagnosis, and treatment of brain diseases, by focusing on traumatic brain injury and ischemia, neurodegenerative disorders, and brain cancer.

Review: Emerging Eye-Based Diagnostic Technologies for Traumatic Brain Injury

The study of ocular manifestations of neurodegenerative disorders, Oculomics, is a growing field of investigation for early diagnostics, enabling structural and chemical biomarkers to be monitored overtime to predict prognosis. Traumatic brain injury (TBI) triggers a cascade of events harmful to the brain, which can lead to neurodegeneration. TBI, termed the "silent epidemic" is becoming a leading cause of death and disability worldwide. There is currently no effective diagnostic tool for TBI, and yet, early-intervention is known to considerably shorten hospital stays, improve outcomes, fasten neurological recovery and lower mortality rates, highlighting the unmet need for techniques capable of rapid and accurate point-of-care diagnostics, implemented in the earliest stages. This review focuses on the latest advances in the main neuropathophysiological responses and the achievements and shortfalls of TBI diagnostic methods. Validated and emerging TBI-indicative biomarkers are outlined and linked to ocular neuro-disorders. Methods detecting structural and chemical ocular responses to TBI are categorised along with prospective chemical and physical sensing techniques. Particular attention is drawn to the potential of Raman spectroscopy as a non-invasive sensing of neurological molecular signatures in the ocular projections of the brain, laying the platform for the first tangible path towards alternative point-of-care diagnostic technologies for TBI.

Raman Spectroscopy on Brain Disorders: Transition from Fundamental Research to Clinical Applications

Brain disorders such as brain tumors and neurodegenerative diseases (NDs) are accompanied by chemical alterations in the tissues. Early diagnosis of these diseases will provide key benefits for patients and opportunities for preventive treatments. To detect these sophisticated diseases, various imaging modalities have been developed such as computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET). However, they provide inadequate molecule-specific information. In comparison, Raman spectroscopy (RS) is an analytical tool that provides rich information about molecular fingerprints. It is also inexpensive and rapid compared to CT, MRI, and PET. While intrinsic RS suffers from low yield, in recent years, through the adoption of Raman enhancement technologies and advanced data analysis approaches, RS has undergone significant advancements in its ability to probe biological tissues, including the brain. This review discusses recent clinical and biomedical applications of RS and related techniques applicable to brain tumors and NDs.

Gold nanoparticle decorated blu-ray digital versatile disc as a highly reproducible surface-enhanced Raman scattering substrate for detection and analysis of rotavirus RNA in laboratory environment

Detection and estimation of various biomolecular samples are often required in research and clinical laboratory applications. Present work demonstrates the functioning of a surface-enhanced Raman scattering (SERS) substrate that has been obtained by drop-casting of citrate-reduced gold nanoparticles (AuNPs) of average dimension of 23 nm on a bare blu-ray digital versatile disc (BR-DVD) substrate. The performance of the proposed SERS substrate has been initially evaluated with standard Raman active samples, namely malachite green (MG) and 1,2-bis(4-pyridyl)ethylene (BPE). The designed SERS substrate yields an average enhancement factor of 3.2 × 10⁶ while maintaining reproducibility characteristics as good as 94% over the sensing region of the substrate. The usability of the designed SERS substrate has been demonstrated through the detection and analysis of purified rotavirus double-stranded RNA (dsRNA) samples in the laboratory environment condition. Rotavirus RNA concentrations as low as 10 ng/μL could be detected with the proposed sensing scheme.

SERS liquid biopsy in breast cancer. What can we learn from SERS on serum and urine?

SERS analysis of biofluids, coupled with classification algorithms, has recently emerged as a candidate for point-of-care medical diagnosis. Nonetheless, despite the impressive results reported in the literature, there are still gaps in our knowledge of the biochemical information provided by the SERS analysis of biofluids. Therefore, by a critical assignment of the SERS bands, our work aims to provide a systematic analysis of the molecular information that can be achieved from the SERS analysis of serum and urine obtained from breast cancer patients and controls. Further, we compared the relative performance of five different machine learning algorithms for breast cancer and control samples classification based on the serum and urine SERS datasets, and found comparable classification accuracies in the range of 61-89%. This result is not surprising since both biofluids show striking similarities in their SERS spectra providing similar metabolic information, related to purine metabolites. Lastly, by carefully comparing the two datasets (i.e., serum and urine) we show that it is possible to link the misclassified samples to specific metabolic imbalances, such as carotenoid levels, or variations in the creatinine concentration.

Spectral homogeneity of human platelets investigated by SERS

This paper describes a detailed study of the spectral homogeneity of human platelets using Surface-enhanced Raman spectroscopy (SERS). We used a combined approach based on multivariate methods as principal component analysis and pair correlation algorithms to investigate platelets spectral properties. The correlation coefficients for each sample have been calculated, and the average coefficient of determination has been estimated. The high degree of spectral homogeneity inside one probe and between them has been revealed. The prospects of obtained results usage for pathologies based on platelet conformations during cardiovascular diseases have been demonstrated.

