Harnessing Risk Assessment for Thrombosis and Bleeding to Optimize Anticoagulation Strategy in Nonvalvular Atrial Fibrillation

Abstract

Background

Oral anticoagulation (OAC) following catheter ablation (CA) of nonvalvular atrial fibrillation (NVAF) is essential for the prevention of thrombosis events. Inappropriate application of OACs does not benefit stroke prevention but may be associated with a higher risk of bleeding. Therefore, this study aims to develop clinical data-driven machine learning (ML) methods to predict the risk of thrombosis and bleeding to establish more precise anticoagulation strategies for patients with NVAF.

Methods

Patients with NVAF who underwent CA therapy were enrolled from Southwest Hospital from 2015 to 2023. This study compared eight ML algorithms to evaluate the predictive power for both thrombosis and bleeding. Model interpretations were recognized by feature importance and SHapley Additive exPlanations methods. With potential essential risk factors, simplified ML models were proposed to improve the feasibility of the tool.

Results

A total of 1,055 participants were recruited, including 105 patients with thrombosis and 252 patients with bleeding. The models based on XGBoost achieved the best performance with accuracies of 0.740 and 0.781 for thrombosis and bleeding, respectively. Age, BNP, and the duration of heparin are closely related to the high risk of thrombosis, whereas the anticoagulation strategy, BNP, and lipids play a crucial role in the occurrence of bleeding. The optimized models enrolling crucial risk factors, RF-T for thrombosis and Xw-B for bleeding, achieved the best recalls of 0.774 and 0.780, respectively.

Conclusion

The optimized models will have a great application potential in predicting thrombosis and bleeding among patients with NVAF and will form the basis for future score scales.

Keywords

nonvalvular atrial fibrillation - risk assessment - thrombosis-related adverse events - bleeding-related events - anticoagulation strategy

Data Availability Statement

Data will be made available on request.

Ethical Approval Statement

This research was approved by the Ethics Committee of the First Affiliated Hospital of Army Medical University [(B)KY2023076] prior to the commencement of this study, and informed consent was waived because of a retrospective observational study.

Authors' Contribution

Y.Z. contributed to conceptualization, methodology, formal analysis, visualization, writing—original draft, writing—review and editing. L.-Y.C. contributed to data curation, investigation, visualization, writing—review and editing. Y.-X.Z. contributed to data curation, visualization, writing—review and editing. D.Z. contributed to data curation, writing—review. Y.-F.H. contributed to data curation, writing—review. F.W. contributed to investigation, supervision, writing—review. Q.W. contributed to supervision, writing—review and editing, funding acquisition.

^* These authors contributed equally to this article.

