Hostname: page-component-586b7cd67f-rdxmf Total loading time: 0 Render date: 2024-11-22T23:43:39.390Z Has data issue: false hasContentIssue false
  • English
  • Français

Early identification of impending cardiac arrest in neonates and infants in the cardiovascular ICU: a statistical modelling approach using physiologic monitoring data

Published online by Cambridge University Press:  09 September 2019

Sanjukta N. Bose Open the ORCID record for Sanjukta N. Bose [Opens in a new window] ,
Adam Verigan ,
Jade Hanson ,
Luis M. Ahumada ,
Sharon R. Ghazarian ,
Neil A. Goldenberg ,
Arabela Stock  and
Jeffrey P. Jacobs
Sanjukta N. Bose
Affiliation:
Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA Institute for Computational Medicine, Johns Hopkins University, Baltimore, MD, USA
Adam Verigan
Affiliation:
Johns Hopkins All Children’s Heart Institute, Johns Hopkins All Children’s Hospital, St. Petersburg, FL, USA
Jade Hanson
Affiliation:
Johns Hopkins All Children’s Heart Institute, Johns Hopkins All Children’s Hospital, St. Petersburg, FL, USA Johns Hopkins All Children’s Clinical and Translational Research Organization and All Children’s Research Institute, St. Petersburg, FL, USA
Luis M. Ahumada
Affiliation:
Johns Hopkins All Children’s Health Informatics Core, St. Petersburg, FL, USA
Sharon R. Ghazarian
Affiliation:
Johns Hopkins All Children’s Health Informatics Core, St. Petersburg, FL, USA
Neil A. Goldenberg
Affiliation:
Johns Hopkins All Children’s Heart Institute, Johns Hopkins All Children’s Hospital, St. Petersburg, FL, USA Johns Hopkins All Children’s Clinical and Translational Research Organization and All Children’s Research Institute, St. Petersburg, FL, USA Departments of Pediatrics and Medicine, Divisions of Hematology, Johns Hopkins School of Medicine, Baltimore, MD, USA
Arabela Stock
Affiliation:
Division of Cardiology and Critical Care, New York Presbyterian Weill-Cornell Medical Center, NY, USA
Jeffrey P. Jacobs*
Affiliation:
Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA Institute for Computational Medicine, Johns Hopkins University, Baltimore, MD, USA Johns Hopkins All Children’s Heart Institute, Johns Hopkins All Children’s Hospital, St. Petersburg, FL, USA Johns Hopkins All Children’s Clinical and Translational Research Organization and All Children’s Research Institute, St. Petersburg, FL, USA Johns Hopkins All Children’s Health Informatics Core, St. Petersburg, FL, USA Departments of Pediatrics and Medicine, Divisions of Hematology, Johns Hopkins School of Medicine, Baltimore, MD, USA Division of Cardiology and Critical Care, New York Presbyterian Weill-Cornell Medical Center, NY, USA
*
Author for correspondence: J. P. Jacobs, MD, 2021 Brightwaters Blvd., Saint Petersburg, Florida 33704. Tel: (727) 235-3100; Fax: (727) 551-0404; E-mail: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

Objective:

To develop a physiological data-driven model for early identification of impending cardiac arrest in neonates and infants with cardiac disease hospitalised in the cardiovascular ICU.

Methods:

We performed a single-institution retrospective cohort study (11 January 2013–16 September 2015) of patients ≤1 year old with cardiac disease who were hospitalised in the cardiovascular ICU at a tertiary care children’s hospital. Demographics and diagnostic codes of cardiac arrest were obtained via the electronic health record. Diagnosis of cardiac arrest was validated by expert clinician review. Minute-to-minute physiological monitoring data were recorded via bedside monitors. A generalized linear model was used to compute a minute by minute risk score. Training and test data sets both included data from patients who did and did not develop cardiac arrest. An optimal risk-score threshold was derived based on the model’s discriminatory capacity for impending arrest versus non-arrest. Model performance measures included sensitivity, specificity, accuracy, likelihood ratios, and post-test probability of arrest.

Results:

The final model consisting of multiple clinical parameters was able to identify impending cardiac arrest at least 2 hours prior to the event with an overall accuracy of 75% (sensitivity = 61%, specificity = 80%) and observed an increase in probability of detection of cardiac arrest from a pre-test probability of 9.6% to a post-test probability of 21.2%.

Conclusions:

Our findings demonstrate that a predictive model using physiologic monitoring data in neonates and infants with cardiac disease hospitalised in the paediatric cardiovascular ICU can identify impending cardiac arrest on average 17 hours prior to arrest.

Keywords

Cardiac arrestcardiothoracic surgeryneonateinfantintensive carephysiologic monitoring
Type
Original Article
Information
Cardiology in the Young , Volume 29 , Issue 11 , November 2019 , pp. 1340 - 1348
Copyright
© Cambridge University Press 2019 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Footnotes

‡

The original version of this article was published with one incorrect author name. A notice detailing this has been published and the error rectified in the online and print PDF and HTML copies.

