An Empirical Investigation of PU Learning for Predicting Length of Stay
| Autor: | Tom Arjannikov, George Tzanetakis |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
2019-20 coronavirus outbreak
Coronavirus disease 2019 (COVID-19) Computer science business.industry Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) food and beverages Hospital based Machine learning computer.software_genre Hospital planning Prediction algorithms Artificial intelligence business PU learning computer Hospital stay |
| Zdroj: | ICHI |
| Popis: | Reliably predicting the length of stay of patients in a hospital based on their demographic and clinical characteristics as well as the care they received can inform hospital planning, particularly in novel response scenarios such as Covid-19. Positive Unlabelled (PU) learning is a type of semi-supervised learning in which only the positive labels in a dataset are reliable. PU learning can be used when the length of stay prediction is formulated as a classification problem, and the prediction needs to be performed dynamically while the patients are being treated. This paper empirically investigates how unlabeling can negatively affect classification accuracy and show how this effect can be mitigated using different algorithms for PU learning. A large dataset of Covid-19 length of hospital stay was used for the experiments. The results show the potential of utilizing PU learning approaches to predicting the length of hospital stay. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|