Institutional Repository of Vilnius University
COVID-19 pacientų mirtingumo prognozavimas taikant statistinius ir mašininio mokymo metodus /
Abstract
dc:descriptionAt the end of 2019, the outbreak of the SARS-CoV-2 coronavirus, which causes COVID-19, became a global health catastrophe. This crisis resulted in an enormous number of deaths, highlighting the need for reliable predictive models. Now, after more than four years from the start of pandemic, a substantial amount of data has been collected, offering an opportunity to refine these models and enhance their accuracy and utility. Data is being used to analyze how various demographic and clinical characteristics, as well as laboratory test results, influence patient survival. Durning this study 12 predictive models were developed using statistical methods, such as logistic regression and stepwise regression, along with regularization techniques and machine learning algorithms like support vector machines and random forests. Insights are provided for each model, detailing their strengths and weaknesses, and describing the specific circumstances under which each model performs optimally. The study found that stepwise regression with direct selection and random forest models demonstrated the best predictive performance.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Lycholip, Valentinas,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD210644657&prefLang=en_US