Abstract
Background
Targeting ischemic strokes patients at risk of incident atrial fibrillation (AF) for prolonged cardiac monitoring and oral anticoagulation remains a challenge. Clinical risk scores have been developed to predict post-stroke AF with suboptimal performances. Machine learning (ML) models are developing in the field of AF prediction and may be used to discriminate post-stroke patients at risk of new onset AF. This study aimed to evaluate ML models for the prediction of AF and to compare predictive ability to usual clinical scores.
Methods
Based on a French nationwide cohort of 240,459 ischemic stroke patients without AF at baseline from 2009 to 2012, ML models were trained on a train set and the best model was selected to be evaluate on the test set. Discrimination of the best model was evaluated using the C index. We finally compared our best model with previously described clinical scores.
Results
During a mean follow-up of 7.9 ± 11.5 months, 14,095 patients (mean age 77.6 ± 10.6; 50.3% female) developed incident AF. After training, the best ML model selected was a deep neural network with a C index of 0.77 (95% CI 0.76–0.78) on the test set. Compared to traditional clinical scores, the selected model was statistically significantly superior to the CHA2DS2-VASc score, Framingham risk score, HAVOC score and C2HEST score (P < 0.0001). The ability to predict AF was improved as shown by net reclassification index increase (P < 0.0001) and decision curve analysis.
Conclusions
ML algorithms predict incident AF post-stroke with a better ability than previously developed clinical scores.
Graphic Abstract
AF: atrial fibrillation; DNN: deep neural network; IS: ischemic stroke; KNN: K-nearest neighbors; LR: logistic regression; RFC: random forest classifier; XGBoost: extreme gradient boosting
Similar content being viewed by others
Data availability
Data will not be available according to the French legislation.
References
Benjamin EJ, Muntner P, Alonso A, Bittencourt MS, Callaway CW, Carson AP, Chamberlain AM et al (2019) Heart disease and stroke statistics-2019 update: a report from the American Heart Association. Circulation 139(10):e56-528. https://doi.org/10.1161/CIR.0000000000000659
Guo Y, Tian Y, Wang H, Si Q, Wang Y, Lip G (2015) Prevalence, incidence, and lifetime risk of atrial fibrillation in China: new insights into the global burden of atrial fibrillation. Chest 147(1):109–119. https://doi.org/10.1378/chest.14-0321
Burdett P, Lip GYH (2022) Atrial fibrillation in the UK: predicting costs of an emerging epidemic recognizing and forecasting the cost drivers of atrial fibrillation-related costs. Eur Heart J 8(2):187–194. https://doi.org/10.1093/ehjqcco/qcaa093
Hart RG, Pearce LA, Aguilar MI (2007) Meta-analysis: antithrombotic therapy to prevent stroke in patients who have nonvalvular atrial fibrillation. Ann Intern Med 146(12):857–867. https://doi.org/10.7326/0003-4819-146-12-200706190-00007
Hindricks G, Potpara T, Dagres N, Arbelo E, Bax JJ, Blomström-Lundqvist C, Boriani G et al (2021) 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 42(5):373–498. https://doi.org/10.1093/eurheartj/ehaa612
Chao T-F, Joung B, Takahashi Y, Lim TW, Choi E-K, Chan Y-H, Guo Y et al (2022) 2021 Focused update consensus guidelines of the Asia Pacific Heart rhythm society on stroke prevention in atrial fibrillation: executive summary. Thromb Haemost 122(1):20–47. https://doi.org/10.1055/s-0041-1739411
Kishore A, Vail A, Majid A, Dawson J, Lees KR, Tyrrell PJ, Smith CJ (2014) Detection of atrial fibrillation after ischemic stroke or transient ischemic attack: a systematic review and meta-analysis. Stroke 45(2):520–526. https://doi.org/10.1161/STROKEAHA.113.003433
Sposato LA, Cipriano LE, Saposnik G, Vargas ER, Riccio PM, Hachinski V (2015) Diagnosis of atrial fibrillation after stroke and transient ischaemic attack: a systematic review and meta-analysis. Lancet Neurol 14(4):377–387. https://doi.org/10.1016/S1474-4422(15)70027-X
Bisson A, Bodin A, Clementy N, Babuty D, Lip GYH, Fauchier L (2018) Prediction of incident atrial fibrillation according to gender in patients with ischemic stroke from a nationwide cohort. Am J Cardiol 121(4):437–444. https://doi.org/10.1016/j.amjcard.2017.11.016
