An explainable knowledge distillation method with XGBoost for ICU mortality prediction
Computers in Biology and Medicine(2022)
摘要
•Distilling knowledge from deep learning to improve predictive performance of XGBoost.•Model calibration for obtaining prediction reflecting the true posterior probabilities.•Insights about patients’ physiological conditions are obtained through SHAP.•Comprehensive experiments were conducted on the MIMIC-III dataset.
更多查看译文
关键词
Intensive care units,Mortality prediction,Knowledge distillation,Explainable machine learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要