Machine learning for mortality analysis in patients with COVID-19
| Autor: | Pablo Rodríguez-Belenguer, Antonio J. Serrano-López, Emilio Soria-Olivas, Yasser Alakhdar-Mohmara, Manuel A. Sánchez-Montañés |
|---|---|
| Přispěvatelé: | UAM. Departamento de Ingeniería Informática |
| Rok vydání: | 2020 |
| Předmět: |
feature importance
Computer science Health Toxicology and Mutagenesis Pneumonia Viral Decision tree lcsh:Medicine Sample (statistics) Machine learning computer.software_genre Logistic regression Article survival analysis Biclustering 03 medical and health sciences Betacoronavirus 0302 clinical medicine Risk of mortality graphical models Humans 030212 general & internal medicine Graphical model Pandemics Survival analysis Informática 0303 health sciences 030306 microbiology business.industry SARS-CoV-2 Decision Trees lcsh:R Public Health Environmental and Occupational Health COVID-19 Decision rule Feature importance machine learning Spain Artificial intelligence Graphical models business Coronavirus Infections computer |
| Zdroj: | Biblos-e Archivo. Repositorio Institucional de la UAM instname International Journal of Environmental Research and Public Health, Vol 17, Iss 8386, p 8386 (2020) International Journal of Environmental Research and Public Health Volume 17 Issue 22 |
| Popis: | This paper analyzes a sample of patients hospitalized with COVID-19 in the region of Madrid (Spain). Survival analysis, logistic regression, and machine learning techniques (both supervised and unsupervised) are applied to carry out the analysis where the endpoint variable is the reason for hospital discharge (home or deceased). The different methods applied show the importance of variables such as age, O2 saturation at Emergency Rooms (ER), and whether the patient comes from a nursing home. In addition, biclustering is used to globally analyze the patient-drug dataset, extracting segments of patients. We highlight the validity of the classifiers developed to predict the mortality, reaching an appreciable accuracy. Finally, interpretable decision rules for estimating the risk of mortality of patients can be obtained from the decision tree, which can be crucial in the prioritization of medical care and resources. This research was funded by Agencia Estatal de Investigación AEI/FEDER Spain, Project PGC2018-095895-B-I00, and Comunidad Autónoma de Madrid, Spain, Project S2017/BMD-3688 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|