Li Y-G, Bisson A, Bodin A, Herbert J, Grammatico-Guillon L, Joung B, Wang Y-T, Lip GYH, Fauchier L (2019) C2 HEST score and prediction of incident atrial fibrillation in poststroke patients: a french nationwide study. J Am Heart Assoc 8(13):e012546. https://doi.org/10.1161/JAHA.119.012546
Bishop CM (2006) Pattern recognition and machine learning, 3rd edn. Springer, New York
Hill NR, Ayoubkhani D, McEwan P, Sugrue DM, Farooqui U, Lister S, Lumley M et al (2019) Predicting atrial fibrillation in primary care using machine learning. PLoS One 14(11):e0224582. https://doi.org/10.1371/journal.pone.0224582
Sekelj S, Sandler B, Johnston E, Pollock KG, Hill NR, Gordon J, Tsang C, Khan S, Ng FS, Farooqui U (2020) Detecting undiagnosed atrial fibrillation in UK primary care: validation of a machine learning prediction algorithm in a retrospective cohort study. Eur J Prevent Cardiol. https://doi.org/10.1177/2047487320942338
Lip GYH, Genaidy A, Tran G, Marroquin P, Estes C, Sloop S (2022) Improving stroke risk prediction in the general population: a comparative assessment of common clinical rules, a new multimorbid index, and machine-learning-based algorithms. Thromb Haemost 122(1):142–150. https://doi.org/10.1055/a-1467-2993
Couris CM, Polazzi S, Olive F, Remontet L, Bossard N, Gomez F, Schott A-M, Mitton N, Colonna M, Trombert B (2009) Breast cancer incidence using administrative data: correction with sensitivity and specificity. J Clin Epidemiol 62(6):660–666. https://doi.org/10.1016/j.jclinepi.2008.07.013
Fauchier L, Clementy N, Pelade C, Collignon C, Nicolle E, Lip GYH (2015) Patients with ischemic stroke and incident atrial fibrillation: a nationwide cohort study. Stroke 46(9):2432–2437. https://doi.org/10.1161/STROKEAHA.115.010270
Lip GYH, Nieuwlaat R, Pisters R, Lane DA, Crijns HJGM (2010) Refining clinical risk stratification for predicting stroke and thromboembolism in atrial fibrillation using a novel risk factor-based approach: the euro heart survey on atrial fibrillation. Chest 137(2):263–272. https://doi.org/10.1378/chest.09-1584
Li Y-G, Pastori D, Farcomeni A, Yang P-S, Jang E, Joung B, Wang Y-T, Guo Y-T, Lip GYH (2019) A simple clinical risk score (C2HEST) for predicting incident atrial fibrillation in Asian subjects: derivation in 471,446 Chinese subjects, with internal validation and external application in 451,199 Korean Subjects. Chest 155(3):510–518. https://doi.org/10.1016/j.chest.2018.09.011
Kwong C, Ling AY, Crawford MH, Zhao SX, Shah NH (2017) A clinical score for predicting atrial fibrillation in patients with cryptogenic stroke or transient ischemic attack. Cardiology 138(3):133–140. https://doi.org/10.1159/000476030
Schnabel RB, Sullivan LM, Levy D, Pencina MJ, Massaro JM, D’Agostino RB, Newton-Cheh C et al (2009) Development of a risk score for atrial fibrillation (Framingham Heart Study): a community-based cohort study. Lancet (London, England) 373(9665):739–745. https://doi.org/10.1016/S0140-6736(09)60443-8
DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44(3):837–845
Pencina MJ, D’Agostino RB, D’Agostino RB, Vasan RS (2008) Evaluating the added predictive ability of a new marker: from area under the ROC curve to reclassification and beyond. Stat Med 27(2):157–172. https://doi.org/10.1002/sim.2929. (discussion 207–212)
Vickers AJ, Cronin AM, Elkin EB, Gonen M (2008) Extensions to decision curve analysis, a novel method for evaluating diagnostic tests, prediction models and molecular markers. BMC Med Inform Decis Mak 8:53
Bisson A, Clementy N, Bodin A, Angoulvant D, Babuty D, Lip GYH, Fauchier L (2017) Relationship of preexisting cardiovascular comorbidities to newly diagnosed atrial fibrillation after ischemic stroke. Stroke 48(10):2878–2880. https://doi.org/10.1161/STROKEAHA.117.018251
Olier I, Ortega-Martorell S, Pieroni M, Lip GYH (2021) How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management. Cardiovasc Res 117(7):1700–1717. https://doi.org/10.1093/cvr/cvab169
Chua W, Purmah Y, Cardoso VR, Gkoutos GV, Tull SP, Neculau G, Thomas MR et al (2019) Data-driven discovery and validation of circulating blood-based biomarkers associated with prevalent atrial fibrillation. Eur Heart J 40(16):1268–1276. https://doi.org/10.1093/eurheartj/ehy815
