Symptom-Based Predictive Model of COVID-19 Disease in Children.


Por: Antoñanzas JM, Perramon A, López C, Boneta M, Aguilera C, Capdevila R, Gatell A, Serrano P, Poblet M, Canadell D, Vilà M, Catasús G, Valldepérez C, Català M, Soler-Palacín P, Prats C, Soriano-Arandes A and The Copedi-Cat Research Group

Publicada: 30 dic 2021 Ahead of Print: 30 dic 2021
Resumen:
BACKGROUND: Testing for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection is neither always accessible nor easy to perform in children. We aimed to propose a machine learning model to assess the need for a SARS-CoV-2 test in children (<16 years old), depending on their clinical symptoms. METHODS: Epidemiological and clinical data were obtained from the REDCap(®) registry. Overall, 4434 SARS-CoV-2 tests were performed in symptomatic children between 1 November 2020 and 31 March 2021, 784 were positive (17.68%). We pre-processed the data to be suitable for a machine learning (ML) algorithm, balancing the positive-negative rate and preparing subsets of data by age. We trained several models and chose those with the best performance for each subset. RESULTS: The use of ML demonstrated an AUROC of 0.65 to predict a COVID-19 diagnosis in children. The absence of high-grade fever was the major predictor of COVID-19 in younger children, whereas loss of taste or smell was the most determinant symptom in older children. CONCLUSIONS: Although the accuracy of the models was lower than expected, they can be used to provide a diagnosis when epidemiological data on the risk of exposure to COVID-19 is unknown.

Filiaciones:
Antoñanzas JM:
 Barcelona School of Informatics, Universitat Politècnica de Catalunya (UPC·BarcelonaTech), 08034 Barcelona, Spain

Perramon A:
 Department of Physics, Universitat Politècnica de Catalunya (UPC·BarcelonaTech), 08028 Barcelona, Spain

López C:
 Barcelona School of Informatics, Universitat Politècnica de Catalunya (UPC·BarcelonaTech), 08034 Barcelona, Spain

Boneta M:
 Barcelona School of Informatics, Universitat Politècnica de Catalunya (UPC·BarcelonaTech), 08034 Barcelona, Spain

Aguilera C:
 Barcelona School of Informatics, Universitat Politècnica de Catalunya (UPC·BarcelonaTech), 08034 Barcelona, Spain

Capdevila R:
 ABS Borges Blanques, Institut Català de Salut (ICS), 25400 Lleida, Spain

Gatell A:
 Equip Pediatria Territorial Alt Penedès-Garraf, Institut Català de Salut (ICS), 28036 Barcelona, Spain

Serrano P:
 Equip Pediatria Territorial Alt Penedès-Garraf, Institut Català de Salut (ICS), 28036 Barcelona, Spain

Poblet M:
 Equip Territorial Pediàtric Sabadell Nord, Institut Català de Salut (ICS), 08206 Barcelona, Spain

Canadell D:
 CAP Barberà del Vallés, 08210 Barcelona, Spain

Vilà M:
 EAP Horta, 08024 Barcelona, Spain

Catasús G:
 CAP Drassanes, 08001 Barcelona, Spain

Valldepérez C:
 Equip Pediatria Territorial Alt Penedès-Garraf, Institut Català de Salut (ICS), 28036 Barcelona, Spain

:
 Department of Physics, Universitat Politècnica de Catalunya (UPC·BarcelonaTech), 08028 Barcelona, Spain

 Comparative Medicine and Bioimage Centre of Catalonia (CMCiB), Fundació Institut d'Investigació en Ciències de la Salut Germans Trias i Pujol (IGTP), 58525 Badalona, Spain

Soler-Palacín P:
 Paediatric Infectious Diseases and Immunodeficiencies Unit, Hospital Universitari Vall d'Hebron, 08035 Barcelona, Spain

Prats C:
 Department of Physics, Universitat Politècnica de Catalunya (UPC·BarcelonaTech), 08028 Barcelona, Spain

Soriano-Arandes A:
 Paediatric Infectious Diseases and Immunodeficiencies Unit, Hospital Universitari Vall d'Hebron, 08035 Barcelona, Spain
ISSN: 19994915





VIRUSES-BASEL
Editorial
Multidisciplinary Digital Publishing Institute (MDPI), ST ALBAN-ANLAGE 66, CH-4052 BASEL, SWITZERLAND, Suiza
Tipo de documento: Article
Volumen: 14 Número: 1
Páginas:
WOS Id: 000747051900001
ID de PubMed: 35062267
imagen Green Published, gold

MÉTRICAS