Format

Send to

Choose Destination
J Clin Monit Comput. 2019 Dec;33(6):973-985. doi: 10.1007/s10877-019-00277-0. Epub 2019 Feb 14.

Predicting tachycardia as a surrogate for instability in the intensive care unit.

Author information

1
Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, University of Pittsburgh, Pittsburgh, PA, USA. yoonjh@upmc.edu.
2
Department of Critical Care Medicine, University of Pittsburgh, Pittsburgh, PA, USA. yoonjh@upmc.edu.
3
, 2557 Terrace Street, 6th Floor, Pittsburgh, PA, 15206, USA. yoonjh@upmc.edu.
4
Auton Lab, Department of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA.
5
School of Nursing, University of Pittsburgh, Pittsburgh, PA, USA.
6
Department of Critical Care Medicine, University of Pittsburgh, Pittsburgh, PA, USA.

Abstract

Tachycardia is a strong though non-specific marker of cardiovascular stress that proceeds hemodynamic instability. We designed a predictive model of tachycardia using multi-granular intensive care unit (ICU) data by creating a risk score and dynamic trajectory. A subset of clinical and numerical signals were extracted from the Multiparameter Intelligent Monitoring in Intensive Care II database. A tachycardia episode was defined as heart rate ≥ 130/min lasting for ≥ 5 min, with ≥ 10% density. Regularized logistic regression (LR) and random forest (RF) classifiers were trained to create a risk score for upcoming tachycardia. Three different risk score models were compared for tachycardia and control (non-tachycardia) groups. Risk trajectory was generated from time windows moving away at 1 min increments from the tachycardia episode. Trajectories were computed over 3 hours leading up to the episode for three different models. From 2809 subjects, 787 tachycardia episodes and 707 control periods were identified. Patients with tachycardia had increased vasopressor support, longer ICU stay, and increased ICU mortality than controls. In model evaluation, RF was slightly superior to LR, which accuracy ranged from 0.847 to 0.782, with area under the curve from 0.921 to 0.842. Risk trajectory analysis showed average risks for tachycardia group evolved to 0.78 prior to the tachycardia episodes, while control group risks remained < 0.3. Among the three models, the internal control model demonstrated evolving trajectory approximately 75 min before tachycardia episode. Clinically relevant tachycardia episodes can be predicted from vital sign time series using machine learning algorithms.

KEYWORDS:

Critical Care; Intensive care unit; Machine learning; Prediction; Tachycardia

Supplemental Content

Full text links

Icon for Springer Icon for PubMed Central
Loading ...
Support Center