Skip to main content
Fig. 3 | Critical Care

Fig. 3

From: Interpretable machine learning models for predicting venous thromboembolism in the intensive care unit: an analysis based on data from 207 centers

Fig. 3

Feature importance derived from random forest model. This figure is the result of the DALEX package. The X-axis represents the loss in AUC calculated after randomly permuting the feature compared to the original AUC. The greater this loss, the higher the model's importance of this feature. Abbreviations: PTT, partial thromboplastin time; AST, aspartate transaminase; PT, prothrombin time; INR, international standard ratio; BMI, body mass index; ALT, alanine aminotransferase; WBC, white blood cell; CVC, central venous catheter

Back to article page

Critical Care

ISSN: 1364-8535