Comparison of machine learning and nomogram to predict 30-day in-hospital mortality in patients with acute myocardial infarction combined with cardiogenic shock: a retrospective study based on the eICU-CRD and MIMIC-IV databases

Figures

• 

  Fig. 1.. Patient screening process

• 

  Fig. 2.. Recursive elimination of random forest features

• 

  Fig. 3.. LASSO regression screening characteristics. A Lasso coefficient profiles of the 49 clinical features. B The cross-validation curves of the Lasso regression analysis employ a ten-fold cross-validation approach, employing a minimum selection criterion to ascertain the optimal penalty coefficient λ.

• 

  Fig. 4.. Nomogram for predicting the risk of hospital mortality in AMI-CS patients

• 

  Fig. 5.. Dynamic Nomogram for Predicting Outcomes in AMI-CS Patients

• 

  Fig. 6.. Receiver Operating Characteristic (ROC) Curves for the Internal Test Set and External Validation Set. A ROC Curves of the eICU-CRD Internal Test Set to Assess the Model's Discriminative Ability. B ROC Curves of the MIMIC-IV External Validation Set to Assess the Model's Discriminative Ability

• 

  Fig. 7.. Calibration curves for internal test set and external validation set. A Calibration curves for the eICU-CRD internal test set; B Calibration curves for the MIMIC-IV external validation set

• 

  Fig. 8.. Decision Curve Analysis (DCA) and Clinical Impact Curve (CIC) for the Internal Test Set and External Validation Set. A DCA Curves of the eICU-CRD Internal Test Set. B CIC Curves of the eICU-CRD Internal Test Set. C DCA Curve of the MIMIC-IV External Validation Set. D CIC Curve of the MIMIC-IV External Validation Set