Prediction of Atrial Fibrillation Recurrence after Thoracoscopic Surgical Ablation Using Machine Learning Techniques
Thoracoscopic surgical ablation (SA) for atrial fibrillation (AF) has shown to be an effective treatment to restore sinus rhythm in patients with advanced AF. Identifying patients who will not benefit from this procedure would be valuable to improve personalized AF therapy. Machine learning (ML) tec...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/10/1787 |
| _version_ | 1797514866083233792 |
|---|---|
| author | Sarah W. E. Baalman Ricardo R. Lopes Lucas A. Ramos Jolien Neefs Antoine H. G. Driessen WimJan P. van Boven Bas A. J. M. de Mol Henk A. Marquering Joris R. de Groot |
| author_facet | Sarah W. E. Baalman Ricardo R. Lopes Lucas A. Ramos Jolien Neefs Antoine H. G. Driessen WimJan P. van Boven Bas A. J. M. de Mol Henk A. Marquering Joris R. de Groot |
| author_sort | Sarah W. E. Baalman |
| collection | DOAJ |
| description | Thoracoscopic surgical ablation (SA) for atrial fibrillation (AF) has shown to be an effective treatment to restore sinus rhythm in patients with advanced AF. Identifying patients who will not benefit from this procedure would be valuable to improve personalized AF therapy. Machine learning (ML) techniques may assist in the improvement of clinical prediction models for patient selection. The aim of this study is to investigate how available baseline characteristics predict AF recurrence after SA using ML techniques. One-hundred-sixty clinical baseline variables were collected from 446 AF patients undergoing SA in our tertiary referral center. Multiple ML models were trained on five outcome measurements, including either all or a number of key variables selected by using the least absolute shrinkage and selection operator (LASSO). There was no difference in model performance between different ML techniques or outcome measurements. Variable selection significantly improved model performance (AUC: 0.73, 95% CI: 0.68–0.77). Subgroup analysis showed a higher model performance in younger patients (<55 years, AUC: 0.82 vs. >55 years, AUC 0.66). Recurrences of AF after SA can be predicted best when using a selection of baseline characteristics, particularly in young patients. |
| first_indexed | 2024-03-10T06:37:36Z |
| format | Article |
| id | doaj.art-78b66d58f6b04a639a0049fb41c832ec |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T06:37:36Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-78b66d58f6b04a639a0049fb41c832ec2023-11-22T17:56:45ZengMDPI AGDiagnostics2075-44182021-09-011110178710.3390/diagnostics11101787Prediction of Atrial Fibrillation Recurrence after Thoracoscopic Surgical Ablation Using Machine Learning TechniquesSarah W. E. Baalman0Ricardo R. Lopes1Lucas A. Ramos2Jolien Neefs3Antoine H. G. Driessen4WimJan P. van Boven5Bas A. J. M. de Mol6Henk A. Marquering7Joris R. de Groot8Heart Centre, Amsterdam UMC, University of Amsterdam, 1105 AZ Amsterdam, The NetherlandsDepartment of Biomedical Engineering and Physics, Amsterdam UMC, University of Amsterdam, 1105 AZ Amsterdam, The NetherlandsDepartment of Biomedical Engineering and Physics, Amsterdam UMC, University of Amsterdam, 1105 AZ Amsterdam, The NetherlandsHeart Centre, Amsterdam UMC, University of Amsterdam, 1105 AZ Amsterdam, The NetherlandsHeart Centre, Amsterdam UMC, University of Amsterdam, 1105 AZ Amsterdam, The NetherlandsHeart Centre, Amsterdam UMC, University of Amsterdam, 1105 AZ Amsterdam, The NetherlandsHeart Centre, Amsterdam UMC, University of Amsterdam, 1105 AZ Amsterdam, The NetherlandsDepartment of Biomedical Engineering and Physics, Amsterdam UMC, University of Amsterdam, 1105 AZ Amsterdam, The NetherlandsHeart Centre, Amsterdam UMC, University of Amsterdam, 1105 AZ Amsterdam, The NetherlandsThoracoscopic