Resuscitation
-
Cardiac arrest is a leading cause of mortality prior to discharge for children admitted to the pediatric intensive care unit. To address this problem, we used machine learning to predict cardiac arrest up to three hours in advance. ⋯ We have created high-performing models that identify signatures of in-hospital cardiac arrest (IHCA) that may not be evident to clinicians. These signatures include a combination of heart rate variability metrics, vital signs data, and therapeutic drug classes. These machine learning models can predict IHCA up to three hours prior to onset with high performance, allowing clinicians to intervene earlier, improving patient outcomes.
-
Women have less favorable resuscitation characteristics than men. We investigated whether the Advanced Life Support Termination of Resuscitation rule (ALS-TOR) performs equally in women and men. Additionally, we studied whether adding or removing criteria from the ALS-TOR improved classification into survivors and non-survivors. ⋯ For both women and men, the ALS-TOR has high specificity and low miss rate for predicting 30-day OHCA survival. We could not improve the classification with additional characteristics. Employing a simplified version may decrease the number of futile transports to the hospital.