A random forest machine learning model using pre-operative variables predicted the need for a permanent pacemaker after TAVR with an ROC of 0.63 and overall accuracy of 0.78 on the test set.
Observational (n=513)
No
Can a random forest machine learning model using pre-operative variables predict the need for a permanent pacemaker device following TAVR?
A random forest machine learning model using pre-operative variables demonstrated modest discriminatory ability (ROC 0.63 on test set) in predicting the need for a permanent pacemaker after TAVR.
Introduction: TAVR is approved for use for a range of patients with aortic stenosis. The need for a permanent pacemaker device (PPD) after TAVR varies, but can range from 2 to 51%. Risk factors for requiring PPD after TAVR appear to include being male and having baseline conduction disturbances. Being able to predict who may require PPD could identify at risk patients early and may confer cost savings. Given the advent of machine learning classifier techniques, random forests may aid in better predicting need for PPD after TAVR by using pre-operative variables. Hypothesis: Random Forests offer discriminatory ability in predicting the need for PPD after TAVR using primarily pre-operative variables. Methods: Pre-operative data from a single institution were collected patients undergoing TAVR without a history of PPD between January 2016 and December 2019. EKG data was obtained including underlying rhythm, QRS duration and any underlying conduction abnormality. Other variables included anti-arrhythmic data, comorbidities, and eGFR. Data was imported into Python and a stratified 5 fold cross validation with SMOTE oversampling running at every fold to avoid overfitting was run on the training set. The model that optimized the receiver under the operator curve was exported and applied to a test data set. Precision and recall were calculated to assess classification. Results: A total of 513 patients were identified with nearly 9% eventually requiring PPD. A total of 40 predictor variables were utilized in the modeling. A stratified split of the data resulted in a training set of 384 patients and a test set of 129 patients. A total of 500 trees were used on the training set. The final optimized model had an ROC of 0.71 with the following parameters: gini criterion, max depth of 4, and logarithm max features . When applied to the test set, the model had an ROC of 0.63. Overall accuracy was 0.78, with a precision and recall for no PPD after TAVR being 0.94 and 0.81 and a precision and recall for PPD after TAVR of 0.18 and 0.45. Conclusions: Our results show that machine learning techniques, specifically random forests have discriminatory ability in predicting PPD after TAVR. More tuning of the models are required to achieve better discrimination.
Sheikh et al. (Thu,) conducted a observational in Aortic stenosis undergoing TAVR (n=513). Random forest machine learning model was evaluated on Need for permanent pacemaker device (PPD) after TAVR. A random forest machine learning model using pre-operative variables predicted the need for a permanent pacemaker after TAVR with an ROC of 0.63 and overall accuracy of 0.78 on the test set.