Early prediction of shock in intensive care unit patients by machine learning using discrete electronic health record data

Abstract

Purpose

To use machine learning to predict new-onset shock for at-risk intensive care unit (ICU) patients based on discrete vital sign data from the electronic health record.

Methods and results

We included 11,305 adult cardiac, medical, neurological, and surgical ICU patients who did not have shock within 4 h of ICU admission. We used routine vital sign data collected from the first 4 h of the ICU stay to predict new-onset shock within the subsequent 4 h. We compared logistic regression with machine learning models including elastic net, random forest, boosted trees and extreme gradient boosting (XGB). Median age was 64.0 years (44.5 % females). New-onset shock after 4 h developed in 483 (4.3 %) patients, and these patients had higher ICU (8.5 % vs. 1.9 %) and in-hospital (14.3 % vs. 5.0 %) mortality. Standard logistic regression had limited discrimination for new-onset shock, with the best single predictors being the maximum shock index and the minimum blood pressure during the second 2 h of the ICU stay. Discrimination in the validation cohort (n = 2826) was better for each ML model: elastic net, 0.76; boosted tree, 0.76; random forest, 0.79; XGB, 0.82; each model had ≥ 98 % negative predictive value. Accuracy was highest (81 %) with XGB, although positive predictive value was only 14 %. The XGB model also predicted in-hospital mortality with good discrimination.

Conclusions

Machine learning prediction models can achieve very good discrimination and accuracy for new-onset shock in ICU patients using vital sign data within 4 h after ICU admission.