Open Access

P1064<br />Using Data Mining to Predict Bleeding Events caused by Novel Oral Anticoagulants

logo

Date: 18 June 2020
Journal: EP Europace Journal , Volume 22 , Issue Supplement_1
Authors: W. Chiou , M. Hsieh , H. Chuang , C. Huang , J. Chuang , P. Lin , Y. Lee

ESC Journals

AbstractBackground

Novel oral anticoagulants (NOAC) is important in preventing thromboembolism in atrial fibrillation (AF) patients. Bleeding risk was evaluated by HAS-BLED score traditionally. Data mining is a relatively new discipline that has sprung up at the confluence of several other disciplines, driven primarily by the growth of large databases. 

Purpose

This study aimed to find a useful predictive model by data mining to assess the risk of rivaroxaban, an antithrombotic drug that causes bleeding in AF patients. The seven parameters of the HAS-BLED score were used to predict the effect of rivaroxaban on bleeding tendency in AF patients and may provide clinicians with appropriate treatments to avoid complications from bleeding events and reduce the incidence of health damage.

Methods

Through conducting a multicenter retrospective study, we identified patients with AF who were treated with rivaroxaban for more than 1 month between December 1, 2011 and November 30, 2016. After preprocessing, the established data were used for training and testing of data mining models. This study evaluated four models, including association rules, neural networks, Bayesian classification, and decision trees.

Result

Of the 872 enrolled cases, 432 were in any of the bleeding groups and 432 were in the non-bleeding randomized control group. After comparing the overall classification accuracy, omission error and over-prediction error, the decision tree proved to be the most accurate model for bleeding prediction. The overall classification accuracy is 77%, the omission error is 15%, the over-prediction error is 21.9%, and the AUC score is 0.84. The results show that the model has good discriminative ability and visibility of decision rules.

Conclusion

Among several data mining models, decision tree proved to be the most accurate model for bleeding prediction. The conclusion of this study can be used as a reference for supporting decision making before anticoagulation treatment and suggest future research to compare efficacy of bleeding prediction between HAS-BLED score and decision tree.

Data mining comparison

ModelOmission errorCommission errorOverall accuracyAUC scoreRanking
Decision tree15.0%21.90%77.00%0.841
Association rules16.8%27.20%76.50%0.812
Neural networks12.0%26.40%78.20%0.833
Bayesian classification16.1%27.50%76.50%0.834

About the contributors

W R Chiou

Role: Author

M C Hsieh

Role: Author

H N Chuang

Role: Author