Advanced Search
DSpace@MIT

Prediction of postoperative outcomes using intraoperative hemodynamic monitoring data

Research and Teaching Output of the MIT Community

Show simple item record

dc.contributor.author Guerrisi, Maria
dc.contributor.author Dauri, Mario
dc.contributor.author Coniglione, Filadelfo
dc.contributor.author Tisone, Giuseppe
dc.contributor.author De Carolis, Elisa
dc.contributor.author Cillis, Annagrazia
dc.contributor.author Canichella, Antonio
dc.contributor.author Toschi, Nicola
dc.contributor.author Prasad, Varesh
dc.contributor.author Heldt, Thomas
dc.date.accessioned 2017-12-01T13:51:48Z
dc.date.available 2017-12-01T13:51:48Z
dc.date.issued 2017-11
dc.date.submitted 2017-08
dc.identifier.issn 2045-2322
dc.identifier.uri http://hdl.handle.net/1721.1/112328
dc.description.abstract Major surgeries can result in high rates of adverse postoperative events. Reliable prediction of which patient might be at risk for such events may help guide peri- and postoperative care. We show how archiving and mining of intraoperative hemodynamic data in orthotopic liver transplantation (OLT) can aid in the prediction of postoperative 180-day mortality and acute renal failure (ARF), improving upon predictions that rely on preoperative information only. From 101 patient records, we extracted 15 preoperative features from clinical records and 41 features from intraoperative hemodynamic signals. We used logistic regression with leave-one-out cross-validation to predict outcomes, and incorporated methods to limit potential model instabilities from feature multicollinearity. Using only preoperative features, mortality prediction achieved an area under the receiver operating characteristic curve (AUC) of 0.53 (95% CI: 0.44–0.78). By using intraoperative features, performance improved significantly to 0.82 (95% CI: 0.56–0.91, P = 0.001). Similarly, including intraoperative features (AUC = 0.82; 95% CI: 0.66–0.94) in ARF prediction improved performance over preoperative features (AUC = 0.72; 95% CI: 0.50–0.85), though not significantly (P = 0.32). We conclude that inclusion of intraoperative hemodynamic features significantly improves prediction of postoperative events in OLT. Features strongly associated with occurrence of both outcomes included greater intraoperative central venous pressure and greater transfusion volumes. en_US
dc.language.iso en_US
dc.publisher Nature Publishing Group en_US
dc.relation.isversionof http://dx.doi.org/10.1038/s41598-017-16233-4 en_US
dc.rights Creative Commons Attribution en_US
dc.rights.uri http://creativecommons.org/licenses/by/4.0/ en_US
dc.source Heldt en_US
dc.title Prediction of postoperative outcomes using intraoperative hemodynamic monitoring data en_US
dc.type Article en_US
dc.identifier.citation Prasad, Varesh et al. “Prediction of Postoperative Outcomes Using Intraoperative Hemodynamic Monitoring Data.” Scientific Reports 7, 1 (November 2017): 16376 © 2017 he Author(s) en_US
dc.contributor.department Harvard University--MIT Division of Health Sciences and Technology en_US
dc.contributor.department Institute for Medical Engineering and Science en_US
dc.contributor.department Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science en_US
dc.contributor.approver Heldt, Thomas en_US
dc.contributor.mitauthor Prasad, Varesh
dc.contributor.mitauthor Heldt, Thomas
dc.relation.journal Scientific Reports en_US
dc.identifier.mitlicense PUBLISHER_CC en_US
dc.eprint.version Final published version en_US
dc.type.uri http://purl.org/eprint/type/JournalArticle en_US
eprint.status http://purl.org/eprint/status/PeerReviewed en_US
dspace.orderedauthors Prasad, Varesh; Guerrisi, Maria; Dauri, Mario; Coniglione, Filadelfo; Tisone, Giuseppe; De Carolis, Elisa; Cillis, Annagrazia; Canichella, Antonio; Toschi, Nicola; Heldt, Thomas en_US
dspace.embargo.terms N en_US
dc.identifier.orcid https://orcid.org/0000-0003-4125-5205
dc.identifier.orcid https://orcid.org/0000-0002-2446-1499


Files in this item

Name Size Format
Downloadable Full Text - PDF

This item appears in the following Collection(s)

Show simple item record

Creative Commons Attribution Except where otherwise noted, this item's license is described as Creative Commons Attribution
Open Access