Classification of COVID19 Patients Using Robust Logistic Regression
Coronavirus disease 2019 (COVID19) has triggered a global pandemic affecting millions of people. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causing the COVID-19 disease is hypothesized to gain entry into humans via the airway epithelium, where it initiates a host response. The expr...
| Autores: | , , |
|---|---|
| Formato: | artículo |
| Fecha de publicación: | 2022 |
| País: | España |
| Recursos: | Universidad Complutense de Madrid (UCM) |
| Repositorio: | Docta Complutense |
| Idioma: | inglés |
| OAI Identifier: | oai:docta.ucm.es:20.500.14352/72041 |
| Acesso em linha: | https://hdl.handle.net/20.500.14352/72041 |
| Access Level: | acceso abierto |
| Palavra-chave: | 519.22 616.98:578.834 Density power divergence High-dimensional data Sparse logistic regression COVID-19 Gene expression Estadística matemática (Matemáticas) Enfermedades infecciosas Genética médica Biomatemáticas 1209 Estadística 3205.05 Enfermedades Infecciosas 2410.07 Genética Humana 2404 Biomatemáticas |
| Resumo: | Coronavirus disease 2019 (COVID19) has triggered a global pandemic affecting millions of people. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causing the COVID-19 disease is hypothesized to gain entry into humans via the airway epithelium, where it initiates a host response. The expression levels of genes at the upper airway that interact with the SARS-CoV-2 could be a telltale sign of virus infection. However, gene expression data have been flagged as suspicious of containing different contamination errors via techniques for extracting such information, and clinical diagnosis may contain labelling errors due to the specificity and sensitivity of diagnostic tests. We propose to fit the regularized logistic regression model as a classifier for COVID-19 diagnosis, which simultaneously identifies genes related to the disease and predicts the COVID-19 cases based on the expression values of the selected genes. We apply a robust estimating methods based on the density power divergence to obtain stable results ignoring the effects of contamination or labelling errors in the data and compare its performance with respect to the classical maximum likelihood estimator with different penalties, including the LASSO and the general adaptive LASSO penalties. |
|---|