scholarly journals Saliva-based detection of COVID-19 infection in a real-world setting using reagent-free Raman spectroscopy and machine learning

2021 ◽  
Author(s):  
Katherine J I Ember ◽  
François Daoust ◽  
Myriam Mahfoud ◽  
Frédérick Dallaire ◽  
Esmat Zamani ◽  
...  
Keyword(s):  
Machine Learning ◽  
Raman Spectroscopy ◽  
Real World ◽  
Roc Curves ◽  
Screening Tools ◽  
Molecular Profile ◽  
Label Free ◽  
Raman Spectroscopic ◽  
Non Invasive ◽  
Real World Setting

Significance: The primary method of COVID-19 detection is reverse transcription polymerase chain reaction (RT-PCR) testing. PCR test sensitivity may decrease as more variants of concern arise. Aim: We aimed to develop a reagent-free way to detect COVID-19 in a real-world setting with minimal constraints on sample acquisition. Approach: We present a workflow for collecting, preparing and imaging dried saliva supernatant droplets using a non-invasive, label-free technique known as Raman spectroscopy to detect changes in the molecular profile of saliva associated with COVID-19 infection. Results: Using machine learning and droplet segmentation, amongst all confounding factors, we discriminated between COVID-positive and negative individuals yielding receiver operating coefficient (ROC) curves with an area under curve (AUC) of 0.8 in both males (79% sensitivity, 75% specificity) and females (84% sensitivity, 64% specificity). Taking the sex of the saliva donor into account increased the AUC by 5%. Conclusion:These findings may pave the way for new rapid Raman spectroscopic screening tools for COVID-19 and other infectious diseases.

scholarly journals Dear Watch, Should I get a COVID Test? Designing deployable machine learning for wearables

2021 ◽  
Author(s):  
Anna Goldenberg ◽  
Bret Nestor ◽  
Jaryd Hunter ◽  
Raghu Kainkaryam ◽  
Erik Drysdale ◽  
...  
Keyword(s):  
Public Health ◽  
Machine Learning ◽  
Real World ◽  
False Positive Rate ◽  
Wearable Devices ◽  
Classification Performance ◽  
Wearable Device ◽  
Screening Tools ◽  
Machine Learning Model ◽  
Positive Rate

Abstract Commercial wearable devices are surfacing as an appealing mechanism to detect COVID-19 and potentially other public health threats, due to their widespread use. To assess the validity of wearable devices as population health screening tools, it is essential to evaluate predictive methodologies based on wearable devices by mimicking their real-world deployment. Several points must be addressed to transition from statistically significant differences between infected and uninfected cohorts to COVID-19 inferences on individuals. We demonstrate the strengths and shortcomings of existing approaches on a cohort of 32,198 individuals who experience influenza like illness (ILI), 204 of which report testing positive for COVID-19. We show that, despite commonly made design mistakes resulting in overestimation of performance, when properly designed wearables can be effectively used as a part of the detection pipeline. For example, knowing the week of year, combined with naive randomised test set generation leads to substantial overestimation of COVID-19 classification performance at 0.73 AUROC. However, an average AUROC of only 0.55 +/- 0.02 would be attainable in a simulation of real-world deployment, due to the shifting prevalence of COVID-19 and non-COVID-19 ILI to trigger further testing. In this work we show how to train a machine learning model to differentiate ILI days from healthy days, followed by a survey to differentiate COVID-19 from influenza and unspecified ILI based on symptoms. In a forthcoming week, models can expect a sensitivity of 0.50 (0-0.74, 95% CI), while utilising the wearable device to reduce the burden of surveys by 35%. The corresponding false positive rate is 0.22 (0.02-0.47, 95% CI). In the future, serious consideration must be given to the design, evaluation, and reporting of wearable device interventions if they are to be relied upon as part of frequent COVID-19 or other public health threat testing infrastructures.

scholarly journals Label-free Raman monitoring of extracellular matrix formation in three-dimensional polymeric scaffolds

2013 ◽  
Vol 10 (86) ◽  
pp. 20130464 ◽  
Author(s):  
Aliz Kunstar ◽  
Anne M. Leferink ◽  
Paul I. Okagbare ◽  
Michael D. Morris ◽  
Blake J. Roessler ◽  
...  
Keyword(s):  
Extracellular Matrix ◽  
Raman Spectroscopy ◽  
Three Dimensional ◽  
Raman Microspectroscopy ◽  
Collagen Content ◽  
Cartilage Tissue ◽  
Fibre Optic ◽  
Label Free ◽  
Tissue Quality ◽  
Non Invasive

Monitoring extracellular matrix (ECM) components is one of the key methods used to determine tissue quality in three-dimensional scaffolds for regenerative medicine and clinical purposes. Raman spectroscopy can be used for non-invasive sensing of cellular and ECM biochemistry. We have investigated the use of conventional (confocal and semiconfocal) Raman microspectroscopy and fibre-optic Raman spectroscopy for in vitro monitoring of ECM formation in three-dimensional poly(ethylene oxide terephthalate)–poly(butylene terephthalate) (PEOT/PBT) scaffolds. Chondrocyte-seeded PEOT/PBT scaffolds were analysed for ECM formation by Raman microspectroscopy, biochemical analysis, histology and scanning electron microscopy. ECM deposition in these scaffolds was successfully detected by biochemical and histological analysis and by label-free non-destructive Raman microspectroscopy. In the spectra collected by the conventional Raman set-ups, the Raman bands at 937 and at 1062 cm −1 which, respectively, correspond to collagen and sulfated glycosaminoglycans could be used as Raman markers for ECM formation in scaffolds. Collagen synthesis was found to be different in single chondrocyte-seeded scaffolds when compared with microaggregate-seeded samples. Normalized band-area ratios for collagen content of single cell-seeded samples gradually decreased during a 21-day culture period, whereas collagen content of the microaggregate-seeded samples significantly increased during this period. Moreover, a fibre-optic Raman set-up allowed for the collection of Raman spectra from multiple pores inside scaffolds in parallel. These fibre-optic measurements could give a representative average of the ECM Raman signal present in tissue-engineered constructs. Results in this study provide proof-of-principle that Raman microspectroscopy is a promising non-invasive tool to monitor ECM production and remodelling in three-dimensional porous cartilage tissue-engineered constructs.

