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

Author(s):Show less -

Delafiori, Jeany ^[1] ; Navarro, Luiz Claudio ^[2] ; Siciliano, Rinaldo Focaccia ^{[3, 4]} ; de Melo, Gisely Cardoso ^{[5, 6]} ; Brandt Busanello, Estela Natacha ^[1] ; Nicolau, Jose Carlos ^[4] ; Sales, Geovana Manzan ^[1] ; de Oliveira, Arthur Noin ^[1] ; Almeida Val, Fernando Fonseca ^{[5, 6]} ; de Oliveira, Diogo Noin ^[1] ; Eguti, Adriana ^[7] ; dos Santos, Luiz Augusto ^[8] ; Dalcoquio, Talia Falcao ^[4] ; Bertolin, Adriadne Justi ^[4] ; Abreu-Netto, Rebeca Linhares ^{[5, 6]} ; Salsoso, Rocio ^[4] ; Baia-da-Silva, Djane ^{[5, 6]} ; Marcondes-Braga, Fabiana G. ^[4] ; Sampaio, Vanderson Souza ^{[5, 9]} ; Judice, Carla Cristina ^[10] ; Maranhao Costa, Fabio Trindade ^[10] ; Duran, Nelson ^[11] ; Perroud, Mauricio Wesley ^[7] ; Sabino, Ester Cerdeira ^[12] ; Guimaraes Lacerda, Marcus Vinicius ^[5] ; Reis, Leonardo Oliveira ^[13] ; Favaro, Wagner Jose ^[11] ; Monteiro, Wuelton Marcelo ^{[5, 6]} ; Rocha, Anderson Rezende ^[2] ; Catharino, Rodrigo Ramos ^[1]

Affiliation:Show less -

^[1] Univ Estadual Campinas, Sch Pharmaceut Sci, Innovare Biomarkers Lab, BR-35013083 Campinas, SP - Brazil

^[2] Univ Estadual Campinas, Comp Inst, RECOD Lab, BR-57313083 Campinas, SP - Brazil

^[3] Univ Sao Paulo, Clin Div Infect & Parasit Dis, Med Sch, BR-01246903 Sao Paulo - Brazil

^[4] Univ Sao Paulo, Hosp Clin HCFMUSP, Fac Med, Inst Coracao InCor, BR-44054039 Sao Paulo, SP - Brazil

^[5] Trop Med Fdn Dr Heitor Vieira Dourado, BR-69040000 Manaus, Amazonas - Brazil

^[6] Amazonas State Univ, BR-25690400 Manaus, Amazonas - Brazil

^[7] Sumare State Hosp, Sumare, SP - Brazil

^[8] Paulinia Municipal Hosp, BR-10013140 Paulinia, SP - Brazil

^[9] Hlth Surveillance Fdn Amazonas State, Manaus, Amazonas - Brazil

^[10] Univ Estadual Campinas, Inst Biol, Lab Trop Dis, BR-13083970 Campinas, SP - Brazil

^[11] Univ Estadual Campinas, Lab Urogenital Carcinogenesis & Immunotherapy, BR-13083865 Campinas, SP - Brazil

^[12] Univ Sao Paulo, Inst Trop Med, BR-47005403 Sao Paulo - Brazil

^[13] Univ Estadual Campinas, UroSci Lab, BR-12613083 Campinas, SP - Brazil

• Document type: Journal article
• Source: Analytical Chemistry; v. 93, n. 4, p. 2471-2479, FEB 2 2021.
• Web of Science Citations: 23

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. (AU)

• FAPESP's process: 20/04705-2 - Diagnostic and prognostic study of SARS-CoV-2 and Influenza virus infection
• Grantee: José Carlos Nicolau
• Support Opportunities: Regular Research Grants
• FAPESP's process: 20/05369-6 - Artificial inteligence driven drug repositioning strategy for COVID-19
• Grantee: Fabio Trindade Maranhão Costa
• Support Opportunities: Regular Research Grants
• FAPESP's process: 18/10052-1 - New Therapeutic Approaches for Non-Muscle Invasive Bladder Cancer (NMIBC): Intravesical Use of OncoTherad Biological Response Modifier and Its Association with Platelet Rich Plasma (PRP)
• Grantee: Wagner José Fávaro
• Support Opportunities: Regular Research Grants
• FAPESP's process: 19/05718-3 - Determination of metabolic alterations and therapeutic potential of Zika Virus in cancer cells by mass spectrometry and artificial intelligence
• Grantee: Jeany Delafiori
• Support Opportunities: Scholarships in Brazil - Doctorate (Direct)
• FAPESP's process: 17/12646-3 - Déjà vu: feature-space-time coherence from heterogeneous data for media integrity analytics and interpretation of events
• Grantee: Anderson de Rezende Rocha
• Support Opportunities: Research Projects - Thematic Grants