{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:38:17Z","timestamp":1792787897198,"version":"4.5.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T00:00:00Z","timestamp":1676592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T00:00:00Z","timestamp":1676592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"General program of National Natural Science Funds of China","award":["81970274"],"award-info":[{"award-number":["81970274"]}]},{"name":"General program of National Natural Science Funds of China","award":["81970274"],"award-info":[{"award-number":["81970274"]}]},{"name":"General program of National Natural Science Funds of China","award":["81970274"],"award-info":[{"award-number":["81970274"]}]},{"name":"General program of National Natural Science Funds of China","award":["81970274"],"award-info":[{"award-number":["81970274"]}]},{"name":"General program of National Natural Science Funds of China","award":["81970274"],"award-info":[{"award-number":["81970274"]}]},{"name":"General program of National Natural Science Funds of China","award":["81970274"],"award-info":[{"award-number":["81970274"]}]},{"name":"General program of National Natural Science Funds of China","award":["81970274"],"award-info":[{"award-number":["81970274"]}]},{"name":"General program of National Natural Science Funds of China","award":["81970274"],"award-info":[{"award-number":["81970274"]}]},{"name":"General program of National Natural Science Funds of China","award":["81970274"],"award-info":[{"award-number":["81970274"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Cardiovasc Disord"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>A number of models have been reported for predicting atrial fibrillation (AF) recurrence after catheter ablation. Although many machine learning (ML) models were developed among them, black-box effect existed widely. It was always difficult to explain how variables affect model output. We sought to implement an explainable ML model and then reveal its decision-making process in identifying patients with paroxysmal AF at high risk for recurrence after catheter ablation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Between January 2018 and December 2020, 471 consecutive patients with paroxysmal AF who had their first catheter ablation procedure were retrospectively enrolled. Patients were randomly assigned into training cohort (70%) and testing cohort (30%). The explainable ML model based on Random Forest (RF) algorithm was developed and modified on training cohort, and tested on testing cohort. In order to gain insight into the association between observed values and model output, Shapley additive explanations (SHAP) analysis was used to visualize the ML model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      In this cohort, 135 patients experienced tachycardias recurrences. With hyperparameters adjusted, the ML model predicted AF recurrence with an area under the curve of 66.7% in the testing cohort. Summary plots listed the top 15 features in descending order and preliminary showed the association between features and outcome prediction. Early recurrence of AF showed the most positive impact on model output. Dependence plots combined with force plots showed the impact of single feature on model output, and helped determine high risk cut-off points. The thresholds of CHA\n                      <jats:sub>2<\/jats:sub>\n                      DS\n                      <jats:sub>2<\/jats:sub>\n                      -VASc score, systolic blood pressure, AF duration, HAS-BLED score, left atrial diameter and age were 2, 130\u00a0mmHg, 48\u00a0months, 2, 40\u00a0mm and 70\u00a0years, respectively. Decision plot recognized significant outliers.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>An explainable ML model effectively revealed its decision-making process in identifying patients with paroxysmal atrial fibrillation at high risk for recurrence after catheter ablation by listing important features, showing the impact of every feature on model output, determining appropriate thresholds and identifying significant outliers. Physicians can combine model output, visualization of model and clinical experience to make better decision.