scholarly journals Raman spectroscopy enables phenotyping and assessment of nutrition values of plants: a review

Plant Methods ◽  
2021 ◽  
Vol 17 (1) ◽  
Author(s):  
William Z. Payne ◽  
Dmitry Kurouski
Keyword(s):  
Raman Spectroscopy ◽  
Abiotic Stresses ◽  
Molecular Techniques ◽  
Plant Diseases ◽  
Label Free ◽  
Breeding Programs ◽  
Non Invasive ◽  
Nutrition Value ◽  
Non Destructive ◽  
Selection Of

AbstractOur civilization has to enhance food production to feed world’s expected population of 9.7 billion by 2050. These food demands can be met by implementation of innovative technologies in agriculture. This transformative agricultural concept, also known as digital farming, aims to maximize the crop yield without an increase in the field footprint while simultaneously minimizing environmental impact of farming. There is a growing body of evidence that Raman spectroscopy, a non-invasive, non-destructive, and laser-based analytical approach, can be used to: (i) detect plant diseases, (ii) abiotic stresses, and (iii) enable label-free phenotyping and digital selection of plants in breeding programs. In this review, we critically discuss the most recent reports on the use of Raman spectroscopy for confirmatory identification of plant species and their varieties, as well as Raman-based analysis of the nutrition value of seeds. We show that high selectivity and specificity of Raman makes this technique ideal for optical surveillance of fields, which can be used to improve agriculture around the world. We also discuss potential advances in synergetic use of RS and already established imaging and molecular techniques. This combinatorial approach can be used to reduce associated time and cost, as well as enhance the accuracy of diagnostics of biotic and abiotic stresses.

scholarly journals Identification of ceftazidime interaction with bacteria in wastewater treatment by Raman spectroscopic mapping

RSC Advances ◽  
2019 ◽  
Vol 9 (56) ◽  
pp. 32744-32752
Author(s):  
Meng-Wen Peng ◽  
Xiang-Yang Wei ◽  
Qiang Yu ◽  
Peng Yan ◽  
You-Peng Chen ◽  
...  
Keyword(s):  
Biological Sciences ◽  
Raman Spectroscopy ◽  
Wastewater Treatment ◽  
Aqueous Environment ◽  
Raman Spectroscopic ◽  
Non Invasive ◽  
Non Destructive

Raman spectroscopy yields a fingerprint spectrum and is of great importance in medical and biological sciences as it is non-destructive, non-invasive, and available in the aqueous environment.

scholarly journals Non-Invasive Tools to Detect Smoke Contamination in Grapevine Canopies, Berries and Wine: A Remote Sensing and Machine Learning Modeling Approach

Sensors ◽  
2019 ◽  
Vol 19 (15) ◽  
pp. 3335 ◽  
Author(s):  
Sigfredo Fuentes ◽  
Eden Jane Tongson ◽  
Roberta De Bei ◽  
Claudia Gonzalez Viejo ◽  
Renata Ristic ◽  
...  
Keyword(s):  
Machine Learning ◽  
Pattern Recognition ◽  
Management Practices ◽  
Near Infrared ◽  
Detection System ◽  
Screening Tools ◽  
Unmanned Aerial Systems ◽  
Non Invasive ◽  
Aerial Systems ◽  
Non Destructive

Bushfires are becoming more frequent and intensive due to changing climate. Those that occur close to vineyards can cause smoke contamination of grapevines and grapes, which can affect wines, producing smoke-taint. At present, there are no available practical in-field tools available for detection of smoke contamination or taint in berries. This research proposes a non-invasive/in-field detection system for smoke contamination in grapevine canopies based on predictable changes in stomatal conductance patterns based on infrared thermal image analysis and machine learning modeling based on pattern recognition. A second model was also proposed to quantify levels of smoke-taint related compounds as targets in berries and wines using near-infrared spectroscopy (NIR) as inputs for machine learning fitting modeling. Results showed that the pattern recognition model to detect smoke contamination from canopies had 96% accuracy. The second model to predict smoke taint compounds in berries and wine fit the NIR data with a correlation coefficient (R) of 0.97 and with no indication of overfitting. These methods can offer grape growers quick, affordable, accurate, non-destructive in-field screening tools to assist in vineyard management practices to minimize smoke taint in wines with in-field applications using smartphones and unmanned aerial systems (UAS).

Surface-enhanced spatially-offset Raman spectroscopy (SESORS) for detection of neurochemicals through the skull at physiologically relevant concentrations

The Analyst ◽  
2020 ◽  
Vol 145 (5) ◽  
pp. 1885-1893 ◽  
Author(s):  
Amber S. Moody ◽  
Taylor D. Payne ◽  
Brian A. Barth ◽  
Bhavya Sharma
Keyword(s):  
Raman Spectroscopy ◽  
Neurological Disease ◽  
Label Free ◽  
Detection Techniques ◽  
Non Invasive ◽  
Surface Enhanced

Detection techniques for neurotransmitters that are rapid, label-free, and non-invasive are needed to move towards earlier diagnosis of neurological disease.

Sign in / Sign up

Export Citation Format

Share Document