학술논문
Covid-19 Automated Diagnosis and Risk Assessment through Metabolomics and Machine Learning.
Document Type
Academic Journal
Author
Delafiori J; Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Cidade Universitária Zeferino Vaz, Campinas, São Paulo 350-13083-970, Brazil.; Navarro LC; RECOD Laboratory, Computing Institute, University of Campinas, Cidade Universitária Zeferino Vaz,, Campinas, São Paulo 573-13083-852, Brazil.; Siciliano RF; Clinical Division of Infectious and Parasitic Diseases, University of São Paulo Medical School, São Paulo, São Paulo 01246-903, Brazil.; Instituto do Coracao (InCor), Hospital das Clinicas HCFMUSP, Faculdade de Medicina, Universidade de São Paulo, Cerqueira César, São Paulo 44-05403-90, Brazil.; de Melo GC; Tropical Medicine Foundation Dr. Heitor Vieira Dourado, Manaus, Amazonas 69040-000,Brazil.; Amazonas State University, Manaus, Amazonas 25-69040-000, Brazil.; Busanello ENB; Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Cidade Universitária Zeferino Vaz, Campinas, São Paulo 350-13083-970, Brazil.; Nicolau JC; Instituto do Coracao (InCor), Hospital das Clinicas HCFMUSP, Faculdade de Medicina, Universidade de São Paulo, Cerqueira César, São Paulo 44-05403-90, Brazil.; Sales GM; Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Cidade Universitária Zeferino Vaz, Campinas, São Paulo 350-13083-970, Brazil.; de Oliveira AN; Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Cidade Universitária Zeferino Vaz, Campinas, São Paulo 350-13083-970, Brazil.; Val FFA; Tropical Medicine Foundation Dr. Heitor Vieira Dourado, Manaus, Amazonas 69040-000,Brazil.; Amazonas State University, Manaus, Amazonas 25-69040-000, Brazil.; de Oliveira DN; Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Cidade Universitária Zeferino Vaz, Campinas, São Paulo 350-13083-970, Brazil.; Eguti A; Sumaré State Hospital, Sumaré, São Paulo 2400-13175-490, Brazil.; Dos Santos LA; Paulínia Municipal Hospital, Paulínia, São Paulo 100-13140-000, Brazil.; Dalçóquio TF; Instituto do Coracao (InCor), Hospital das Clinicas HCFMUSP, Faculdade de Medicina, Universidade de São Paulo, Cerqueira César, São Paulo 44-05403-90, Brazil.; Bertolin AJ; Instituto do Coracao (InCor), Hospital das Clinicas HCFMUSP, Faculdade de Medicina, Universidade de São Paulo, Cerqueira César, São Paulo 44-05403-90, Brazil.; Abreu-Netto RL; Tropical Medicine Foundation Dr. Heitor Vieira Dourado, Manaus, Amazonas 69040-000,Brazil.; Amazonas State University, Manaus, Amazonas 25-69040-000, Brazil.; Salsoso R; Instituto do Coracao (InCor), Hospital das Clinicas HCFMUSP, Faculdade de Medicina, Universidade de São Paulo, Cerqueira César, São Paulo 44-05403-90, Brazil.; Baía-da-Silva D; Tropical Medicine Foundation Dr. Heitor Vieira Dourado, Manaus, Amazonas 69040-000,Brazil.; Amazonas State University, Manaus, Amazonas 25-69040-000, Brazil.; Marcondes-Braga FG; Instituto do Coracao (InCor), Hospital das Clinicas HCFMUSP, Faculdade de Medicina, Universidade de São Paulo, Cerqueira César, São Paulo 44-05403-90, Brazil.; Sampaio VS; Tropical Medicine Foundation Dr. Heitor Vieira Dourado, Manaus, Amazonas 69040-000,Brazil.; Health Surveillance Foundation of Amazonas State, Manaus, Amazonas, 4010-69093-018 Brazil.; Judice CC; Laboratory of Tropical Diseases, Institute of Biology, University of Campinas, Cidade Universitária Zeferino Vaz, Campinas, São Paulo 13083-970 Brazil.; Costa FTM; Laboratory of Tropical Diseases, Institute of Biology, University of Campinas, Cidade Universitária Zeferino Vaz, Campinas, São Paulo 13083-970 Brazil.; Durán N; Laboratory of Urogenital Carcinogenesis and Immunotherapy, University of Campinas, Cidade Universitária Zeferino Vaz, Campinas, São Paulo 13083-865, Brazil.; Perroud MW; Sumaré State Hospital, Sumaré, São Paulo 2400-13175-490, Brazil.; Sabino EC; Institute of Tropical Medicine, University of São Paulo, São Paulo, São Paulo 470-05403-000,Brazil.; Lacerda MVG; Tropical Medicine Foundation Dr. Heitor Vieira Dourado, Manaus, Amazonas 69040-000,Brazil.; Leônidas and Maria Deane Institute, Manaus, Amazonas, 476-69057-070 Brazil.; Reis LO; UroScience Laboratory, University of Campinas, Cidade Universitária Zeferino Vaz, Campinas, São Paulo 126-13083-887, Brazil.; Fávaro WJ; Laboratory of Urogenital Carcinogenesis and Immunotherapy, University of Campinas, Cidade Universitária Zeferino Vaz, Campinas, São Paulo 13083-865, Brazil.; Monteiro WM; Tropical Medicine Foundation Dr. Heitor Vieira Dourado, Manaus, Amazonas 69040-000,Brazil.; Amazonas State University, Manaus, Amazonas 25-69040-000, Brazil.; Rocha AR; RECOD Laboratory, Computing Institute, University of Campinas, Cidade Universitária Zeferino Vaz,, Campinas, São Paulo 573-13083-852, Brazil.; Catharino RR; Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Cidade Universitária Zeferino Vaz, Campinas, São Paulo 350-13083-970, Brazil.
Source
Publisher: American Chemical Society Country of Publication: United States NLM ID: 0370536 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1520-6882 (Electronic) Linking ISSN: 00032700 NLM ISO Abbreviation: Anal Chem Subsets: MEDLINE
Subject
Language
English
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.