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12872-023-03087-0","type":"journal-article","created":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T06:06:49Z","timestamp":1676614009000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Explainable machine learning model reveals its decision-making process in identifying patients with paroxysmal atrial fibrillation at high risk for recurrence after catheter ablation"],"prefix":"10.1186","volume":"23","author":[{"given":"Yibo","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huani","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miaoyang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiqiang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lanyan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fu","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,17]]},"reference":[{"issue":"Suppl 3","key":"3087_CR1","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1055\/s-2007-1013197","volume":"47","author":"MD Lesh","year":"1999","unstructured":"Lesh MD, Diederich C, Guerra PG, et al. An anatomic approach to prevention of atrial fibrillation: pulmonary vein isolation with through-the-balloon ultrasound ablation (TTB-USA). Thorac Cardiovasc Surg. 1999;47(Suppl 3):347\u201351.","journal-title":"Thorac Cardiovasc Surg"},{"key":"3087_CR2","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1056\/NEJM199809033391003","volume":"339","author":"M Ha\u00efssaguerre","year":"1998","unstructured":"Ha\u00efssaguerre M, Ja\u00efs P, Shah DC, et al. Spontaneous initiation of atrial fibrillation by ectopic beats originating in the pulmonary veins. N Engl J Med. 1998;339:659\u201366.","journal-title":"N Engl J Med"},{"key":"3087_CR3","doi-asserted-by":"publisher","first-page":"1630","DOI":"10.1136\/heartjnl-2021-319496","volume":"107","author":"JF Imberti","year":"2021","unstructured":"Imberti JF, Ding WY, Kotalczyk A, et al. Catheter ablation as first-line treatment for paroxysmal atrial fibrillation: a systematic review and meta-analysis. Heart. 2021;107:1630\u20136.","journal-title":"Heart"},{"key":"3087_CR4","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1016\/j.jacc.2009.11.040","volume":"55","author":"CB de Vos","year":"2010","unstructured":"de Vos CB, Pisters R, Nieuwlaat R, et al. Progression from paroxysmal to persistent atrial fibrillation clinical correlates and prognosis. J Am Coll Cardiol. 2010;55:725\u201331.","journal-title":"J Am Coll Cardiol"},{"key":"3087_CR5","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1007\/s00392-015-0856-x","volume":"104","author":"J Kornej","year":"2015","unstructured":"Kornej J, Hindricks G, Shoemaker MB, et al. The APPLE score: a novel and simple score for the prediction of rhythm outcomes after catheter ablation of atrial fibrillation. Clin Res Cardiol. 2015;104:871\u20136.","journal-title":"Clin Res Cardiol"},{"key":"3087_CR6","doi-asserted-by":"publisher","first-page":"2119","DOI":"10.1016\/j.hrthm.2016.07.018","volume":"13","author":"RA Winkle","year":"2016","unstructured":"Winkle RA, Jarman JW, Mead RH, et al. Predicting atrial fibrillation ablation outcome: the CAAP-AF score. Heart Rhythm. 2016;13:2119\u201325.","journal-title":"Heart Rhythm"},{"key":"3087_CR7","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2021.736491","volume":"8","author":"G Wang","year":"2021","unstructured":"Wang G, Zhang Y, Li S, et al. A machine learning-based prediction model for cardiovascular risk in women with preeclampsia. Front Cardiovasc Med. 2021;8: 736491.","journal-title":"Front Cardiovasc Med"},{"key":"3087_CR8","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1007\/s00380-018-1244-z","volume":"34","author":"J Budzianowski","year":"2019","unstructured":"Budzianowski J, Hiczkiewicz J, Burchardt P, et al. Predictors of atrial fibrillation early recurrence following cryoballoon ablation of pulmonary veins using statistical assessment and machine learning algorithms. Heart Vessels. 2019;34:352\u20139.","journal-title":"Heart Vessels"},{"key":"3087_CR9","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.119.008213","volume":"13","author":"JK Shade","year":"2020","unstructured":"Shade JK, Ali RL, Basile D, et al. Preprocedure application of machine learning and mechanistic simulations predicts likelihood of paroxysmal atrial fibrillation recurrence following pulmonary vein isolation. Circ Arrhythm Electrophysiol. 