Por favor, use este identificador para citar o enlazar este ítem:
http://conacyt.repositorioinstitucional.mx/jspui/handle/1000/3110| COVID-19 diagnosis prediction in emergency care patients: a machine learning approach | |
| Batista Andre Filipe de Moraes. Miraglia Joao Luiz. Donato Thiago Henrique Rizzi. Chiavegatto Filho Alexandre Dias Porto. | |
| Acceso Abierto | |
| Atribución-NoComercial-SinDerivadas | |
| 10.1101/2020.04.04.20052092 | |
| The coronavirus disease (COVID-19) pandemic has increased the necessity of immediate clinical decisions and effective usage of healthcare resources. Currently, the most validated diagnosis test for COVID-19 (RT-PCR) is in shortage in most developing countries, which may increase infection rates and delay important preventive measures. The objective of this study was to predict the risk of positive COVID-19 diagnosis with machine learning, using as predictors only results from emergency care admission exams. We collected data from a sample of 235 adult patients from the Hospital Israelita Albert Einstein in Sao Paulo, Brazil, from 17 to 30 of March, 2020, of which 102 (43%) received a positive diagnosis of COVID-19 from RT-PCR tests. Five machine learning algorithms (neural networks, random forests, gradient boosting trees, logistic regression and support vector machines) were trained on a random sample of 70% of the patients, and performance was tested on new unseen data (30%). The best predictive performance was obtained by the support vector machines algorithm (AUC: 0.85; Sensitivity: 0.68; Specificity: 0.85; Brier Score: 0.16). In conclusion, we found that targeted decisions for receiving COVID-19 tests using only routinely-collected data is a promising new area with the use of machine learning algorithms. | |
| www.medrxiv.org | |
| 2020 | |
| Artículo | |
| https://www.medrxiv.org/content/medrxiv/early/2020/04/07/2020.04.04.20052092.full.pdf | |
| Inglés | |
| VIRUS RESPIRATORIOS | |
| Aparece en las colecciones: | Artículos científicos |
Cargar archivos:
| Fichero | Tamaño | Formato | |
|---|---|---|---|
| 1103467.pdf | 408.8 kB | Adobe PDF | Visualizar/Abrir |