surgical ablation (SA) for atrial fibrillation (AF) has shown to be an effective treatment to restore sinus rhythm in patients with advanced AF. Identifying patients who will not benefit from this procedure would be valuable to improve personalized AF therapy. Machine learning (ML) techniques may assist in the improvement of clinical prediction models for patient selection. The aim of this study is to investigate how available baseline characteristics predict AF recurrence after SA using ML techniques. One-hundred-sixty clinical baseline variables were collected from 446 AF patients undergoing SA in our tertiary referral center. Multiple ML models were trained on five outcome measurements, including either all or a number of key variables selected by using the least absolute shrinkage and selection operator (LASSO). There was no difference in model performance between different ML techniques or outcome measurements. Variable selection significantly improved model performance (AUC: 0.73, 95% CI: 0.68–0.77). Subgroup analysis showed a higher model performance in younger patients (<55 years, AUC: 0.82 vs. >55 years, AUC 0.66). Recurrences of AF after SA can be predicted best when using a selection of baseline characteristics, particularly in young patients.https://www.mdpi.com/2075-4418/11/10/1787atrial fibrillationsurgical ablationmachine learning |
| spellingShingle | Sarah W. E. Baalman Ricardo R. Lopes Lucas A. Ramos Jolien Neefs Antoine H. G. Driessen WimJan P. van Boven Bas A. J. M. de Mol Henk A. Marquering Joris R. de Groot Prediction of Atrial Fibrillation Recurrence after Thoracoscopic Surgical Ablation Using Machine Learning Techniques Diagnostics atrial fibrillation surgical ablation machine learning |
| title | Prediction of Atrial Fibrillation Recurrence after Thoracoscopic Surgical Ablation Using Machine Learning Techniques |
| title_full | Prediction of Atrial Fibrillation Recurrence after Thoracoscopic Surgical Ablation Using Machine Learning Techniques |
| title_fullStr | Prediction of Atrial Fibrillation Recurrence after Thoracoscopic Surgical Ablation Using Machine Learning Techniques |
| title_full_unstemmed | Prediction of Atrial Fibrillation Recurrence after Thoracoscopic Surgical Ablation Using Machine Learning Techniques |
| title_short | Prediction of Atrial Fibrillation Recurrence after Thoracoscopic Surgical Ablation Using Machine Learning Techniques |
| title_sort | prediction of atrial fibrillation recurrence after thoracoscopic surgical ablation using machine learning techniques |
| topic | atrial fibrillation surgical ablation machine learning |
| url | https://www.mdpi.com/2075-4418/11/10/1787 |
| work_keys_str_mv | AT sarahwebaalman predictionofatrialfibrillationrecurrenceafterthoracoscopicsurgicalablationusingmachinelearningtechniques AT ricardorlopes predictionofatrialfibrillationrecurrenceafterthoracoscopicsurgicalablationusingmachinelearningtechniques AT lucasaramos predictionofatrialfibrillationrecurrenceafterthoracoscopicsurgicalablationusingmachinelearningtechniques AT jolienneefs predictionofatrialfibrillationrecurrenceafterthoracoscopicsurgicalablationusingmachinelearningtechniques AT antoinehgdriessen predictionofatrialfibrillationrecurrenceafterthoracoscopicsurgicalablationusingmachinelearningtechniques AT wimjanpvanboven predictionofatrialfibrillationrecurrenceafterthoracoscopicsurgicalablationusingmachinelearningtechniques AT basajmdemol predictionofatrialfibrillationrecurrenceafterthoracoscopicsurgicalablationusingmachinelearningtechniques AT henkamarquering predictionofatrialfibrillationrecurrenceafterthoracoscopicsurgicalablationusingmachinelearningtechniques AT jorisrdegroot predictionofatrialfibrillationrecurrenceafterthoracoscopicsurgicalablationusingmachinelearningtechniques |