Your privacy, your choice

We use essential cookies to make sure the site can function. We also use optional cookies for advertising, personalisation of content, usage analysis, and social media.

By accepting optional cookies, you consent to the processing of your personal data - including transfers to third parties. Some third parties are outside of the European Economic Area, with varying standards of data protection.

See our privacy policy for more information on the use of your personal data.

for further information and to change your choices.
Skip to main content
Fig. 2 | BMC Medical Informatics and Decision Making

Fig. 2

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

Fig. 2

Selection process of variables. Figure 2 shows the process of variable screening. Figure 2-a and -b correspond to the results of variable screening using LASSO and GradientBoost RFE methods, respectively. The AUC of the model output changes with the change of the model input variables. From Fig. 2-c, it can be found that the number of variables when LASSO and GradientBoost RFE achieve the best AUC is 32 and 12 respectively, and merging them can get a common 10 variables. Figure 2-d illustrates the spearman correlation between the 10 variables

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us