Data analytics in pediatric cardiac intensive care: How and what can we learn to improve care

Abstract

Infants and children with congenital and acquired heart disease carry a significant burden of morbidity and mortality around the time of cardiothoracic surgery and cardiopulmonary bypass. Identifying patients with unstable physiology, at risk for clinical deterioration, is a constant struggle, limited by issues of patient complexity, information overload, and distraction all competing for the finite resource of clinician cognitive processing throughput. Advances in clinical data management and analysis hold the potential to assist clinicians in identifying patients at high risk of deterioration. High-frequency, high-fidelity capture of physiologic data can improve diagnostic precision and identification of rapidly changing patient states. Optimal formatting of data display can improve clinician comprehension of patient state and decrease cognitive burden. Finally, using this data to build novel clinical decision support tools can assist the inexperienced, fatigued, distracted, or unaware clinician in making appropriate and timely clinical decisions on critically ill patients.