Predicting the onset of delirium on hourly basis in an intensive care unit following cardiac surgery

Lapp, Linda and Roper, Marc and Kavanagh, Kimberley and Schraag, Stefan; Shen, Linlin and Gonzalez, Alejandro Rodriguez and Santosh, KC and Lai, Zhihui and Sicilia, Rosa and Almeida, Joao Rafael and Kane, Bridget, eds. (2022) Predicting the onset of delirium on hourly basis in an intensive care unit following cardiac surgery. In: 2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS). IEEE, Piscataway, N.J., pp. 234-239. ISBN 9781665467704 (https://doi.org/10.1109/cbms55023.2022.00048)

[thumbnail of Lapp-etal-IEEE-CBMS-2022-Predicting-the-onset-of-delirium-on-hourly]
Preview
 Text. Filename: Lapp_etal_IEEE_CBMS_2022_Predicting_the_onset_of_delirium_on_hourly.pdf
Accepted Author Manuscript
License: Strathprints license 1.0
Download (987kB)| Preview

Abstract

Delirium, affecting up to 52% of cardiac surgery patients, can have serious long-term effects on patients by damaging cognitive ability and causing subsequent functional decline. This study reports on the development and evaluation of predictive models aimed at identifying the likely onset of delirium on an hourly basis in intensive care unit following cardiac surgery. Most models achieved a mean AUC > 0.900 across all lead times. A support vector machine achieved the highest performance across all lead times of AUC = 0.941 and Sensitivity = 0.907, and BARTm, where missing values were replaced with missForest imputation, achieved the highest Specificity of 0.892. Being able to predict delirium hours in advance gives clinicians the ability to intervene and optimize treatments for patients who are at risk and avert potentially serious and life-threatening consequences.

CORE (COnnecting REpositories)