Your browser doesn't support javascript.
Assessing Hospitalization for SARS-CoV-2 Confirmed Cases by a Cross-Entropy Weighted Ensemble Classifier
Virtual Meeting of the Mexican Statistical Association, AME 2020 and 34FNE meeting, 2021 ; 397:65-80, 2022.
Article in English | Scopus | ID: covidwho-2173617
ABSTRACT
The potential need of hospitalization for patients with acute respiratory COVID-19 infection caused by the SARS-CoV2 virus is a critical decision, as it has a direct effect on the potential response. In addition, it leads to an allocation of resources (bed, care, and medical personnel) that, given the pandemic, are limited. According to official information reported since March 1, 2020 and updated to June 30, 2021, an ensemble of classifiers weighted by the cross-entropy information measure is proposed. We considered data based on the knowledge of a set of features before a wide availability of vaccines or identified variants of the virus were present. The aim is to contribute toward the enhancement of a better-informed assessment of risk by the general population when exposed to the disease in the aforementioned period. The results show an improvement in the detection of cases susceptible to hospitalization, with an accuracy of 91.46%, and in a restrictive scenario, there is a preventive alert to patients, even though under the established criteria should not be admitted, to remain under monitoring to anticipate the evolution of the disease to a severe stage. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Keywords

Full text: Available Collection: Databases of international organizations Database: Scopus Type of study: Randomized controlled trials Language: English Journal: Virtual Meeting of the Mexican Statistical Association, AME 2020 and 34FNE meeting, 2021 Year: 2022 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: Databases of international organizations Database: Scopus Type of study: Randomized controlled trials Language: English Journal: Virtual Meeting of the Mexican Statistical Association, AME 2020 and 34FNE meeting, 2021 Year: 2022 Document Type: Article