Using Time Series Analysis to Predict Cardiac Arrest in a PICU
Authors:
- Curtis E. KennedyCKCurtis E. Kennedy
- Noriaki AokiNANoriaki Aoki
- 1 November 2015
- journal article
- online clinical-investigations
- Published by Wolters Kluwer Health in Pediatric Critical Care Medicine
- Vol. 16 (9) , e332-e339
Abstract
Objectives: To build and test cardiac arrest prediction models in a PICU, using time series analysis as input, and to measure changes in prediction accuracy attributable to different classes of time series data. Design: Retrospective cohort study. Setting: Thirty-one bed academic PICU that provides care for medical and general surgical (not congenital heart surgery) patients. Subjects: Patients experiencing a cardiac arrest in the PICU and requiring external cardiac massage for at least 2 minutes. Interventions: None. Measurements and Main Results: One hundred three cases of cardiac arrest and 109 control cases were used to prepare a baseline dataset that consisted of 1,025 variables in four data classes: multivariate, raw time series, clinical calculations, and time series trend analysis. We trained 20 arrest prediction models using a matrix of five feature sets (combinations of data classes) with four modeling algorithms: linear regression, decision tree, neural network, and support vector machine. The reference model (multivariate data with regression algorithm) had an accuracy of 78% and 87% area under the receiver operating characteristic curve. The best model (multivariate + trend analysis data with support vector machine algorithm) had an accuracy of 94% and 98% area under the receiver operating characteristic curve. Conclusions: Cardiac arrest predictions based on a traditional model built with multivariate data and a regression algorithm misclassified cases 3.7 times more frequently than predictions that included time series trend analysis and built with a support vector machine algorithm. Although the final model lacks the specificity necessary for clinical application, we have demonstrated how information from time series data can be used to increase the accuracy of clinical prediction models.Keywords
This publication has 36 references indexed in Scilit:
- Time series analysis as input for clinical predictive modeling: Modeling cardiac arrest in a pediatric ICUTheoretical Biology and Medical Modelling, 2011
- Impact of implementation of evidence-based strategies to reduce door-to-balloon time in patients presenting with STEMI: continuous data analysis and feedback using a statistical process control plotHeart, 2010
- Sensitivity of the Pediatric Early Warning Score to Identify Patient DeteriorationPediatrics, 2010
- Monitor Alarm Fatigue: Standardizing Use of Physiological Monitors and Decreasing Nuisance AlarmsAmerican Journal of Critical Care, 2010
- Telemetry-based vital sign monitoring for ambulatory hospital patients2009
- Pediatric in–intensive-care-unit cardiac arrest: New horizon of extracorporeal life supportCritical Care Medicine, 2006
- Pediatric in-intensive-care-unit cardiac arrest: Incidence, survival, and predictive factors*Critical Care Medicine, 2006
- Reduction of paediatric in-patient cardiac arrest and death with a medical emergency team: preliminary resultsArchives of Disease in Childhood, 2005
- A Prospective Investigation Into the Epidemiology of In-Hospital Pediatric Cardiopulmonary Resuscitation Using the International Utstein Reporting StylePediatrics, 2002
- Validation of a modified Early Warning Score in medical admissionsQJM: An International Journal of Medicine, 2001