University of Twente Student Theses
Predicting COVID severity using machine learning methods : -Comparison between real life and mimic dataset-
Nae, Teodora (2022) Predicting COVID severity using machine learning methods : -Comparison between real life and mimic dataset-.
|
PDF
904kB |
| Abstract: | After the declaration of the COVID-19 disease as a pandemic, the hospitals were overflowing with patients. Using machine learning methods to predict the severity of the disease can help the professionals from the medical field better allocate the resources in order to minimize the mortality rate. Knowing which patients to prioritize (the ones more likely to have a severe form of the disease rather than the ones with a non-severe form) would help hospitals to better respond to the needs of each individual infected with COVID-19. The CRISP-DM methodology for preparing the datasets was used in this paper to help with organizing and implementing the project. The aim of this research paper is to predict the severity of the disease based on a number of biomarkers, with the help of different machine learning algorithms. As well as to analyze the discrepancies between the results from two different datasets (a mimic dataset versus a real and accurate dataset) with the same features obtained using the same machine learning methods. For the mimic dataset a total of around 4000 entries were used for training the model, while for the real life set a total of around 700 entries matched the requirements for this study. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science BSc (56964) |
| Link to this item: | https://purl.utwente.nl/essays/91745 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page