Early Changes in Near-Infrared Spectroscopy Are Associated With Cardiac Arrest in Children With Congenital Heart Disease

BACKGROUND: The association of near-infrared spectroscopy (NIRS) with various outcomes after pediatric cardiac surgery has been studied extensively. However, the role of NIRS in the prediction of cardiac arrest (CA) in children with heart disease has yet to be evaluated. We sought to determine if a model utilizing regional cerebral oximetry (rSO2c) and somatic oximetry (rSO2s) could predict CA in children admitted to a single-center pediatric cardiac intensive care unit (CICU). METHODS: We retrospectively reviewed 160 index CA events for patients admitted to our pediatric CICU between November 2010 and January 2019. We selected 711 control patients who did not have a cardiac arrest. Hourly data was collected from the electronic health record (EHR). We previously created a machine-learning algorithm to predict the risk of CA using EHR data. Univariable analysis was done on these variables, which we then used to create a multivariable logistic regression model. The outputs from the model were presented by odds ratio (OR) and 95% confidence interval (CI). RESULTS: We created a multivariable model to evaluate the association of CA using five variables: arterial saturation (SpO2)- rSO2c difference, SpO2-rSO2s difference, heart rate, diastolic blood pressure, and vasoactive inotrope score. While the SpO2-rSO2c difference was not a significant contributor to the multivariable model, the SpO2-rSO2s difference was. The average SpO2-rSO2s difference cutoff with the best prognostic accuracy for CA was 29% [CI 26–31%]. In the multivariable model, a 10% increase in the SpO2-rSO2s difference was independently associated with increased odds of CA [OR 1.40 (1.18, 1.67), P < 0.001] at 1 h before CA. Our model predicted CA with an AUROC of 0.83 at 1 h before CA. CONCLUSION: In this single-center case-control study of children admitted to a pediatric CICU, we created a multivariable model utilizing hourly data from the EHR to predict CA. At 1 h before the event, for every 10% increase in the SpO2-rSO2s difference, the odds of cardiac arrest increased by 40%. These findings are important as the field explores ways to capitalize on the wealth of data at our disposal to improve patient care.