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.
Copyright © 2016 The American Association for Thoracic Surgery. Published by Elsevier Inc. All rights reserved.