Fig 1.
A. Screening Process for MIMIC-IV. B. Screening Process for MIMIC-III.
Table 1.
Baseline characteristics of the cohort from MIMIC-IV.
Fig 2.
Feature coefficients.
Fig 3.
ROC curves of the predictive model.
A. Internal validation set. B. External validation set.
Table 2.
Compared performance evaluation of 8 machine learning classification models in predicting 28-day mortality rate in the internal validation set.
Fig 4.
DCA curves of the top three best-performing models.
Fig 5.
ROC curves of the random forest and traditional disease severity scores.
A. Internal validation set. B. External validation set.
Table 3.
Compared performance evaluation of random forest and traditional disease severity scores in predicting 28-day mortality rate in the internal validation set.
Table 4.
Compared performance of the random forest model before and after hyperparameter tuning.
Fig 6.
A. SHAP values showing the influence of different features on the output of RF Model. B. Mean absolute SHAP values for each clinical feature.
Fig 7.
SHAP dependency plot of the top 5 influential clinical features on model outcomes.
A. Urine output; B. CCI; C. GCS_min; D. BUN; E. Admission_age.