Acoustofluidic multimodal diagnostic system for Alzheimer's disease

Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative brain disorder that affects tens of millions of older adults worldwide and has significant economic and societal impacts. Despite its prevalence and severity, early diagnosis of AD remains a considerable challenge. Here we report an integrated acoustofluidics-based diagnostic system (ADx), which combines triple functions of acoustics, microfluidics, and orthogonal biosensors for clinically accurate, sensitive, and rapid detection of AD biomarkers from human plasma. We design and fabricate a surface acoustic wave-based acoustofluidic separation device to isolate and purify AD biomarkers to increase the signal-to-noise ratio. Multimodal biosensors within the integrated ADx are fabricated by in-situ patterning of the ZnO nanorod array and deposition of Ag nanoparticles onto the ZnO nanorods for surface-enhanced Raman scattering (SERS) and electrochemical immunosensors. We obtain the label-free detections of SERS and electrochemical immunoassay of clinical plasma samples from AD patients and healthy controls with high sensitivity and specificity. We believe that this efficient integration provides promising solutions for the early diagnosis of AD.

Identification of the Raman Salivary Fingerprint of Parkinson's Disease Through the Spectroscopic- Computational Combinatory Approach

Despite the wide range of proposed biomarkers for Parkinson's disease (PD), there are no specific molecules or signals able to early and uniquely identify the pathology onset, progression and stratification. Saliva is a complex biofluid, containing a wide range of biological molecules shared with blood and cerebrospinal fluid. By means of an optimized Raman spectroscopy procedure, the salivary Raman signature of PD can be characterized and used to create a classification model. Raman analysis was applied to collect the global signal from the saliva of 23 PD patients and related pathological and healthy controls. The acquired spectra were computed using machine and deep learning approaches. The Raman database was used to create a classification model able to discriminate each spectrum to the correct belonging group, with accuracy, specificity, and sensitivity of more than 97% for the single spectra attribution. Similarly, each patient was correctly assigned with discriminatory power of more than 90%. Moreover, the extracted data were significantly correlated with clinical data used nowadays for the PD diagnosis and monitoring. The preliminary data reported highlight the potentialities of the proposed methodology that, once validated in larger cohorts and with multi-centered studies, could represent an innovative minimally invasive and accurate procedure to determine the PD onset, progression and to monitor therapies and rehabilitation efficacy.

Clinically oriented Alzheimer's biosensors: expanding the horizons towards point-of-care diagnostics and beyond

The development of minimally invasive and easy-to-use sensor devices is of current interest for ultrasensitive detection and signal recognition of Alzheimer's disease (AD) biomarkers. Over the years, tremendous effort has been made on diagnostic platforms specifically targeting neurological markers for AD in order to replace the conventional, laborious, and invasive sampling-based approaches. However, the sophistication of analytical outcomes, marker inaccessibility, and material validity strongly limit the current strategies towards effectively predicting AD. Recently, with the promising progress in biosensor technology, the realization of a clinically applicable sensing platform has become a potential option to enable early diagnosis of AD and other neurodegenerative diseases. In this review, various types of biosensors, which include electrochemical, fluorescent, plasmonic, photoelectrochemical, and field-effect transistor (FET)-based sensor configurations, with better clinical applicability and analytical performance towards AD are highlighted. Moreover, the feasibility of these sensors to achieve point-of-care (POC) diagnosis is also discussed. Furthermore, by grafting nanoscale materials into biosensor architecture, the remarkable enhancement in durability, functionality, and analytical outcome of sensor devices is presented. Finally, future perspectives on further translational and commercialization pathways of clinically driven biosensor devices for AD are discussed and summarized.

Establishment of a reliable scheme for obtaining highly stable SERS signal of biological serum

As a rapid and non-destructive biological serum detection method, SERS technology was widely used in the screening and medical diagnosis of various diseases by combining the analysis of serum SERS spectrum and multivariate statistical algorithm. Because of the high complexity of serum components and the variability of SERS spectra, which often resulted in the phenomenon that the SERS spectrum of the same biological serum was significantly different due to the different test conditions. In this experiment, through the dilution treatment of the serum and the systematic test of the serum of all concentration gradients with lasers of wavelength of 785, 633 and 532 nm, the most suitable conditions for detecting the serum were investigated. The experimental results showed that only when the serum is diluted to low concentration (10 ppm), the SERS spectrum with high reproducibility and stability could be obtained, furthermore, the low concentration serum had weak tolerance to laser, and 532 nm laser was not suitable for serum detection. In this paper, a set of test scheme for obtaining highly stable serum SERS spectra was established by using high-performance gold nanoparticles (Au NPs) as the active substrate of SERS. Through comparative analysis of SERS spectrum of serum of normal people and cervical cancer, the reliability of the established low-concentration serum test program was verified, as well as its great potential advantages in disease screening and diagnosis.