Publication History

Received: 08 April 2024

Accepted: 04 August 2024

Accepted Manuscript online:
13 August 2024

Article published online:
19 September 2024

• References

• 1 Yang W-Y, Du X, Jiang C. et al. The safety of discontinuation of oral anticoagulation therapy after apparently successful atrial fibrillation ablation: a report from the Chinese Atrial Fibrillation Registry study. Europace 2020; 22 (01) 90-99
• 2 Friberg L, Tabrizi F, Englund A. Catheter ablation for atrial fibrillation is associated with lower incidence of stroke and death: data from Swedish health registries. Eur Heart J 2016; 37 (31) 2478-2487
• 3 Meyre PB, Blum S, Hennings E. et al. Bleeding and ischaemic events after first bleed in anticoagulated atrial fibrillation patients: risk and timing. Eur Heart J 2022; 43 (47) 4899-4908
• 4 Hylek EM, Held C, Alexander JH. et al. Major bleeding in patients with atrial fibrillation receiving apixaban or warfarin: the ARISTOTLE Trial (Apixaban for Reduction in Stroke and Other Thromboembolic Events in Atrial Fibrillation): predictors, characteristics, and clinical outcomes. J Am Coll Cardiol 2014; 63 (20) 2141-2147
• 5 Chew D, Piccini JP. Long-term oral anticoagulant after catheter ablation for atrial fibrillation. Europace 2021; 23 (08) 1157-1165
• 6 Mark DB, Anstrom KJ, Sheng S. et al; CABANA Investigators. Effect of catheter ablation vs medical therapy on quality of life among patients with atrial fibrillation: the CABANA randomized clinical trial. JAMA 2019; 321 (13) 1275-1285
• 7 Marrouche NF, Brachmann J, Andresen D. et al; CASTLE-AF Investigators. Catheter ablation for atrial fibrillation with heart failure. N Engl J Med 2018; 378 (05) 417-427
• 8 Hindricks G, Potpara T, Dagres N. et al; ESC Scientific Document Group. 2020 ESC Guidelines for the diagnosis and management of atrial fibrillation developed in collaboration with the European Association for Cardio-Thoracic Surgery (EACTS): the Task Force for the diagnosis and management of atrial fibrillation of the European Society of Cardiology (ESC) developed with the special contribution of the European Heart Rhythm Association (EHRA) of the ESC. Eur Heart J 2021; 42 (05) 373-498
• 9 Zhang Z, Zhu J, Wu M, Neidlin M, Wu WT, Wu P. Computational modeling of hemodynamics and risk of thrombosis in the left atrial appendage using patient-specific blood viscosity and boundary conditions at the mitral valve. Biomech Model Mechanobiol 2023; 22 (04) 1447-1457
• 10 Nagao T, Higo S, Suzuki H. et al. Prospective comparison of periprocedural coagulation markers among uninterrupted anticoagulants for atrial fibrillation ablation. Heart Rhythm 2020; 17 (03) 391-397
• 11 Akar JG, Jeske W, Wilber DJ. Acute onset human atrial fibrillation is associated with local cardiac platelet activation and endothelial dysfunction. J Am Coll Cardiol 2008; 51 (18) 1790-1793
• 12 Berg DD, Ruff CT, Jarolim P. et al. Performance of the ABC scores for assessing the risk of stroke or systemic embolism and bleeding in patients with atrial fibrillation in ENGAGE AF-TIMI 48. Circulation 2019; 139 (06) 760-771
• 13 Oyama K, Giugliano RP, Berg DD. et al. Serial assessment of biomarkers and the risk of stroke or systemic embolism and bleeding in patients with atrial fibrillation in the ENGAGE AF-TIMI 48 trial. Eur Heart J 2021; 42 (17) 1698-1706
• 14 Hijazi Z, Lindahl B, Oldgren J. et al. Repeated measurements of cardiac biomarkers in atrial fibrillation and validation of the ABC stroke score over time. J Am Heart Assoc 2017; 6 (06) e004851
• 15 Yu I, Song T-J, Kim BJ. et al. CHADS2, CHA2DS2-VASc, ATRIA, and Essen stroke risk scores in stroke with atrial fibrillation: a nationwide multicenter registry study. Medicine (Baltimore) 2021; 100 (03) e24000
• 16 Pisters R, Lane DA, Nieuwlaat R, de Vos CB, Crijns HJ, Lip GY. A novel user-friendly score (HAS-BLED) to assess 1-year risk of major bleeding in patients with atrial fibrillation: the Euro Heart Survey. Chest 2010; 138 (05) 1093-1100
• 17 Kosolwattana T, Liu C, Hu R, Han S, Chen H, Lin Y. A self-inspected adaptive SMOTE algorithm (SASMOTE) for highly imbalanced data classification in healthcare. BioData Min 2023; 16 (01) 15
• 18 Bi X-A, Xing Z, Zhou W, Li L, Xu L. Pathogeny detection for mild cognitive impairment via weighted evolutionary random forest with brain imaging and genetic data. IEEE J Biomed Health Inform 2022; 26 (07) 3068-3079
• 19 Zhang Y, Zhang X, Lane AN, Fan TW, Liu J. Inferring gene regulatory networks of metabolic enzymes using gradient boosted trees. IEEE J Biomed Health Inform 2020; 24 (05) 1528-1536
• 20 Natekin A, Knoll A. Gradient boosting machines, a tutorial. Front Neurorobot 2013; 7: 21
• 21 Bertsimas D, Mingardi L, Stellato B. Machine learning for real-time heart disease prediction. IEEE J Biomed Health Inform 2021; 25 (09) 3627-3637
• 22 LaValley MP. Logistic regression. Circulation 2008; 117 (18) 2395-2399
• 23 Zuo C, Qian J, Feng S. et al. Deep learning in optical metrology: a review. Light Sci Appl 2022; 11 (01) 39
• 24 Fillbrunn A, Dietz C, Pfeuffer J, Rahn R, Landrum GA, Berthold MR. KNIME for reproducible cross-domain analysis of life science data. J Biotechnol 2017; 261: 149-156
• 25 Ali S, Akhlaq F, Imran AS, Kastrati Z, Daudpota SM, Moosa M. The enlightening role of explainable artificial intelligence in medical & healthcare domains: a systematic literature review. Comput Biol Med 2023; 166: 107555
• 26 Lu J, Hutchens R, Hung J. et al. Performance of multilabel machine learning models and risk stratification schemas for predicting stroke and bleeding risk in patients with non-valvular atrial fibrillation. Comput Biol Med 2022; 150: 106126
• 27 Apostolakis S, Lane DA, Guo Y, Buller H, Lip GY. Performance of the HEMORR(2)HAGES, ATRIA, and HAS-BLED bleeding risk-prediction scores in patients with atrial fibrillation undergoing anticoagulation: the AMADEUS (evaluating the use of SR34006 compared to warfarin or acenocoumarol in patients with atrial fibrillation) study. J Am Coll Cardiol 2012; 60 (09) 861-867
• 28 Zhao Y, Cao L-Y, Zhao Y-X. et al. Medical record data-enabled machine learning can enhance prediction of left atrial appendage thrombosis in nonvalvular atrial fibrillation. Thromb Res 2023; 223: 174-183
• 29 Atehortúa A, Gkontra P, Camacho M. et al. Cardiometabolic risk estimation using exposome data and machine learning. Int J Med Inform 2023; 179: 105209
• 30 Shwartz-Ziv R, Armon A. Tabular data: deep learning is not all you need. Inf Fusion 2022; 81: 84-90
• 31 Prifti E, Fall A, Davogustto G. et al. Deep learning analysis of electrocardiogram for risk prediction of drug-induced arrhythmias and diagnosis of long QT syndrome. Eur Heart J 2021; 42 (38) 3948-3961
• 32 Sideris S, Archontakis S, Latsios G. et al. Biomarkers associated with bleeding risk in the setting of atrial fibrillation. Curr Med Chem 2019; 26 (05) 824-836
• 33 Shechter M, Merz CN, Paul-Labrador MJ, Kaul S. Blood glucose and platelet-dependent thrombosis in patients with coronary artery disease. J Am Coll Cardiol 2000; 35 (02) 300-307
• 34 Hart R, Veenstra DL, Boudreau DM, Roth JA. Impact of body mass index and genetics on warfarin major bleeding outcomes in a community setting. Am J Med 2017; 130 (02) 222-228