Skip to main content
Fig. 7 | BMC Medical Informatics and Decision Making

Fig. 7

From: A machine learning-based model for predicting paroxysmal and persistent atrial fibrillation based on EHR

Fig. 7

Model prediction performance by AUC and interpretation by SHAP method in different gender and age group. Figure 7 shows the AUC results for different gender and age subgroups and the interpretation of the model obtained using the SHAP method. Figure 7-a and 7-b series represent the AUC and SHAP value rankings, respectively. 1, 2, 3, and 4 are male younger than 60 years old, male older than or equal to 60 years old, female younger than 60 years old, and female older than or equal to 60 years old, respectively

Back to article page