Important Risk Factors in Patients with Nonvalvular Atrial Fibrillation Taking Dabigatran Using Integrated Machine Learning Scheme—A Post Hoc Analysis
Our study aims to develop an effective integrated machine learning (ML) scheme to predict vascular events and bleeding in patients with nonvalvular atrial fibrillation taking dabigatran and identify important risk factors. This study is a post-hoc analysis from the Randomized Evaluation of Long-Term...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Journal of Personalized Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4426/12/5/756 |
| _version_ | 1797498610509676544 |
|---|---|
| author | Yung-Chuan Huang Yu-Chen Cheng Mao-Jhen Jhou Mingchih Chen Chi-Jie Lu |
| author_facet | Yung-Chuan Huang Yu-Chen Cheng Mao-Jhen Jhou Mingchih Chen Chi-Jie Lu |
| author_sort | Yung-Chuan Huang |
| collection | DOAJ |
| description | Our study aims to develop an effective integrated machine learning (ML) scheme to predict vascular events and bleeding in patients with nonvalvular atrial fibrillation taking dabigatran and identify important risk factors. This study is a post-hoc analysis from the Randomized Evaluation of Long-Term Anticoagulant Therapy trial database. One traditional prediction method, logistic regression (LGR), and four ML techniques—naive Bayes, random forest (RF), classification and regression tree, and extreme gradient boosting (XGBoost)—were combined to construct our scheme. Area under the receiver operating characteristic curve (AUC) of RF (0.780) and XGBoost (0.717) was higher than that of LGR (0.674) in predicting vascular events. In predicting bleeding, AUC of RF (0.684) and XGBoost (0.618) showed higher values than those generated by LGR (0.605). Our integrated ML feature selection scheme based on the two convincing prediction techniques identified age, history of congestive heart failure and myocardial infarction, smoking, kidney function, and body mass index as major variables of vascular events; age, kidney function, smoking, bleeding history, concomitant use of specific drugs, and dabigatran dosage as major variables of bleeding. ML is an effective data analysis algorithm for solving complex medical data. Our results may provide preliminary direction for precision medicine. |
| first_indexed | 2024-03-10T03:35:48Z |
| format | Article |
| id | doaj.art-851aaa8033a14ff08d2dc5d2bc0a6c07 |
| institution | Directory Open Access Journal |
| issn | 2075-4426 |
| language | English |
| last_indexed | 2024-03-10T03:35:48Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Personalized Medicine |
| spelling | doaj.art-851aaa8033a14ff08d2dc5d2bc0a6c072023-11-23T11:44:14ZengMDPI AGJournal of Personalized Medicine2075-44262022-05-0112575610.3390/jpm12050756Important Risk Factors in Patients with Nonvalvular Atrial Fibrillation Taking Dabigatran Using Integrated Machine Learning Scheme—A Post Hoc AnalysisYung-Chuan Huang0Yu-Chen Cheng1Mao-Jhen Jhou2Mingchih Chen3Chi-Jie Lu4Graduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City 242062, TaiwanDepartment of Neurology, Fu Jen Catholic University Hospital, Fu Jen Catholic University, New Taipei City 24352, TaiwanGraduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City 242062, TaiwanGraduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City 242062, TaiwanGraduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City 242062, TaiwanOur study aims to develop an effective integrated machine learning (ML) scheme to predict vascular events and bleeding in patients with nonvalvular atrial fibrillation taking dabigatran and identify important risk factors. This study is a post-hoc analysis from the Randomized Evaluation of Long-Term Anticoagulant Therapy trial database. One traditional prediction method, logistic regression (LGR), and four ML techniques—naive Bayes, random forest (RF), classification and regression tree, and extreme gradient boosting (XGBoost)—were combined to construct our scheme. Area under the receiver operating characteristic curve (AUC) of RF (0.780) and XGBoost (0.717) was higher than that of LGR (0.674) in predicting vascular events. In predicting bleeding, AUC of RF (0.684) and XGBoost (0.618) showed higher values than those generated by LGR (0.605). Our integrated ML feature selection scheme based on the two convincing prediction techniques identified age, history of congestive heart failure and myocardial infarction, smoking, kidney function, and body mass index as major variables of vascular events; age, kidney function, smoking, bleeding history, concomitant use of specific drugs, and dabigatran dosage as major variables of bleeding. ML is an effective data analysis algorithm for solving complex medical data. Our results may provide preliminary direction for precision medicine.https://www.mdpi.com/2075-4426/12/5/756arrhythmiacardioembolic strokenon-vitamin K antagonist oral anticoagulantsdabigatranmachine learning |
| spellingShingle | Yung-Chuan Huang Yu-Chen Cheng Mao-Jhen Jhou Mingchih Chen Chi-Jie Lu Important Risk Factors in Patients with Nonvalvular Atrial Fibrillation Taking Dabigatran Using Integrated Machine Learning Scheme—A Post Hoc Analysis Journal of Personalized Medicine arrhythmia cardioembolic stroke non-vitamin K antagonist oral anticoagulants dabigatran machine learning |
| title | Important Risk Factors in Patients with Nonvalvular Atrial Fibrillation Taking Dabigatran Using Integrated Machine Learning Scheme—A Post Hoc Analysis |
| title_full | Important Risk Factors in Patients with Nonvalvular Atrial Fibrillation Taking Dabigatran Using Integrated Machine Learning Scheme—A Post Hoc Analysis |
| title_fullStr | Important Risk Factors in Patients with Nonvalvular Atrial Fibrillation Taking Dabigatran Using Integrated Machine Learning Scheme—A Post Hoc Analysis |
| title_full_unstemmed | Important Risk Factors in Patients with Nonvalvular Atrial Fibrillation Taking Dabigatran Using Integrated Machine Learning Scheme—A Post Hoc Analysis |
| title_short | Important Risk Factors in Patients with Nonvalvular Atrial Fibrillation Taking Dabigatran Using Integrated Machine Learning Scheme—A Post Hoc Analysis |
| title_sort | important risk factors in patients with nonvalvular atrial fibrillation taking dabigatran using integrated machine learning scheme a post hoc analysis |
| topic | arrhythmia cardioembolic stroke non-vitamin K antagonist oral anticoagulants dabigatran machine learning |
| url | https://www.mdpi.com/2075-4426/12/5/756 |
| work_keys_str_mv | AT yungchuanhuang importantriskfactorsinpatientswithnonvalvularatrialfibrillationtakingdabigatranusingintegratedmachinelearningschemeaposthocanalysis AT yuchencheng importantriskfactorsinpatientswithnonvalvularatrialfibrillationtakingdabigatranusingintegratedmachinelearningschemeaposthocanalysis AT maojhenjhou importantriskfactorsinpatientswithnonvalvularatrialfibrillationtakingdabigatranusingintegratedmachinelearningschemeaposthocanalysis AT mingchihchen importantriskfactorsinpatientswithnonvalvularatrialfibrillationtakingdabigatranusingintegratedmachinelearningschemeaposthocanalysis AT chijielu importantriskfactorsinpatientswithnonvalvularatrialfibrillationtakingdabigatranusingintegratedmachinelearningschemeaposthocanalysis |