Skip to main content
Fig. 2 | BMC Medical Informatics and Decision Making

Fig. 2

From: Explainable machine learning to predict long-term mortality in critically ill ventilated patients: a retrospective study in central Taiwan

Fig. 2

Receiver operating characteristic curves demonstrating the performance of the three machine learning models for predicting the mortality at 30-day (A), 90-day (B), and 1-year (C). Area under curve (A 30-day, XGBoost 0.858, 95% CI 0.830–0.886; RF 0.840, 95% CI 0.811–0.869; LR 0.837, 95% CI 0.805–0.869) (B 90-day, XGBoost 0.839, 95% CI 0.816–0.863; RF 0.837, 95% CI 0.813–0.861; LR 0.821, 95% CI 0.795–0.847) (C 365-day, XGBoost 0.816, 95% CI 0.786–0.832; RF 0.809, 95% CI 0.786–0.832; LR 0.795, 95% CI 0.771–0.819)

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us