Curtis E Kennedy1, Noriaki Aoki, Michele Mariscalco, James P Turley. 1. 1Section of Critical Care Medicine, Department of Pediatrics, Baylor College of Medicine, Houston, TX. 2Department of Pediatrics, University of Illinois College of Medicine, Urbana, IL. 3The University of Texas School of Biomedical Informatics, Houston, TX.
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.
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.
Authors: Babu Kunadian; Robert Morley; Anthony P Roberts; Zulfiquar Adam; Darragh Twomey; James A Hall; Robert A Wright; Andrew G C Sutton; Douglas F Muir; Mark A de Belder Journal: Heart Date: 2010-08-23 Impact factor: 5.994
Authors: Christina Orphanidou; David Clifton; Shahab Khan; Marc Smith; Jacques Feldmar; Lionel Tarassenko Journal: Conf Proc IEEE Eng Med Biol Soc Date: 2009
Authors: Nienke de Mos; Raphaele R L van Litsenburg; Brian McCrindle; Desmond J Bohn; Christopher S Parshuram Journal: Crit Care Med Date: 2006-04 Impact factor: 7.598
Authors: Craig Futterman; Joshua W Salvin; Michael McManus; Adam W Lowry; Dimitar Baronov; Melvin C Almodovar; Jose A Pineda; Vinay M Nadkarni; Peter C Laussen; Avihu Z Gazit Journal: Resuscitation Date: 2019-07-17 Impact factor: 5.262
Authors: Joost D J Plate; Rutger R van de Leur; Luke P H Leenen; Falco Hietbrink; Linda M Peelen; M J C Eijkemans Journal: BMC Med Res Methodol Date: 2019-10-26 Impact factor: 4.615