Show simple item record

dc.contributor.authorBopche, Rajeev
dc.contributor.authorGustad, Lise Tuset
dc.contributor.authorAfset, Jan Egil
dc.contributor.authorDamås, Jan Kristian
dc.contributor.authorNytrø, Øystein
dc.date.accessioned2023-10-04T08:06:11Z
dc.date.available2023-10-04T08:06:11Z
dc.date.issued2023
dc.description.abstractMedical histories of patients can provide insight into the immediate future of a patient. While most studies propose to predict survival from vital signs and hospital tests within one episode of care, we carry out selective feature engineering from longitudinal historical medical records in this study to develop a dataset with derived features. We then train multiple machine learning models for the binary prediction whether an episode of care will culminate in death among patients suspected of bloodstream infections. The machine learning classifier performance is evaluated and compared and the feature importance impacting the model output is explored. The findings indicated that the logistic regression model achieved the best performance for predicting death in the next hospital episode with an accuracy of 98% and an almost perfect area under the receiver operating characteristic curve. Exploring the feature importance reveals that time to and severity of the last episode and previous history of sepsis episodes were the most critical features.en_US
dc.identifier.citationBopche R, Gustad LT, Afset JE, Damås JK, Nytrø ØN: Predicting in-hospital death from derived EHR trajectory features. In: Seneviratne, Magrabi F. MedInfo 2023 – the 19th World Congress on Medical and Health Informatics: THE FUTURE IS ACCESSIBLE, 2023. IOS Pressen_US
dc.identifier.cristinIDFRIDAID 2181240
dc.identifier.isbn978-1-64368-432-1
dc.identifier.issn0926-9630
dc.identifier.issn1879-8365
dc.identifier.urihttps://hdl.handle.net/10037/31417
dc.language.isoengen_US
dc.publisherIOS Pressen_US
dc.relation.projectIDNorges teknisk-naturvitenskapelige universitet: 80352300en_US
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2023 The Author(s)en_US
dc.titlePredicting in-hospital death from derived EHR trajectory featuresen_US
dc.type.versionacceptedVersionen_US
dc.typeChapteren_US
dc.typeBokkapittelen_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record