Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Observational Study
. 2016 Jul;152(1):171-7.
doi: 10.1016/j.jtcvs.2016.03.083. Epub 2016 Apr 16.

Prediction of imminent, severe deterioration of children with parallel circulations using real-time processing of physiologic data

Craig G Rusin  1 , Sebastian I Acosta  2 , Lara S Shekerdemian  3 , Eric L Vu  4 , Aarti C Bavare  3 , Risa B Myers  5 , Lance W Patterson  2 , Ken M Brady  4 , Daniel J Penny  2
Affiliations
Observational Study

Prediction of imminent, severe deterioration of children with parallel circulations using real-time processing of physiologic data

Craig G Rusin et al. J Thorac Cardiovasc Surg. 2016 Jul.

Abstract

Objectives: Sudden death is common in patients with hypoplastic left heart syndrome and comparable lesions with parallel systemic and pulmonary circulation from a common ventricular chamber. It is hypothesized that unforeseen acute deterioration is preceded by subtle changes in physiologic dynamics before overt clinical extremis. Our objective was to develop a computer algorithm to automatically recognize precursors to deterioration in real-time, providing an early warning to care staff.

Methods: Continuous high-resolution physiologic recordings were obtained from 25 children with parallel systemic and pulmonary circulation who were admitted to the cardiovascular intensive care unit of Texas Children's Hospital between their early neonatal palliation and stage 2 surgical palliation. Instances of cardiorespiratory deterioration (defined as the need for cardiopulmonary resuscitation or endotracheal intubation) were found via a chart review. A classification algorithm was applied to both primary and derived parameters that were significantly associated with deterioration. The algorithm was optimized to discriminate predeterioration physiology from stable physiology.

Results: Twenty cardiorespiratory deterioration events were identified in 13 of the 25 infants. The resulting algorithm was both sensitive and specific for detecting impending events, 1 to 2 hours in advance of overt extremis (receiver operating characteristic area = 0.91, 95% confidence interval = 0.88-0.94).

Conclusions: Automated, intelligent analysis of standard physiologic data in real-time can detect signs of clinical deterioration too subtle for the clinician to observe without the aid of a computer. This metric may serve as an early warning indicator of critical deterioration in patients with parallel systemic and pulmonary circulation.

Keywords: critical deterioration; predictive analytics; single ventricle.

PubMed Disclaimer

Conflict of interest statement

Disclosures

Craig Rusin is the co-founder of Medical Informatics Corp. Medical Informatics provided no funding and/or support for the study. There are no conflicts for the other authors.

Figures

Figure 1
Figure 1
Performance of the optimized logistic regression model. (A) Histogram of the optimized classification algorithm for the control and pre-deterioration data sets projected on the axis of optimal separation (α). (B) The receiver operating characteristic curve for the optimized classification algorithm (ROC Area=0.91). (C) The sensitivity and specificity for the optimized classification model as a function of the choice of Risk Index threshold. (D) The positive likelihood ratio as a function of the choice of Risk Index threshold.
Figure 2
Figure 2
Vital signs (Top) and the Risk Index (Bottom) as a function of time until a critical deterioration event (t=0).
Figure 3
Figure 3
Performance of the predictive model as a function of time from the start of a cardio-respiratory deterioration event. Maximum forecasting time of the model is between four and five hours.
Figure 4
Figure 4
(Left) The observed distribution of the Risk Index metric for all subjects. The most common value of Risk Index was found to be 0.6. (Right) The cumulative distribution function of the Risk Index metric for all subjects. The prevalence of the metric was observed to be 50% for values >1, 10% for values <3.3, and 1% for values >20.
See this image and copyright information in PMC

Comment in

References

    1. Barron DJ, Kilby MD, Davies B, Wright JG, Jones TJ, Brawn WJ. Hypoplastic left heart syndrome. Lancet [Internet] Elsevier Ltd. 2009;374(9689):551–64. Available from: http://dx.doi.org/10.1016/S0140-6736(09)60563-8. - DOI - PubMed
    1. Norwood WI, Kirklin JK, Sanders SP. Hypoplastic left heart syndrome: experience with palliative surgery. Am J Cardiol. 1980;45(1):87–91. - PubMed
    1. Welke KF, Shen I, Ungerleider RM. Current Assessment of Mortality Rates in Congenital Cardiac Surgery. Ann Thorac Surg. 2006;82(1):164–71. - PubMed
    1. Schwartz RS, Murphy JG, Edwards WD, Camrud aR, Vliestra RE, Holmes DR. Restenosis after balloon angioplasty. A practical proliferative model in porcine coronary arteries. Circulation. 1990;82(6):2190–200. - PubMed
    1. Ohye RG, Schonbeck JV, Eghtesady P, Laussen PC, Pizarro C, Shrader P, et al. Cause, timing, and location of death in the Single Ventricle Reconstruction trial. J Thorac Cardiovasc Surg [Internet] The American Association for Thoracic Surgery. 2012;144(4):907–14. Available from: http://dx.doi.org/10.1016/j.jtcvs.2012.04.028. - DOI - PMC - PubMed

Publication types

MeSH terms