March 3, 2026Open Access

Predicting recurrent cardiac arrest within one year after surviving in-hospital cardiac arrest using a machine learning model

Key Result

An XGBoost model predicted recurrent cardiac arrest or death within one year after IHCA with modest performance and good accuracy.

Key Points

Recurrent cardiac arrest prediction achieved good accuracy within one year for IHCA survivors, indicating model potential.
The XGBoost model demonstrated a modest performance, with implications for future risk assessment strategies.
Analysis utilized a machine learning approach to identify risk factors associated with recurrent cardiac events.
Further validation is necessary to confirm clinical applicability of this prediction model for long-term outcomes.

Structured PICO

Can an XGBoost machine learning model predict recurrent cardiac arrest or death within one year in survivors of in-hospital cardiac arrest?

Population

Survivors of in-hospital cardiac arrest (IHCA)

Intervention

XGBoost machine learning predictive model

Outcome

Composite of recurrent cardiac arrest or death within one year after IHCAcomposite

An XGBoost machine learning model shows potential utility in predicting the one-year risk of recurrent cardiac arrest or death in patients who survive an initial in-hospital cardiac arrest.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

In this dataset, an XGBoost model could predict recurrent cardiac arrest or death within one year after IHCA with a modest performance and good accuracy. If these results can be validated, this model could potentially be used clinically to assess the risk of another cardiac arrest in survivors of IHCA.