2020;13: e008213.","journal-title":"Circ Arrhythm Electrophysiol"},{"key":"3087_CR10","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.120.008518","volume":"13","author":"CM Liu","year":"2020","unstructured":"Liu CM, Chang SL, Chen HH, et al. The clinical application of the deep learning technique for predicting trigger origins in patients with paroxysmal atrial fibrillation with catheter ablation. Circ Arrhythm Electrophysiol. 2020;13: e008518.","journal-title":"Circ Arrhythm Electrophysiol"},{"key":"3087_CR11","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.120.009265","volume":"14","author":"M Firouznia","year":"2021","unstructured":"Firouznia M, Feeny AK, LaBarbera MA, et al. Machine learning-derived fractal features of shape and texture of the left atrium and pulmonary veins from cardiac computed tomography scans are associated with risk of recurrence of atrial fibrillation postablation. Circ Arrhythm Electrophysiol. 2021;14: e009265.","journal-title":"Circ Arrhythm Electrophysiol"},{"key":"3087_CR12","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1186\/s12880-021-00578-4","volume":"21","author":"T Atta-Fosu","year":"2021","unstructured":"Atta-Fosu T, LaBarbera M, Ghose S, et al. A new machine learning approach for predicting likelihood of recurrence following ablation for atrial fibrillation from CT. BMC Med Imaging. 2021;21:45.","journal-title":"BMC Med Imaging"},{"key":"3087_CR13","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2022.813085","volume":"9","author":"M Yang","year":"2022","unstructured":"Yang M, Cao Q, Xu Z, et al. Development and validation of a machine learning-based radiomics model on cardiac computed tomography of epicardial adipose tissue in predicting characteristics and recurrence of atrial fibrillation. Front Cardiovasc Med. 2022;9: 813085.","journal-title":"Front Cardiovasc Med"},{"key":"3087_CR14","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.121.010253","volume":"15","author":"CH Roney","year":"2022","unstructured":"Roney CH, Sim I, Yu J, et al. Predicting atrial fibrillation recurrence by combining population data and virtual cohorts of patient-specific left atrial models. Circ Arrhythm Electrophysiol. 2022;15: e010253.","journal-title":"Circ Arrhythm Electrophysiol"},{"key":"3087_CR15","doi-asserted-by":"publisher","first-page":"2636","DOI":"10.3390\/jcm11092636","volume":"11","author":"JC Nu\u00f1ez-Garcia","year":"2022","unstructured":"Nu\u00f1ez-Garcia JC, S\u00e1nchez-Puente A, Sampedro-G\u00f3mez J, et al. Outcome analysis in elective electrical cardioversion of atrial fibrillation patients: development and validation of a machine learning prognostic model. J Clin Med. 2022;11:2636.","journal-title":"J Clin Med"},{"key":"3087_CR16","unstructured":"Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;4765\u201374."},{"key":"3087_CR17","doi-asserted-by":"publisher","first-page":"2235","DOI":"10.1056\/NEJMoa1602014","volume":"374","author":"KH Kuck","year":"2016","unstructured":"Kuck KH, Brugada J, F\u00fcrnkranz A, et al. Cryoballoon or radiofrequency ablation for paroxysmal atrial fibrillation. N Engl J Med. 2016;374:2235\u201345.","journal-title":"N Engl J Med"},{"key":"3087_CR18","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1016\/j.cjca.2021.09.004","volume":"38","author":"J Petch","year":"2022","unstructured":"Petch J, Di S, Nelson W. Opening the black box: the promise and limitations of explainable machine learning in cardiology. Can J Cardiol. 2022;38:204\u201313.","journal-title":"Can J Cardiol"},{"key":"3087_CR19","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1093\/eurheartj\/ehaa612","volume":"42","author":"G Hindricks","year":"2021","unstructured":"Hindricks G, Potpara T, Dagres N, et al. 2020 ESC Guidelines for the diagnosis and management of atrial fibrillation developed in collaboration with the European association for cardio-thoracic surgery (EACTS). Eur Heart J. 2021;42:373\u2013498.","journal-title":"Eur Heart J"},{"key":"3087_CR20","doi-asserted-by":"publisher","first-page":"766","DOI":"10.1016\/j.jcmg.2021.11.029","volume":"15","author":"AS Fahmy","year":"2022","unstructured":"Fahmy AS, Csecs I, Arafati A, et al. An explainable machine learning approach reveals prognostic significance of right ventricular dysfunction in nonischemic cardiomyopathy. JACC Cardiovasc Imag. 2022;15:766\u201379.","journal-title":"JACC Cardiovasc Imag"},{"key":"3087_CR21","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1186\/s12874-022-01540-w","volume":"22","author":"E Stenwig","year":"2022","unstructured":"Stenwig E, Salvi G, Rossi PS, et al. Comparative analysis of explainable machine learning prediction models for hospital mortality. BMC Med Res Methodol. 