| Journal: | Revista de investigación clínica |
| Database: | PERIÓDICA |
| System number: | 000452919 |
| ISSN: | 0034-8376 |
| Authors: | Villagrana Bañuelos, Karen E1 Maeda Gutiérrez, Valeria1 Alcalá Ramírez, Vanessa1 Oropeza Valdez, Juan J2 Herrera Van Oostdam, Ana S3 Castañeda Delgado, Julio E4 López, Jesús Adrián5 Borrego Moreno, Juan C6 Galván Tejada, Carlos E1 Galván Tejeda, Jorge I1 Gamboa Rosales, Hamurabi1 Luna García, Huizilopoztli1 Celaya Padilla, José M1 López Hernández, Yamilé2 |
| Institutions: | 1Universidad Autónoma de Zacatecas, Unidad Académica de Ingeniería Eléctrica, Zacatecas. México 2Universidad Autónoma de Zacatecas, Laboratorio de Metabolómica y Proteómica, Zacatecas. México 3Universidad Autónoma de San Luis Potosí, Centro de Investigación en Ciencias de la Salud y Biomedicina, San Luis Potosí. México 4Instituto Mexicano del Seguro Social, Zacatecas. México 5Universidad Autónoma de Zacatecas, Unidad Académica de Ciencias Biológicas, Zacatecas. México 6Instituto Mexicano del Seguro Social, Hospital General de Zona 1 Emilio Varela Luján, Zacatecas. México |
| Year: | 2022 |
| Season: | Nov-Dic |
| Volumen: | 74 |
| Number: | 6 |
| Pages: | 314-327 |
| Country: | México |
| Language: | Inglés |
| Document type: | Artículo |
| Approach: | Experimental, aplicado |
| English abstract | Background: The coronavirus disease (COVID-19) is an infectious disease caused by the SARS-CoV-2 virus and is responsible for nearly 6 million deaths worldwide in the past 2 years. Machine learning (ML) models could help physicians in identifying high-risk individuals. Objectives: To study the use of ML models for COVID-19 prediction outcomes using clinical data and a combination of clinical and metabolic data, measured in a metabolomics facility from a public university. Methods: A total of 154 patients were included in the study. “Basic profile” was considered with clinical and demographic variables (33 variables), whereas in the “extended profile,” metabolomic and immunological variables were also considered (156 characteristics). A selection of features was carried out for each of the profiles with a genetic algorithm (GA) and random forest models were trained and tested to predict each of the stages of COVID-19. Results: The model based on extended profile was more useful in early stages of the disease. Models based on clinical data were preferred for predicting severe and critical illness and death. ML detected trimethylamine N-oxide, lipid mediators, and neutrophil/lymphocyte ratio as important variables. Conclusion: ML and GAs provided adequate models to predict COVID-19 outcomes in patients with different severity grades |
| Disciplines: | Medicina |
| Keyword: | Virus, Diagnóstico, COVID-19, Metabolómica, Biomarcadores, Aprendizaje de máquinas, Algoritmos genéticos |
| Keyword: | Virus, Diagnosis, COVID-19, Metabolomics, Biomarkers, Machine learning, Genetic algorithms |
| Full text: | Texto completo (Ver HTML) Texto completo (Ver PDF) |
