Cargando…

Integrated Machine Learning Decision Tree Model for Risk Evaluation in Patients with Non-Valvular Atrial Fibrillation When Taking Different Doses of Dabigatran

The new generation of nonvitamin K antagonists are broadly applied for stroke prevention due to their notable efficacy and safety. Our study aimed to develop a suggestive utilization of dabigatran through an integrated machine learning (ML) decision-tree model. Participants taking different doses of...

Descripción completa

Detalles Bibliográficos
Autores principales: Huang, Yung-Chuan, Cheng, Yu-Chen, Jhou, Mao-Jhen, Chen, Mingchih, Lu, Chi-Jie
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9915180/
https://www.ncbi.nlm.nih.gov/pubmed/36767726
http://dx.doi.org/10.3390/ijerph20032359
_version_ 1784885841544347648
author Huang, Yung-Chuan
Cheng, Yu-Chen
Jhou, Mao-Jhen
Chen, Mingchih
Lu, Chi-Jie
author_facet Huang, Yung-Chuan
Cheng, Yu-Chen
Jhou, Mao-Jhen
Chen, Mingchih
Lu, Chi-Jie
author_sort Huang, Yung-Chuan
collection PubMed
description The new generation of nonvitamin K antagonists are broadly applied for stroke prevention due to their notable efficacy and safety. Our study aimed to develop a suggestive utilization of dabigatran through an integrated machine learning (ML) decision-tree model. Participants taking different doses of dabigatran in the Randomized Evaluation of Long-Term Anticoagulant Therapy trial were included in our analysis and defined as the 110 mg and 150 mg groups. The proposed scheme integrated ML methods, namely naive Bayes, random forest (RF), classification and regression tree (CART), and extreme gradient boosting (XGBoost), which were used to identify the essential variables for predicting vascular events in the 110 mg group and bleeding in the 150 mg group. RF (0.764 for 110 mg; 0.747 for 150 mg) and XGBoost (0.708 for 110 mg; 0.761 for 150 mg) had better area under the receiver operating characteristic curve (AUC) values than logistic regression (benchmark model; 0.683 for 110 mg; 0.739 for 150 mg). We then selected the top ten important variables as internal nodes of the CART decision tree. The two best CART models with ten important variables output tree-shaped rules for predicting vascular events in the 110 mg group and bleeding in the 150 mg group. Our model can be used to provide more visualized and interpretable suggestive rules to clinicians managing NVAF patients who are taking dabigatran.
format Online
Article
Text
id pubmed-9915180
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-99151802023-02-11 Integrated Machine Learning Decision Tree Model for Risk Evaluation in Patients with Non-Valvular Atrial Fibrillation When Taking Different Doses of Dabigatran Huang, Yung-Chuan Cheng, Yu-Chen Jhou, Mao-Jhen Chen, Mingchih Lu, Chi-Jie Int J Environ Res Public Health Article The new generation of nonvitamin K antagonists are broadly applied for stroke prevention due to their notable efficacy and safety. Our study aimed to develop a suggestive utilization of dabigatran through an integrated machine learning (ML) decision-tree model. Participants taking different doses of dabigatran in the Randomized Evaluation of Long-Term Anticoagulant Therapy trial were included in our analysis and defined as the 110 mg and 150 mg groups. The proposed scheme integrated ML methods, namely naive Bayes, random forest (RF), classification and regression tree (CART), and extreme gradient boosting (XGBoost), which were used to identify the essential variables for predicting vascular events in the 110 mg group and bleeding in the 150 mg group. RF (0.764 for 110 mg; 0.747 for 150 mg) and XGBoost (0.708 for 110 mg; 0.761 for 150 mg) had better area under the receiver operating characteristic curve (AUC) values than logistic regression (benchmark model; 0.683 for 110 mg; 0.739 for 150 mg). We then selected the top ten important variables as internal nodes of the CART decision tree. The two best CART models with ten important variables output tree-shaped rules for predicting vascular events in the 110 mg group and bleeding in the 150 mg group. Our model can be used to provide more visualized and interpretable suggestive rules to clinicians managing NVAF patients who are taking dabigatran. MDPI 2023-01-29 /pmc/articles/PMC9915180/ /pubmed/36767726 http://dx.doi.org/10.3390/ijerph20032359 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Huang, Yung-Chuan
Cheng, Yu-Chen
Jhou, Mao-Jhen
Chen, Mingchih
Lu, Chi-Jie
Integrated Machine Learning Decision Tree Model for Risk Evaluation in Patients with Non-Valvular Atrial Fibrillation When Taking Different Doses of Dabigatran
title Integrated Machine Learning Decision Tree Model for Risk Evaluation in Patients with Non-Valvular Atrial Fibrillation When Taking Different Doses of Dabigatran
title_full Integrated Machine Learning Decision Tree Model for Risk Evaluation in Patients with Non-Valvular Atrial Fibrillation When Taking Different Doses of Dabigatran
title_fullStr Integrated Machine Learning Decision Tree Model for Risk Evaluation in Patients with Non-Valvular Atrial Fibrillation When Taking Different Doses of Dabigatran
title_full_unstemmed Integrated Machine Learning Decision Tree Model for Risk Evaluation in Patients with Non-Valvular Atrial Fibrillation When Taking Different Doses of Dabigatran
title_short Integrated Machine Learning Decision Tree Model for Risk Evaluation in Patients with Non-Valvular Atrial Fibrillation When Taking Different Doses of Dabigatran
title_sort integrated machine learning decision tree model for risk evaluation in patients with non-valvular atrial fibrillation when taking different doses of dabigatran
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9915180/
https://www.ncbi.nlm.nih.gov/pubmed/36767726
http://dx.doi.org/10.3390/ijerph20032359
work_keys_str_mv AT huangyungchuan integratedmachinelearningdecisiontreemodelforriskevaluationinpatientswithnonvalvularatrialfibrillationwhentakingdifferentdosesofdabigatran
AT chengyuchen integratedmachinelearningdecisiontreemodelforriskevaluationinpatientswithnonvalvularatrialfibrillationwhentakingdifferentdosesofdabigatran
AT jhoumaojhen integratedmachinelearningdecisiontreemodelforriskevaluationinpatientswithnonvalvularatrialfibrillationwhentakingdifferentdosesofdabigatran
AT chenmingchih integratedmachinelearningdecisiontreemodelforriskevaluationinpatientswithnonvalvularatrialfibrillationwhentakingdifferentdosesofdabigatran
AT luchijie integratedmachinelearningdecisiontreemodelforriskevaluationinpatientswithnonvalvularatrialfibrillationwhentakingdifferentdosesofdabigatran