References

Meyer, L, Stubbs, B, Fahrenbruch, C, et al. Incidence, causes, and survival trends from cardiovascular-related sudden cardiac arrest in children and young adults 0 to 35 years of age: a 30-year review. Circulation 2012: 126: 1363–1372.CrossRefGoogle Scholar
Brooten, D, Youngblut, JM, Caicedo, C, et al. Cause of death of infants and children in the intensive care unit: parents’ recall vs chart review. Am J Crit Care 2016; 25: 235–242.CrossRefGoogle ScholarPubMed
Atkins, DL, Everson-Stewart, S, Sears, GK, et al. Epidemiology and outcomes from out-of-hospital cardiac arrest in children. Circulation 2009; 119: 1484–1491.CrossRefGoogle ScholarPubMed
Eisenberg, M, Bergner, L, Hallstrom, A. Epidemiology of cardiac arrest and resuscitation in children. Ann Emergency Med 1983; 12: 672–674.CrossRefGoogle ScholarPubMed
Young, KD, Gausche-Hill, M, McClung, CD, et al. A prospective, population-based study of the epidemiology and outcome of out-of-hospital pediatric cardiopulmonary arrest. Pediatrics 2004; 114: 157–164.CrossRefGoogle ScholarPubMed
Schindler, MB, Bohn, D, Cox, PN, et al. Outcome of out-of-hospital cardiac or respiratory arrest in children. N Engl J Med 1996; 335: 1473–1479.CrossRefGoogle ScholarPubMed
Meert, KL, Donaldson, A, Nadkarni, V, et al. Multicenter cohort study of in-hospital pediatric cardiac arrest. Pediatr Crit Care Med 2009; 10: 544.CrossRefGoogle ScholarPubMed
Tress, EE, Kochanek, PM, Saladino, RA, et al. Cardiac arrest in children. J Emerg Trauma Shock 2010; 3: 267.10.4103/0974-2700.66528CrossRefGoogle ScholarPubMed
Pollack, MM, Patel, KM, Ruttimann, UE. PRISM III: an updated pediatric risk of mortality score. Crit Care Med 1996; 24: 743–752.CrossRefGoogle ScholarPubMed
Pollack, MM, Holubkov, R, Funai, T, et al. The pediatric risk of mortality score: update 2015. Pediatr Crit Care Med 2016; 17: 2.CrossRefGoogle ScholarPubMed
Czaja, AS, Scanlon, MC, Kuhn, EM, et al. Performance of the pediatric index of mortality 2 for pediatric cardiac surgery patients. Pediatr Crit Care Med 2011; 12: 184–189.CrossRefGoogle ScholarPubMed
McLellan, MC, Gauvreau, K, Connor, JA. Validation of the cardiac children’s hospital early warning score: an early warning scoring tool to prevent cardiopulmonary arrests in children with heart disease. Congenital Heart Dis 2014; 9: 194–202.CrossRefGoogle ScholarPubMed
McLellan, MC, Connor, JA. The cardiac children’s hospital early warning score (C-CHEWS). J Pediatr Nurs 2013; 28: 171–178.CrossRefGoogle Scholar
Jeffries, HE, Soto-Campos, G, Katch, A, et al. Pediatric index of cardiac surgical intensive care mortality risk score for pediatric cardiac critical care. Pediatr Crit Care Med 2015; 16: 846–852.CrossRefGoogle ScholarPubMed
O’brien, SM, Clarke, DR, Jacobs, JP, et al. An empirically based tool for analyzing mortality associated with congenital heart surgery. J Thoracic Cardiovasc Surg 2009; 138: 1139–1153.CrossRefGoogle ScholarPubMed
Rogers, L, Ray, S, Johnson, M, et al. The inadequate oxygen delivery index and low cardiac output syndrome score as predictors of adverse events associated with low cardiac output syndrome early after cardiac bypass. Pediatr Crit Care Med 2019; 20: 737–743.CrossRefGoogle ScholarPubMed
Siberry, G, Iannone, R. The Harriet Lane handbook: a manual for pediatric house officers (15th edn). Consultant 2000; 40: 248–248.Google Scholar
Version M. 9.0. 0 (R2016a). MathWorks Inc., Natick, MA, USA, 2016.Google Scholar
Pangerc, U, Jager, F. Robust detection of heart beats in multimodal data using integer multiplier digital filters and morphological algorithms. Computing in Cardiology Conference (CinC), 2014, 2014. IEEE, Cambridge, MA, USA.Google Scholar
Moody, G, Moody, B, Silva, I. Robust detection of heart beats in multimodal data: the physionet/computing in cardiology challenge 2014. Computing in Cardiology Conference (CinC), 2014, 2014. IEEE, Cambridge, MA, USA.Google Scholar
Blough, DK, Madden, CW, Hornbrook, MC. Modeling risk using generalized linear models. J Health Econ 1999; 18: 153–171.CrossRefGoogle ScholarPubMed
