Early Prediction of Critical Events for Infants with Single Ventricle Physiology in Critical Care Using Routinely Collected Data
Ruiz VM, Saenz L, Lopez-Magallon A, Shields A, Ogoe HA, Suresh S, Munoz R, Tsui FR. Early Prediction of Critical Events for Infants with Single Ventricle Physiology in Critical Care Using Routinely Collected Data. The Journal of Thoracic and Cardiovascular Surgery. 2019. https://doi.org/10.1016/j.jtcvs.2019.01.130.
Critical events are common and difficult to predict among infants with congenital heart disease and are associated with mortality and long-term sequelae. We aimed to achieve early prediction of critical events, i.e., cardiopulmonary resuscitation, emergent endotracheal intubation, and extracorporeal membrane oxygenation in infants with single-ventricle (SV) physiology prior to second-stage surgery. We hypothesized that Naïve Bayesian models learned from expert knowledge and clinical data can predict critical events early and accurately.
We collected 93 single-ventricle patients admitted to ICUs in a single tertiary pediatric hospital between 2014 and 2017. Using knowledge elicited from board-certified pediatric cardiologists and machine-learning techniques, we developed and evaluated the Cardiac-intensive-care Warning INdex (C-WIN) system, consisting of a set of Naïve Bayesian models that leverage routinely-collected data. We evaluated predictive performance using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. We performed the evaluation at five different prediction horizons, i.e., one, two, four, six, and eight hours before the onset of critical events.
The AUCs of the C-WIN models ranged between 0.73 and 0.88 at different prediction horizons. At one hour before critical events, C-WIN was able to detect events with an AUC of 0.88 (95% CI: 0.84-0.92) and a sensitivity of 84% at the 81% specificity level.
Predictive models may enhance clinicians’ ability to identify single-ventricle infants at high risk of critical events. Early prediction of critical events may indicate the need to perform timely interventions, potentially reducing morbidity, mortality, and healthcare costs.