What type of study is this?

October 12, 2025Open Access

Explainable Artificial Intelligence for Prognostic Stratification in Out-of-Hospital Cardiac Arrest Patients Undergoing Extracorporeal Cardiopulmonary Resuscitation.

View Full Paper

Ask AI

Bookmark

Authors

Retrospective analysis reveals AI achieves AUC of 0.85 in predicting outcomes for OHCA patients, highlighting the role of explainable AI.

AI models accurately predicted short-term outcomes in patients undergoing ECPR, showing notable predictive power.
In cohort 1, 26.7% experienced all-cause death on day 1, with AI models achieving a strong AUC of 0.85.
SHAP analysis revealed differences in key predictive variables across cohorts, emphasizing the model's interpretability.
SHAP-based clustering identified distinct prognostic subgroups, which supports personalized treatment strategies.

Watanabe et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark