dc.creator | Lovelace, Justin | |
dc.date.accessioned | 2021-07-26T03:37:22Z | |
dc.date.available | 2021-07-26T03:37:22Z | |
dc.date.created | 2020-05 | |
dc.date.issued | 2019-04-22 | |
dc.date.submitted | May 2020 | |
dc.identifier.uri | https://hdl.handle.net/1969.1/194454 | |
dc.description.abstract | Unplanned readmissions to the ICU result in higher medical costs and an increase in the likelihood of adverse events, extended hospital stays, and mortality. Machine learning models can leverage the large amount of data stored in electronic health records to predict these cases and provide physicians with more information about patient risk at the time of ICU discharge. Most prior work in this area has focused on developing models using only the structured data found in electronic health records and neglects the large amount of unstructured information stored in clinical notes. This work applies deep learning techniques to these notes to predict ICU readmission and develops models that outperform prior work that focuses only on structured data. | en |
dc.format.mimetype | application/pdf | |
dc.subject | ICU | en |
dc.subject | readmission | en |
dc.subject | clinical | en |
dc.subject | notes | en |
dc.subject | natural | en |
dc.subject | language | en |
dc.subject | processing | en |
dc.subject | medical | en |
dc.subject | mimic | en |
dc.subject | machine | en |
dc.subject | learning | en |
dc.subject | deep | en |
dc.subject | computer | en |
dc.subject | science | en |
dc.title | Prediction of ICU Readmission Using Clinical Notes | en |
dc.type | Thesis | en |
thesis.degree.department | Computer Science & Engineering | en |
thesis.degree.discipline | Computer Science | en |
thesis.degree.grantor | Undergraduate Research Scholars Program | en |
thesis.degree.name | BS | en |
thesis.degree.level | Undergraduate | en |
dc.contributor.committeeMember | Mortazavi, Bobak J | |
dc.type.material | text | en |
dc.date.updated | 2021-07-26T03:37:22Z | |