How much information is needed to predict outcomes after cardiac arrest?

Introduction: Prognostication after cardiac arrest is challenging but may be improved with machine learning (ML). ML accommodates large quantities of data, but in practice these arise from heterogeneous sources that may be challenging to assemble. We compared ML performance with combinations of registry, electronic health record (EHR) and electroencephalography (EEG) data to test if only a subset of sources was sufficient.

Recovery Potential in Patients After Cardiac Arrest Who Die After Limitations or Withdrawal of Life Support.

Importance: Understanding the relationship between patients' clinical characteristics and outcomes is fundamental to medicine. When critically ill patients die after withdrawal of life-sustaining therapy (WLST), the inability to observe the potential for recovery with continued aggressive care could bias future clinical decisions and research.

Objective: To quantify the frequency with which experts consider patients who died after WLST following resuscitated cardiac arrest to have had recovery potential if life-sustaining therapy had been continued.