Covid-19 Automated Diagnosis and Risk Assessment through Metabolomics and Machine Learning

Abstract

COVID-19 is still placing a heavy health and financial burden worldwide. Impairment in patient screening and risk management plays a fundamental role on how governments and authorities are directing resources, planning reopening, as well as sanitary countermeasures, especially in regions where poverty is a major component in the equation. An efficient diagnostic method must be highly accurate, while having a cost-effective profile. We combined a machine learning-based algorithm with mass spectrometry to create an expeditious platform that discriminate COVID-19 in plasma samples within minutes, while also providing tools for risk assessment, to assist healthcare professionals in patient management and decision-making. A cross-sectional study enrolled 815 patients (442 COVID-19, 350 controls and 23 COVID-19 suspicious) from three Brazilian epicenters from April to July 2020. We were able to elect and identify 19 molecules related to the disease’s pathophysiology and several discriminating features to patient’s health-related outcomes. The method applied for COVID-19 diagnosis showed specificity >96% and sensitivity >83%, and specificity >80% and sensitivity >85% during risk assessment, both from blinded data. Our method introduced a new approach for COVID-19 screening, providing the indirect detection of infection through metabolites and contextualizing the findings with the disease’s pathophysiology. The pairwise analysis of biomarkers brought robustness to the model developed using machine learning algorithms, transforming this screening approach in a tool with great potential for real-world application.

Rapid Screening of COVID-19 Directly from Clinical Nasopharyngeal Swabs Using the MasSpec Pen

“…22 Yet, a recent study by Delafiori et al reported decreased abundances of lysoPC species in the serum of COVID-19 positive patients. 33 Across both classifiers, PE 50:9 was selected as indicative of COVID-19 with the highest weight toward the disease, while other PE species such as PE 34:2 was selected as indicative of being negative for COVID-19. Increased abundance of PE species was also recently reported by Ford et al in nasal swabs from COVID-19 positive patients.…”

Genome‐scale metabolic modelling of SARS‐CoV‐2 in cancer cells reveals an increased shift to glycolytic energy production

“…Similarly, studies of circulating blood metabolites in COVID‐19 patients have yielded interesting biomarkers of infection, including hijacking of nucleic acid intermediates [ 20 , 21 , 22 , 23 ], dysregulation of lipid metabolism [ 22 , 24 , 25 ], changes in amino acid metabolism [ 23 , 25 ], alteration of energy metabolism [ 26 ], immune response [ 27 ], and indicators of hepatic cell damage [ 25 ]. However, a limitation of metabolomics alone is that it focuses on alterations of metabolites at a pathway level rather than identifying altered reaction/enzyme activity, which allows for more specific therapeutic targeting.…”

The Post-COVID-19 Era: Interdisciplinary Demands of Contagion Surveillance Mass Spectrometry for Future Pandemics

“…Though finding a molecular marker specific to a contagion (e.g., SARS-CoV-2) is challenging, other means in relation to COVID-19 diagnosis in human hosts have been demonstrated. These studies (e.g., [35,36]) have shown MS and machine learning protocols can identify distinctive spectral and peak features of peptidomes in human serum [35,36] and metabolites in plasma samples [35,36] of COVID-19 patients (when compared with those of non-COVID-19 patients).…”