Dobson, AJ, Barnett, A. An Introduction to Generalized Linear Models. CRC press, Boca Raton, FL, 2008.Google Scholar
Aitkin, M. A general maximum likelihood analysis of variance components in generalized linear models. Biometrics 1999; 55: 117–128.10.1111/j.0006-341X.1999.00117.xCrossRefGoogle ScholarPubMed
McCullagh, P. Generalized linear models. Eur J Oper Res 1984; 16: 285–292.10.1016/0377-2217(84)90282-0CrossRefGoogle Scholar
Gallop, RJ, Crits-Christoph, P, Muenz, LR, et al. Determination and interpretation of the optimal operating point for ROC curves derived through generalized linear models. Understanding Stat 2003; 2: 219–242.CrossRefGoogle Scholar
Fawcett, T. An introduction to ROC analysis. Pattern Recogn Lett 2006; 27: 861–874.CrossRefGoogle Scholar
Greiner, M, Pfeiffer, D, Smith, R. Principles and practical application of the receiver-operating characteristic analysis for diagnostic tests. Prev Vet Med 2000; 45: 23–41.CrossRefGoogle ScholarPubMed
Hodgetts, TJ, Kenward, G, Vlachonikolis, IG, et al. The identification of risk factors for cardiac arrest and formulation of activation criteria to alert a medical emergency team. Resuscitation 2002; 54: 125–131.CrossRefGoogle ScholarPubMed
Fieselmann, JF, Hendryx, MS, Helms, CM, et al. Respiratory rate predicts cardiopulmonary arrest for internal medicine inpatients. J Gen Int Med 1993; 8: 354–360.CrossRefGoogle ScholarPubMed
Ghuran, A, Reid, F, La Rovere, MT, et al. Heart rate turbulence-based predictors of fatal and nonfatal cardiac arrest (The autonomic tone and reflexes after myocardial infarction substudy). Am J Cardiol 2002; 89: 184–190.CrossRefGoogle Scholar
Kleiger, RE, Stein, PK, Bigger, JT. Heart rate variability: measurement and clinical utility. Ann Noninvas Electro 2005; 10: 88–101.CrossRefGoogle ScholarPubMed
La Rovere, MT, Bigger, JT, Marcus, FI, et al. Baroreflex sensitivity and heart-rate variability in prediction of total cardiac mortality after myocardial infarction. Lancet 1998; 351: 478–484.CrossRefGoogle ScholarPubMed
Malik, M. Heart rate variability. Circulation 1996; 93: 1043–1065.Google Scholar
Martin, GJ, Magid, NM, Myers, G, et al. Heart rate variability and sudden death secondary to coronary artery disease during ambulatory electrocardiographic monitoring. Am J Cardiol 1987; 60: 86–89.CrossRefGoogle ScholarPubMed
Nolan, J, Batin, PD, Andrews, R, et al. Prospective study of heart rate variability and mortality in chronic heart failure. Circulation 1998; 98: 1510–1516.CrossRefGoogle ScholarPubMed
Singer, DH, Martin, GJ, Magid, N, et al. Low heart rate variability and sudden cardiac death. J Electro 1988; 21: S46–S55.CrossRefGoogle ScholarPubMed
Galinier, M, Pathak, A, Fourcade, J, et al. Depressed low frequency power of heart rate variability as an independent predictor of sudden death in chronic heart failure. Eur Heart J 2000; 21: 475–482.CrossRefGoogle ScholarPubMed
Lahiri, MK, Kannankeril, PJ, Goldberger, JJ. Assessment of autonomic function in cardiovascular disease. J Am Coll Cardiol 2008; 51: 1725–1733.CrossRefGoogle ScholarPubMed
Kennedy, CE, Aoki, N, Mariscalco, M, et al. Using time series analysis to predict cardiac arrest in a pediatric intensive care unit. Pediatr Crit Care Med 2015; 16: e332.CrossRefGoogle Scholar
Kennedy, CE, Turley, JP. Time series analysis as input for clinical predictive modeling: modeling cardiac arrest in a pediatric ICU. Theor Biol Med Model 2011; 8: 40.10.1186/1742-4682-8-40CrossRefGoogle Scholar
McCullagh, P, Nelder, JA. Generalized Linear Models, Vol. 37. CRC Press, Boca Raton, FL, 1989.CrossRefGoogle Scholar
Nelder, JA, Baker, RJ. Generalized Linear Models. Wiley, Hoboken, NJ, 1972.Google Scholar
McCullagh, P, Nelder, J. Generalized Linear Models. Chapman and Hall, New York, 1983.CrossRefGoogle Scholar
Deeks, JJ, Altman, DG. Diagnostic tests 4: likelihood ratios. BMJ 2004; 329: 168–169.CrossRefGoogle ScholarPubMed
Akobeng, AK. Understanding diagnostic tests 2: likelihood ratios, pre-and post-test probabilities and their use in clinical practice. Acta Paediatr 2007; 96: 487–491.CrossRefGoogle ScholarPubMed