An effective prediction model based on XGBoost for the 12-month recurrence of AF patients after RFA
Abstract Background Atrial fibrillation (AF) is a common heart rhythm disorder that can lead to complications such as stroke and heart failure. Radiofrequency ablation (RFA) is a procedure used to treat AF, but it is not always successful in maintaining a normal heart rhythm. This study aimed to con...
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | English |
| Veröffentlicht: |
BMC
2023-11-01
|
| Schriftenreihe: | BMC Cardiovascular Disorders |
| Schlagworte: | |
| Online Zugang: | https://doi.org/10.1186/s12872-023-03599-9 |
| _version_ | 1827724841944350720 |
|---|---|
| author | ShiKun Sun Li Wang Jia Lin YouFen Sun ChangSheng Ma |
| author_facet | ShiKun Sun Li Wang Jia Lin YouFen Sun ChangSheng Ma |
| author_sort | ShiKun Sun |
| collection | DOAJ |
| description | Abstract Background Atrial fibrillation (AF) is a common heart rhythm disorder that can lead to complications such as stroke and heart failure. Radiofrequency ablation (RFA) is a procedure used to treat AF, but it is not always successful in maintaining a normal heart rhythm. This study aimed to construct a clinical prediction model based on extreme gradient boosting (XGBoost) for AF recurrence 12 months after ablation. Methods The 27-dimensional data of 359 patients with AF undergoing RFA in the First Affiliated Hospital of Soochow University from October 2018 to November 2021 were retrospectively analysed. We adopted the logistic regression, support vector machine (SVM), random forest (RF) and XGBoost methods to conduct the experiment. To evaluate the performance of the prediction, we used the area under the receiver operating characteristic curve (AUC), the area under the precision-recall curve (AP), and calibration curves of both the training and testing sets. Finally, Shapley additive explanations (SHAP) were utilized to explain the significance of the variables. Results Of the 27-dimensional variables, ejection fraction (EF) of the left atrial appendage (LAA), N-terminal probrain natriuretic peptide (NT-proBNP), global peak longitudinal strain of the LAA (LAAGPLS), left atrial diameter (LAD), diabetes mellitus (DM) history, and female sex had a significant role in the predictive model. The experimental results demonstrated that XGBoost exhibited the best performance among these methods, and the accuracy, specificity, sensitivity, precision and F1 score (a measure of test accuracy) of XGBoost were 86.1%, 89.7%, 71.4%, 62.5% and 0.67, respectively. In addition, SHAP analysis also proved that the 6 parameters were decisive for the effect of the XGBoost-based prediction model. Conclusions We proposed an effective model based on XGBoost that can be used to predict the recurrence of AF patients after RFA. This prediction result can guide treatment decisions and help to optimize the management of AF. |
| first_indexed | 2024-03-10T22:20:13Z |
| format | Article |
| id | doaj.art-4736c491f3d54a84a093b78fe88fdf9b |
| institution | Directory Open Access Journal |
| issn | 1471-2261 |
| language | English |
| last_indexed | 2024-03-10T22:20:13Z |
| publishDate | 2023-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Cardiovascular Disorders |
| spelling | doaj.art-4736c491f3d54a84a093b78fe88fdf9b2023-11-19T12:18:46ZengBMCBMC Cardiovascular Disorders1471-22612023-11-0123111110.1186/s12872-023-03599-9An effective prediction model based on XGBoost for the 12-month recurrence of AF patients after RFAShiKun Sun0Li Wang1Jia Lin2YouFen Sun3ChangSheng Ma4The First Affiliated Hospital of Soochow UniversityThe First Affiliated Hospital of Soochow UniversityThe First Affiliated Hospital of Soochow UniversityThe Shengcheng Street Health CenterThe First Affiliated Hospital of Soochow UniversityAbstract Background Atrial fibrillation (AF) is a common heart rhythm disorder that can lead to complications such as stroke and heart failure. Radiofrequency ablation (RFA) is a procedure used to treat AF, but it is not always