Download PDF
CC BY-NC-ND 4.0 · Thromb Haemost 2025; 125(05): 492-504
DOI: 10.1055/a-2385-1452
Stroke, Systemic or Venous Thromboembolism

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

Yue Zhao‡   *
1   Department of Pharmacy, The First Affiliated Hospital of Army Medical University (Third Military Medical University), Chongqing, P. R. China
,
Li-Ya Cao‡   *
1   Department of Pharmacy, The First Affiliated Hospital of Army Medical University (Third Military Medical University), Chongqing, P. R. China
,
Ying-Xin Zhao‡   *
2   Department of Pharmacy, Army Medical Center, Army Medical University (Third Military Medical University), Chongqing, P. R. China
,
Di Zhao
1   Department of Pharmacy, The First Affiliated Hospital of Army Medical University (Third Military Medical University), Chongqing, P. R. China
,
Yi-Fan Huang
3   Medical Big Data and Artificial Intelligence Center, The First Affiliated Hospital of Army Medical University (Third Military Medical University), Chongqing, PR China
,
Fei Wang
3   Medical Big Data and Artificial Intelligence Center, The First Affiliated Hospital of Army Medical University (Third Military Medical University), Chongqing, PR China
,
Qian Wang
1   Department of Pharmacy, The First Affiliated Hospital of Army Medical University (Third Military Medical University), Chongqing, P. R. China
› Author Affiliations Funding This work was funded by the Chongqing municipal Education Commission Science and Technology Research Program (KJZD-M202212801) and Chongqing Clinical Pharmacy Key Specialties Construction Project (51561Z23772).
› Further Information
Also available at
   Permissions and Reprints


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.


Supplementary Material



Publication History

Received: 08 April 2024

Accepted: 04 August 2024

Accepted Manuscript online:
13 August 2024

Article published online:
19 September 2024

© 2024. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution-NonDerivative-NonCommercial License, permitting copying and reproduction so long as the original work is given appropriate credit. Contents may not be used for commercial purposes, or adapted, remixed, transformed or built upon. (https://creativecommons.org/licenses/by-nc-nd/4.0/)

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

Comment to this article:

The Rise of the Machines: Using Machine Learning to Assess Thrombosis and Bleeding Risks, and Optimizing Anticoagulation StrategiesThromb Haemost 2025; 125(05): 505-507
DOI: 10.1055/a-2460-2894

 

  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 5 Chew D, Piccini JP. Long-term oral anticoagulant after catheter ablation for atrial fibrillation. Europace 2021; 23 (08) 1157-1165
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 20 Natekin A, Knoll A. Gradient boosting machines, a tutorial. Front Neurorobot 2013; 7: 21
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 22 LaValley MP. Logistic regression. Circulation 2008; 117 (18) 2395-2399
    CrossrefPubMedSearch in Google Scholar
  • 23 Zuo C, Qian J, Feng S. et al. Deep learning in optical metrology: a review. Light Sci Appl 2022; 11 (01) 39
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 30 Shwartz-Ziv R, Armon A. Tabular data: deep learning is not all you need. Inf Fusion 2022; 81: 84-90
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar