Secondary Logo

Institutional members access full text with Ovid®

Share this article on:

Applying Artificial Intelligence to Identify Physiomarkers Predicting Severe Sepsis in the PICU*

Kamaleswaran, Rishikesan, PhD1,2; Akbilgic, Oguz, PhD1; Hallman, Madhura A., MD, MPH2; West, Alina N., MD, PhD2; Davis, Robert L., MD, MPH1; Shah, Samir H., MD, MBA, FRCPC2

Pediatric Critical Care Medicine: October 2018 - Volume 19 - Issue 10 - p e495–e503
doi: 10.1097/PCC.0000000000001666
Online Clinical Investigations

Objectives: We used artificial intelligence to develop a novel algorithm using physiomarkers to predict the onset of severe sepsis in critically ill children.

Design: Observational cohort study.

Setting: PICU.

Patients: Children age between 6 and 18 years old.

Interventions: None.

Measurements and Main Results: Continuous minute-by-minute physiologic data were available for a total of 493 critically ill children admitted to a tertiary care PICU over an 8-month period, 20 of whom developed severe sepsis. Using an alert time stamp generated by an electronic screening algorithm as a reference point, we studied up to 24 prior hours of continuous physiologic data. We identified physiomarkers, including SD of heart rate, systolic and diastolic blood pressure, and symbolic transitions probabilities of those variables that discriminated severe sepsis patients from controls (all other patients admitted to the PICU who did not meet severe sepsis criteria). We used logistic regression, random forests, and deep Convolutional Neural Network methods to derive our models. Analysis was performed using data generated in two windows prior to the firing of the electronic screening algorithm, namely, 2–8 and 8–24 hours. When analyzing the physiomarkers present in the 2–8 hours analysis window, logistic regression performed with specificity of 87.4% and sensitivity of 55.0%, random forest performed with 79.6% specificity and 80.0% sensitivity, and the Convolutional Neural Network performed with 83.0% specificity and 75.0% sensitivity. When analyzing physiomarkers from the 8–24 hours window, logistic regression resulted in 77.1% specificity and 39.3% sensitivity, random forest performed with 82.3% specificity and 61.1% sensitivity, whereas the Convolutional Neural Network method achieved 81% specificity and 76% sensitivity.

Conclusions: Artificial intelligence can be used to predict the onset of severe sepsis using physiomarkers in critically ill children. Further, it may detect severe sepsis as early as 8 hours prior to a real-time electronic severe sepsis screening algorithm.

1Center for Biomedical Informatics, Department of Pediatrics, University of Tennessee Health Science Center, Memphis, TN.

2Division of Pediatric Critical Care Medicine, Department of Pediatrics, University of Tennessee Health Science Center, Memphis, TN.

*See also p. 1004.

Supplemental digital content is available for this article. Direct URL citations appear in the printed text and are provided in the HTML and PDF versions of this article on the journal’s website (http://journals.lww.com/pccmjournal).

Dr. West received funding from Learn4Life (board member). Dr. Davis received funding from GlaxoSmithKline. The remaining authors have disclosed that they do not have any potential conflicts of interest.

For information regarding this article, E-mail: rkamales@uthsc.edu

©2018The Society of Critical Care Medicine and the World Federation of Pediatric Intensive and Critical Care Societies