dc.contributor.author | Hammerbeck, Andreas | |
dc.date.accessioned | 2020-06-27T04:27:43Z | |
dc.date.available | 2020-06-27T04:27:43Z | |
dc.date.issued | 2020-06-27 | |
dc.date.submitted | 2020-06-26T22:00:07Z | |
dc.identifier.uri | https://hdl.handle.net/1956/23070 | |
dc.description.abstract | Diabetes is a growing healthcare problem in the world, which affects over 400 million adults. In collaboration with Haukeland University Hospital, we look at medical records from real patients diagnosed with diabetes. The study uses machine learning to predict if a given patient has a high risk of experiencing medical deterioration. Further, the thesis goes through the data cleaning necessary to provide such predictions. The first approach managed to identify 79\% of high-risk patients. If the model classifies a patient to have a high risk of mortality, the model had an accuracy of 18\%. In the second approach, we removed the last four weeks before mortality happens, and the model was able to identify 49\% of the patients with high risk. If the model classifies a patient to have a high risk of mortality, the model had an accuracy of 12\%. | en_US |
dc.language.iso | eng | |
dc.publisher | The University of Bergen | en_US |
dc.rights | Copyright the Author. All rights reserved | |
dc.title | Early detection of medical deterioration of patients with diabetes by using machine learning | |
dc.type | Master thesis | |
dc.date.updated | 2020-06-26T22:00:07Z | |
dc.rights.holder | Copyright the Author. All rights reserved | en_US |
dc.description.degree | Masteroppgave i Programutvikling samarbeid med HVL | en_US |
dc.description.localcode | PROG399 | |
dc.description.localcode | MAMN-PROG | |
dc.subject.nus | 754199 | |
fs.subjectcode | PROG399 | |
fs.unitcode | 12-12-0 | |