successful in maintaining a normal heart rhythm. This study aimed to construct a clinical prediction model based on extreme gradient boosting (XGBoost) for AF recurrence 12 months after ablation. Methods The 27-dimensional data of 359 patients with AF undergoing RFA in the First Affiliated Hospital of Soochow University from October 2018 to November 2021 were retrospectively analysed. We adopted the logistic regression, support vector machine (SVM), random forest (RF) and XGBoost methods to conduct the experiment. To evaluate the performance of the prediction, we used the area under the receiver operating characteristic curve (AUC), the area under the precision-recall curve (AP), and calibration curves of both the training and testing sets. Finally, Shapley additive explanations (SHAP) were utilized to explain the significance of the variables. Results Of the 27-dimensional variables, ejection fraction (EF) of the left atrial appendage (LAA), N-terminal probrain natriuretic peptide (NT-proBNP), global peak longitudinal strain of the LAA (LAAGPLS), left atrial diameter (LAD), diabetes mellitus (DM) history, and female sex had a significant role in the predictive model. The experimental results demonstrated that XGBoost exhibited the best performance among these methods, and the accuracy, specificity, sensitivity, precision and F1 score (a measure of test accuracy) of XGBoost were 86.1%, 89.7%, 71.4%, 62.5% and 0.67, respectively. In addition, SHAP analysis also proved that the 6 parameters were decisive for the effect of the XGBoost-based prediction model. Conclusions We proposed an effective model based on XGBoost that can be used to predict the recurrence of AF patients after RFA. This prediction result can guide treatment decisions and help to optimize the management of AF.https://doi.org/10.1186/s12872-023-03599-9Atrial fibrillationRadiofrequency ablationRecurrenceLeft atrial appendageXGBoost |
| spellingShingle | ShiKun Sun Li Wang Jia Lin YouFen Sun ChangSheng Ma An effective prediction model based on XGBoost for the 12-month recurrence of AF patients after RFA BMC Cardiovascular Disorders Atrial fibrillation Radiofrequency ablation Recurrence Left atrial appendage XGBoost |
| title | An effective prediction model based on XGBoost for the 12-month recurrence of AF patients after RFA |
| title_full | An effective prediction model based on XGBoost for the 12-month recurrence of AF patients after RFA |
| title_fullStr | An effective prediction model based on XGBoost for the 12-month recurrence of AF patients after RFA |
| title_full_unstemmed | An effective prediction model based on XGBoost for the 12-month recurrence of AF patients after RFA |
| title_short | An effective prediction model based on XGBoost for the 12-month recurrence of AF patients after RFA |
| title_sort | effective prediction model based on xgboost for the 12 month recurrence of af patients after rfa |
| topic | Atrial fibrillation Radiofrequency ablation Recurrence Left atrial appendage XGBoost |
| url | https://doi.org/10.1186/s12872-023-03599-9 |
| work_keys_str_mv | AT shikunsun aneffectivepredictionmodelbasedonxgboostforthe12monthrecurrenceofafpatientsafterrfa AT liwang aneffectivepredictionmodelbasedonxgboostforthe12monthrecurrenceofafpatientsafterrfa AT jialin aneffectivepredictionmodelbasedonxgboostforthe12monthrecurrenceofafpatientsafterrfa AT youfensun aneffectivepredictionmodelbasedonxgboostforthe12monthrecurrenceofafpatientsafterrfa AT changshengma aneffectivepredictionmodelbasedonxgboostforthe12monthrecurrenceofafpatientsafterrfa AT shikunsun effectivepredictionmodelbasedonxgboostforthe12monthrecurrenceofafpatientsafterrfa AT liwang effectivepredictionmodelbasedonxgboostforthe12monthrecurrenceofafpatientsafterrfa AT jialin effectivepredictionmodelbasedonxgboostforthe12monthrecurrenceofafpatientsafterrfa AT youfensun effectivepredictionmodelbasedonxgboostforthe12monthrecurrenceofafpatientsafterrfa AT changshengma effectivepredictionmodelbasedonxgboostforthe12monthrecurrenceofafpatientsafterrfa |