Machine learning models on a novel Romanian EHR dataset of 12,286 sepsis hospitalizations achieve AUC 0.983 for death versus recovery prediction and identify eosinopenia as a top predictor via SHAP.
Predicting sepsis in-hospital mortality with machine learning: a multi-center study using clinical and inflammatory biomarkers.European Journal of Medical Research
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Explainable Machine Learning for Sepsis Outcome Prediction Using a Novel Romanian Electronic Health Record Dataset
Machine learning models on a novel Romanian EHR dataset of 12,286 sepsis hospitalizations achieve AUC 0.983 for death versus recovery prediction and identify eosinopenia as a top predictor via SHAP.