September 10, 2025Scientific ReportsOpen Access

Explainable machine learning for predicting ICU mortality in myocardial infarction patients using pseudo-dynamic data

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Retrospective analysis shows improved mortality prediction in ICU patients with myocardial infarction, highlighting the use of explainable models.

XMI-ICU predicts ICU mortality up to 24 hours before the event, enhancing patient management.
Achieved AUROC of 92.0 for 6-hour mortality prediction, indicating high accuracy in a diverse cohort.
The explainable machine learning framework enables time-resolved interpretability, aiding clinical decision-making.
Validates across different patient datasets, suggesting broader applicability in real-world ICU settings.

Mesinovic et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

September 10, 2025Scientific ReportsOpen Access

View Full Paper

Ask AI

Bookmark

Authors

Retrospective analysis shows improved mortality prediction in ICU patients with myocardial infarction, highlighting the use of explainable models.

XMI-ICU predicts ICU mortality up to 24 hours before the event, enhancing patient management.
Achieved AUROC of 92.0 for 6-hour mortality prediction, indicating high accuracy in a diverse cohort.
The explainable machine learning framework enables time-resolved interpretability, aiding clinical decision-making.
Validates across different patient datasets, suggesting broader applicability in real-world ICU settings.

Mesinovic et al. (2025) studied this question.

Synapse has enriched one closely related paper. Consider it for comparative context:

View Full Paper

Ask AI

Bookmark