Zheng X, Wang F, Zhang J, Cui X, Jiang F, Chen N, Zhou J, Chen J, Lin S, Zou J (2022) Using machine learning to predict atrial fibrillation diagnosed after ischemic stroke. Int J Cardiol 347(January):21–27. https://doi.org/10.1016/j.ijcard.2021.11.005
Lip GYH, Tran G, Genaidy A, Marroquin P, Estes C, Landsheft J (2022) Improving dynamic stroke risk prediction in non-anticoagulated patients with and without atrial fibrillation: comparing common clinical risk scores and machine learning algorithms. Eur Heart J 8(5):548–556. https://doi.org/10.1093/ehjqcco/qcab037
Lip GYH, Genaidy A, Tran G, Marroquin P, Estes C (2021) Incident atrial fibrillation and its risk prediction in patients developing COVID-19: a machine learning based algorithm approach. Eur J Intern Med 91(September):53–58. https://doi.org/10.1016/j.ejim.2021.04.023
Skrebelyte-Strøm L, Rønning OM, Dahl FA, Steine K, Kjekshus H (2022) Prediction of occult atrial fibrillation in patients after cryptogenic stroke and transient ischaemic attack: PROACTIA. Europace. https://doi.org/10.1093/europace/euac092
Nielsen JC, Lin Y-J, de Oliveira Figueiredo MJ, Shamloo AS, Alfie A, Boveda S, Dagres N et al (2020) European Heart Rhythm Association (EHRA)/Heart Rhythm Society (HRS)/Asia Pacific Heart Rhythm Society (APHRS)/Latin American Heart Rhythm Society (LAHRS) expert consensus on risk assessment in cardiac arrhythmias: use the right tool for the right outcome, in the right population. Europace 22(8):1147–1148. https://doi.org/10.1093/europace/euaa065
Hart RG, Sharma M, Mundl H, Kasner SE, Bangdiwala SI, Berkowitz SD, Swaminathan B et al (2018) Rivaroxaban for stroke prevention after embolic stroke of undetermined source. N Engl J Med 378(23):2191–2201. https://doi.org/10.1056/NEJMoa1802686
Diener H-C, Sacco RL, Donald Easton J, Granger CB, Bernstein RA, Uchiyama S, Kreuzer J et al (2019) Dabigatran for prevention of stroke after embolic stroke of undetermined source. N Engl J Med 380(20):1906–1917. https://doi.org/10.1056/NEJMoa1813959
Poli S, Meissner C, Baezner HJ, Kraft A, Hillenbrand F, Hobohm C, Liman J et al (2021) Apixaban for treatment of embolic stroke of undetermined source (ATTICUS) randomized trial—update of patient characteristics and study timeline after interim analysis. Eur Heart J 42(Supplement_1):ehab724.2070. https://doi.org/10.1093/eurheartj/ehab724.2070
Sanna T, Diener H-C, Passman RS, Di Lazzaro V, Bernstein RA, Morillo CA, Rymer MM et al (2014) Cryptogenic stroke and underlying atrial fibrillation. N Engl J Med 370(26):2478–2486. https://doi.org/10.1056/NEJMoa1313600
Gladstone DJ, Spring M, Dorian P, Panzov V, Thorpe KE, Hall J, Vaid H et al (2014) Atrial fibrillation in patients with cryptogenic stroke. N Engl J Med 370(26):2467–2477. https://doi.org/10.1056/NEJMoa1311376
Rubiera M, Aires A, Antonenko K, Lémeret S, Nolte CH, Putaala J, Schnabel RB et al (2022) European Stroke Organisation (ESO) guideline on screening for subclinical atrial fibrillation after stroke or transient ischaemic attack of undetermined origin. Eur Stroke J. https://doi.org/10.1177/23969873221099478
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
A.Bisson has been a consultant or speaker for Astra-Zeneca, Bayer, BMS/Pfizer, Medtronic, Vitorpharma and Alnylam. D. Angoulvant has been a consultant or speaker for Amgen, Astra-Zeneca, Bayer, BMS/Pfizer, MSD, Novartis, Novo Nordisk, Sanofi, Servier. GYH.Lip has been a consultant for Bayer/Janssen, BMS/Pfizer, Medtronic, Boehringer Ingelheim, Novartis, Verseon, and Daiichi-Sankyo and a speaker for Bayer, BMS/Pfizer, Medtronic, Boehringer Ingelheim, and Daiichi-Sankyo; no fees are directly received personally. L. Fauchier has been a consultant or speaker for Bayer, BMS/Pfizer, Boehringer Ingelheim, Medtronic, and Novartis.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Bisson, A., Lemrini, Y., El-Bouri, W. et al. Prediction of incident atrial fibrillation in post-stroke patients using machine learning: a French nationwide study. Clin Res Cardiol 112, 815–823 (2023). https://doi.org/10.1007/s00392-022-02140-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00392-022-02140-w