Plasmonic Nanoparticles as Optical Sensing Probes for the Detection of Alzheimer's Disease

Alzheimer's disease (AD), considered a common type of dementia, is mainly characterized by a progressive loss of memory and cognitive functions. Although its cause is multifactorial, it has been associated with the accumulation of toxic aggregates of the amyloid-β peptide (Aβ) and neurofibrillary tangles (NFTs) of tau protein. At present, the development of highly sensitive, high cost-effective, and non-invasive diagnostic tools for AD remains a challenge. In the last decades, nanomaterials have emerged as an interesting and useful tool in nanomedicine for diagnostics and therapy. In particular, plasmonic nanoparticles are well-known to display unique optical properties derived from their localized surface plasmon resonance (LSPR), allowing their use as transducers in various sensing configurations and enhancing detection sensitivity. Herein, this review focuses on current advances in in vitro sensing techniques such as Surface-enhanced Raman scattering (SERS), Surface-enhanced fluorescence (SEF), colorimetric, and LSPR using plasmonic nanoparticles for improving the sensitivity in the detection of main biomarkers related to AD in body fluids. Additionally, we refer to the use of plasmonic nanoparticles for in vivo imaging studies in AD.

Characterization of the COPD Salivary Fingerprint through Surface Enhanced Raman Spectroscopy: A Pilot Study

Chronic Obstructive Pulmonary Disease (COPD) is a debilitating pathology characterized by reduced lung function, breathlessness and rapid and unrelenting decrease in quality of life. The severity rate and the therapy selection are strictly dependent on various parameters verifiable after years of clinical observations, missing a direct biomarker associated with COPD. In this work, we report the methodological application of Surface Enhanced Raman Spectroscopy combined with Multivariate statistics for the analysis of saliva samples collected from 15 patients affected by COPD and 15 related healthy subjects in a pilot study. The comparative Raman analysis allowed to determine a specific signature of the pathological saliva, highlighting differences in determined biological species, already studied and characterized in COPD onset, compared to the Raman signature of healthy samples. The unsupervised principal component analysis and hierarchical clustering revealed a sharp data dispersion between the two experimental groups. Using the linear discriminant analysis, we created a classification model able to discriminate the collected signals with accuracies, specificities, and sensitivities of more than 98%. The results of this preliminary study are promising for further applications of Raman spectroscopy in the COPD clinical field.

Raman spectroscopy and machine learning for biomedical applications: Alzheimer's disease diagnosis based on the analysis of cerebrospinal fluid

Current Alzheimer's disease (AD) diagnostics is based on clinical assessments, imaging and neuropsychological tests that are efficient only at advanced stages of the disease. Early diagnosis of AD will provide decisive opportunities for preventive treatment and development of disease-modifying drugs. Cerebrospinal fluid (CSF) is in direct contact with the human brain, where the deadly pathological process of the disease occurs. As such, the CSF biochemical composition reflects specific changes associated with the disease and is therefore the most promising body fluid for AD diagnostic test development. Here, we describe a new method to diagnose AD based on CSF via near infrared (NIR) Raman spectroscopy in combination with machine learning analysis. Raman spectroscopy is capable of probing the entire biochemical composition of a biological fluid at once. It has great potential to detect small changes specific to AD, even at the earliest stages of pathogenesis. NIR Raman spectra were measured of CSF samples acquired from 21 patients diagnosed with AD and 16 healthy control (HC) subjects. Artificial neural networks (ANN) and support vector machine discriminant analysis (SVM-DA) statistical methods were used for differentiation purposes, with the most successful results allowing for the differentiation of AD and HC subjects with 84% sensitivity and specificity. Our classification models show high discriminative power, suggesting the method has a great potential for AD diagnostics. The reported Raman spectroscopic examination of CSF can complement current clinical tests, making early AD detection fast, accurate, and inexpensive. While this study shows promise using a small sample set, further method validation on a larger scale is required to indicate the true strength of the approach.

COVID-19 salivary Raman fingerprint: innovative approach for the detection of current and past SARS-CoV-2 infections

The pandemic of COVID-19 is continuously spreading, becoming a worldwide emergency. Early and fast identification of subjects with a current or past infection must be achieved to slow down the epidemiological widening. Here we report a Raman-based approach for the analysis of saliva, able to significantly discriminate the signal of patients with a current infection by COVID-19 from healthy subjects and/or subjects with a past infection. Our results demonstrated the differences in saliva biochemical composition of the three experimental groups, with modifications grouped in specific attributable spectral regions. The Raman-based classification model was able to discriminate the signal collected from COVID-19 patients with accuracy, precision, sensitivity and specificity of more than 95%. In order to translate this discrimination from the signal-level to the patient-level, we developed a Deep Learning model obtaining accuracy in the range 89-92%. These findings have implications for the creation of a potential Raman-based diagnostic tool, using saliva as minimal invasive and highly informative biofluid, demonstrating the efficacy of the classification model.