Covid-19 Automated Diagnosis and Risk Assessment through Metabolomics and Machine Learning
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.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2021 |
|---|---|
| Erschienen: |
2021 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:93 |
|---|---|
| Enthalten in: |
Analytical chemistry - 93(2021), 4 vom: 02. Feb., Seite 2471-2479 |
| Sprache: |
Englisch |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 19.02.2021 Date Revised 11.11.2023 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1021/acs.analchem.0c04497 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM320338894 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM320338894 | ||
| 003 | DE-627 | ||
| 005 | 20231225173349.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1021/acs.analchem.0c04497 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1067.xml |
| 035 | |a (DE-627)NLM320338894 | ||
| 035 | |a (NLM)33471512 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Delafiori, Jeany |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Covid-19 Automated Diagnosis and Risk Assessment through Metabolomics and Machine Learning |
| 264 | 1 | |c 2021 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 19.02.2021 | ||
| 500 | |a Date Revised 11.11.2023 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a 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 | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 650 | 7 | |a Biomarkers |2 NLM | |
| 700 | 1 | |a Navarro, Luiz Cláudio |e verfasserin |4 aut | |
| 700 | 1 | |a Siciliano, Rinaldo Focaccia |e verfasserin |4 aut | |
| 700 | 1 | |a de Melo, Gisely Cardoso |e verfasserin |4 aut | |
| 700 | 1 | |a Busanello, Estela Natacha Brandt |e verfasserin |4 aut | |
| 700 | 1 | |a Nicolau, José Carlos |e verfasserin |4 aut | |
| 700 | 1 | |a Sales, Geovana Manzan |e verfasserin |4 aut | |
| 700 | 1 | |a de Oliveira, Arthur Noin |e verfasserin |4 aut | |
| 700 | 1 | |a Val, Fernando Fonseca Almeida |e verfasserin |4 aut | |
| 700 | 1 | |a de Oliveira, Diogo Noin |e verfasserin |4 aut | |
| 700 | 1 | |a Eguti, Adriana |e verfasserin |4 aut | |
| 700 | 1 | |a Dos Santos, Luiz Augusto |e verfasserin |4 aut | |
| 700 | 1 | |a Dalçóquio, Talia Falcão |e verfasserin |4 aut | |
| 700 | 1 | |a Bertolin, Adriadne Justi |e verfasserin |4 aut | |
| 700 | 1 | |a Abreu-Netto, Rebeca Linhares |e verfasserin |4 aut | |
| 700 | 1 | |a Salsoso, Rocio |e verfasserin |4 aut | |
| 700 | 1 | |a Baía-da-Silva, Djane |e verfasserin |4 aut | |
| 700 | 1 | |a Marcondes-Braga, Fabiana G |e verfasserin |4 aut | |
| 700 | 1 | |a Sampaio, Vanderson Souza |e verfasserin |4 aut | |
| 700 | 1 | |a Judice, Carla Cristina |e verfasserin |4 aut | |
| 700 | 1 | |a Costa, Fabio Trindade Maranhão |e verfasserin |4 aut | |
| 700 | 1 | |a Durán, Nelson |e verfasserin |4 aut | |
| 700 | 1 | |a Perroud, Mauricio Wesley |e verfasserin |4 aut | |
| 700 | 1 | |a Sabino, Ester Cerdeira |e verfasserin |4 aut | |
| 700 | 1 | |a Lacerda, Marcus Vinicius Guimarães |e verfasserin |4 aut | |
| 700 | 1 | |a Reis, Leonardo Oliveira |e verfasserin |4 aut | |
| 700 | 1 | |a Fávaro, Wagner José |e verfasserin |4 aut | |
| 700 | 1 | |a Monteiro, Wuelton Marcelo |e verfasserin |4 aut | |
| 700 | 1 | |a Rocha, Anderson Rezende |e verfasserin |4 aut | |
| 700 | 1 | |a Catharino, Rodrigo Ramos |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Analytical chemistry |d 1965 |g 93(2021), 4 vom: 02. Feb., Seite 2471-2479 |w (DE-627)NLM000025771 |x 1520-6882 |7 nnns |
| 773 | 1 | 8 | |g volume:93 |g year:2021 |g number:4 |g day:02 |g month:02 |g pages:2471-2479 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1021/acs.analchem.0c04497 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 93 |j 2021 |e 4 |b 02 |c 02 |h 2471-2479 | ||