for the Garches COVID-19 Collaborative Group RECORDS Collaborators and Exhalomics Ò Collaborators a Hôpital Foch, Exhalomics Ò , D epartement des maladies des voies respiratoires, Suresnes, France (S.

Motivation Analysis of Volatile Organic Compounds (VOCs) in exhaled breath by Proton Transfer Reaction Time-of-Flight Mass Spectrometry (PTR-TOF-MS) is of increasing interest for real-time, non-invasive diagnosis, phenotyping and therapeutic drug monitoring in the clinics. However, there is currently a lack of methods and software tools for the processing of PTR-TOF-MS data from cohorts and suited for biomarker discovery studies. Results We developed a comprehensive suite of algorithms that process raw data from patient acquisitions and generate the table of feature intensities. Notably, we included an innovative 2D peak deconvolution model based on penalized splines signal regression for accurate estimation of the temporal profile and feature quantification, as well as a method to specifically select the VOCs from exhaled breath. The workflow was implemented as the ptairMS software, which contains a graphical interface to facilitate cohort management and data analysis. The approach was validated on both simulated and experimental data sets, and we showed that the sensitivity and specificity of the VOC detection reached 99% and 98.4%, respectively, and that the error of quantification was below 8.1% for concentrations down to 19 ppb. Availability The ptairMS software is publicly available as an R package on Bioconductor (doi:10.18129/B9.bioc.ptairMS), as well as its companion experiment package ptairData (doi:10.18129/B9.bioc.ptairData). Supplementary information Supplementary data are available at Bioinformatics online.

BackgroundAlthough rapid screening for and diagnosis of coronavirus disease 2019 (COVID-19) are still urgently needed, most current testing methods are long, costly or poorly specific. The objective of the present study was to determine whether or not artificial-intelligence-enhanced real-time mass spectrometry breath analysis is a reliable, safe, rapid means of screening ambulatory patients for COVID-19.MethodsIn two prospective, open, interventional studies in a single university hospital, we used real-time, proton transfer reaction time-of-flight mass spectrometry to perform a metabolomic analysis of exhaled breath from adults requiring screening for COVID-19. Artificial intelligence and machine learning techniques were used to build mathematical models based on breath analysis data either alone or combined with patient metadata.ResultsWe obtained breath samples from 173 participants, of whom 67 had proven COVID-19. After using machine learning algorithms to process breath analysis data and further enhancing the model using patient metadata, our method was able to differentiate between COVID-19-positive and -negative participants with a sensitivity of 98%, a specificity of 74%, a negative predictive value of 98%, a positive predictive value of 72% and an area under the receiver operating characteristic curve of 0.961. The predictive performance was similar for asymptomatic, weakly symptomatic and symptomatic participants and was not biased by COVID-19 vaccination status.ConclusionsReal-time, noninvasive, artificial-intelligence-enhanced mass spectrometry breath analysis might be a reliable, safe, rapid, cost-effective, high-throughput method for COVID-19 screening.

Background: Volatilomics is the branch of metabolomics dedicated to the analysis of volatile organic compounds (VOCs) in exhaled breath for medical diagnostic or therapeutic monitoring purposes. Real-time mass spectrometry technologies such as proton transfer reaction mass spectrometry (PTR-MS) are commonly used, and data normalisation is an important step to discard unwanted variation from non-biological sources, as batch effects and loss of sensitivity over time may be observed. As normalisation methods for real-time breath analysis have been poorly investigated, we aimed to benchmark known metabolomic data normalisation methods and apply them to PTR-MS data analysis. Methods: We compared seven normalisation methods, five statistically based and two using multiple standard metabolites, on two datasets from clinical trials for COVID-19 diagnosis in patients from the emergency department or intensive care unit. We evaluated different means of feature selection to select the standard metabolites, as well as the use of multiple repeat measurements of ambient air to train the normalisation methods. Results: We show that the normalisation tools can correct for time-dependent drift. The methods that provided the best corrections for both cohorts were Probabilistic Quotient Normalisation and Normalisation using Optimal Selection of Multiple Internal Standards. Normalisation also improved the diagnostic performance of the machine learning models, significantly increasing sensitivity, specificity and area under the ROC curve for the diagnosis of COVID-19. Conclusions: Our results highlight the importance of adding an appropriate normalisation step during the processing of PTR-MS data, which allows significant improvements in the predictive performance of statistical models.

BackgroundAlthough rapid screening for and diagnosis of COVID-19 are still urgently needed, most current testing methods are either long, costly, and/or poorly specific. The objective of the present study was to determine whether or not artificial-intelligence-enhanced real-time MS breath analysis is a reliable, safe, rapid means of screening ambulatory patients for COVID-19.MethodsIn two prospective, open, interventional studies in a single university hospital, we used real-time, proton transfer reaction time-of-flight mass spectrometry to perform a metabolomic analysis of exhaled breath from adults requiring screening for COVID-19. Artificial intelligence and machine learning techniques were used to build mathematical models based on breath analysis data either alone or combined with patient metadata.ResultsWe obtained breath samples from 173 participants, of whom 67 had proven COVID-19. After using machine learning algorithms to process breath analysis data and further enhancing the model using patient metadata, our method was able to differentiate between COVID-19-positive and -negative participants with a sensitivity of 98%, a specificity of 74%, a negative predictive value of 98%, a positive predictive value of 72%, and an area under the receiver operating characteristic curve of 0.961. The predictive performance was similar for asymptomatic, weakly symptomatic and symptomatic participants and was not biased by the COVID-19 vaccination status.ConclusionsReal-time, non-invasive, artificial-intelligence-enhanced mass spectrometry breath analysis might be a reliable, safe, rapid, cost-effective, high-throughput method for COVID-19 screening.