Covid-19 automated diagnosis and risk assessment through Metabolomics and Machine-Learning

Delafiori, J.; Navarro, L. C.; Siciliano, R. F.; de Melo, G. C.; Busanello, E. N. B.; Nicolau, J. C.; Sales, G. M.; de Oliveira, A. N.; Val, F. F. A.; de Oliveira, D. N.; Eguti, A.; dos Santos, L. A.; Dalcoquio, T. F.; Bertolin, A. J.; Alonso, J. C. C.; Abreu-Netto, R. L.; Salsoso, R.; Baia-da-Silva, D.; Sampaio, V. S.; Judice, C. C.; Costa, F. M. T.; Duran, N.; Perroud, M. W.; Sabino, E. C.; Lacerda, M. V. G.; Reis, L. O.; Favaro, W. J.; Monteiro, W. M.; Rocha, A. R.; Catharino, R. R.

COVID-19 is still placing a heavy health and financial burden worldwide. Impairments in patient screening and risk management play 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 instrumental analysis using 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 cohort of 728 patients (369 confirmed COVID-19 and 359 controls) was enrolled from three Brazilian epicentres (Sao Paulo capital, Sao Paulo countryside and Manaus) in the months of April, May, June and July 2020. We were able to elect and identify 21 molecules that are related to the disease's pathophysiology and 26 features to patient's health-related outcomes. With specificity >97% and sensitivity >83% from blinded data, this screening approach is understood as a tool with great potential for real-world application.