Figures & data
Table 1 Simplified Set and Full Set of Features
Table 2 Basic Characteristics of Continuous Numerical Variables
Table 3 Basic Characteristics of Categorical Variables
Table 4 Performance Comparison of the Traditional and Optimized ML Models Using the Full Set
Figure 1 ROC analysis results of models trained without RUS using the full set.
![Figure 1 ROC analysis results of models trained without RUS using the full set.](/cms/asset/853079df-37d9-4b1d-b3ad-0c8e25a6a463/dtcr_a_12181124_f0001_c.jpg)
Figure 2 ROC analysis results of models trained with RUS using the full set.
![Figure 2 ROC analysis results of models trained with RUS using the full set.](/cms/asset/91cbb381-cac8-46a6-9222-336718eac58b/dtcr_a_12181124_f0002_c.jpg)
Figure 3 The confusion matrix of the SVM trained with RUS using the full set.
![Figure 3 The confusion matrix of the SVM trained with RUS using the full set.](/cms/asset/b7186203-33dd-43f9-95a6-2e581683f09e/dtcr_a_12181124_f0003_c.jpg)
Figure 4 The confusion matrix of the SVM trained without RUS using the full set.
![Figure 4 The confusion matrix of the SVM trained without RUS using the full set.](/cms/asset/29d2f16d-4625-403d-ad87-a0963d42455c/dtcr_a_12181124_f0004_c.jpg)
Table 5 Performance Comparison of the Traditional and Optimized ML Models Using the Simplified Set
Figure 5 The confusion matrix of the SVM trained with RUS using the simplified set.
![Figure 5 The confusion matrix of the SVM trained with RUS using the simplified set.](/cms/asset/d75fd5bd-70c4-4c94-b023-dcadb4d749f4/dtcr_a_12181124_f0005_c.jpg)
Figure 6 The feature importance scores for predicting the in-hospital mortality provided by the RF.
![Figure 6 The feature importance scores for predicting the in-hospital mortality provided by the RF.](/cms/asset/0bc06c33-478b-44a6-8280-5e8b536abca3/dtcr_a_12181124_f0006_c.jpg)
Table 6 Best Predictive Performance Results of the Models Developed by Other Articles