2022;22:53.","journal-title":"BMC Med Res Methodol"},{"key":"3087_CR22","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2021.750818","volume":"12","author":"X Wei","year":"2021","unstructured":"Wei X, Fu B, Chen X, et al. U-shaped association between serum uric acid and short-term mortality in patients with infective endocarditis. Front Endocrinol. 2021;12: 750818.","journal-title":"Front Endocrinol"},{"key":"3087_CR23","doi-asserted-by":"publisher","first-page":"2355","DOI":"10.1161\/HYPERTENSIONAHA.122.19912","volume":"79","author":"V Trimarco","year":"2022","unstructured":"Trimarco V, Izzo R, Morisco C, et al. High HDL (high-density lipoprotein) cholesterol increases cardiovascular risk in hypertensive patients. Hypertension. 2022;79:2355\u201363.","journal-title":"Hypertension"},{"key":"3087_CR24","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2022.866260","volume":"9","author":"Y Shao","year":"2022","unstructured":"Shao Y, Hu J. U-shaped association between blood pressure and mortality risk in ICU patients with atrial fibrillation: the MIMIC-III database. Front Cardiovasc Med. 2022;9: 866260.","journal-title":"Front Cardiovasc Med"},{"key":"3087_CR25","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1378\/chest.09-1584","volume":"137","author":"GY Lip","year":"2010","unstructured":"Lip GY, Nieuwlaat R, Pisters R, et al. 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. 2010;137:263\u201372.","journal-title":"Chest"},{"key":"3087_CR26","doi-asserted-by":"publisher","first-page":"6968","DOI":"10.1038\/s41598-021-86327-7","volume":"11","author":"A Moncada-Torres","year":"2021","unstructured":"Moncada-Torres A, van Maaren MC, Hendriks MP, et al. Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival. Sci Rep. 2021;11:6968.","journal-title":"Sci Rep"},{"key":"3087_CR27","doi-asserted-by":"publisher","first-page":"1635","DOI":"10.1093\/europace\/euaa172","volume":"22","author":"Z Loring","year":"2020","unstructured":"Loring Z, Mehrotra S, Piccini JP, et al. Machine learning does not improve upon traditional regression in predicting outcomes in atrial fibrillation: an analysis of the ORBIT-AF and GARFIELD-AF registries. Europace. 2020;22:1635\u201344.","journal-title":"Europace"},{"key":"3087_CR28","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m3919","volume":"371","author":"Y Li","year":"2020","unstructured":"Li Y, Sperrin M, Ashcroft DM, et al. Consistency of variety of machine learning and statistical models in predicting clinical risks of individual patients: longitudinal cohort study using cardiovascular disease as exemplar. BMJ. 2020;371: m3919.","journal-title":"BMJ"},{"key":"3087_CR29","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/S0140-6736(19)31721-0","volume":"394","author":"ZI Attia","year":"2019","unstructured":"Attia ZI, Noseworthy PA, Lopez-Jimenez F, et al. An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction. Lancet. 2019;394:861\u20137.","journal-title":"Lancet"},{"key":"3087_CR30","doi-asserted-by":"publisher","first-page":"1909","DOI":"10.1056\/NEJMoa1901183","volume":"381","author":"MV Perez","year":"2019","unstructured":"Perez MV, Mahaffey KW, Hedlin H, et al. Large-scale assessment of a smartwatch to identify atrial fibrillation. N Engl J Med. 2019;381:1909\u201317.","journal-title":"N Engl J Med"},{"key":"3087_CR31","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.122.025303","volume":"11","author":"AC van der Burgh","year":"2022","unstructured":"van der Burgh AC, Geurts S, Ikram MA, et al. Bidirectional association between kidney function and atrial fibrillation: a population-based cohort study. J Am Heart Assoc. 2022;11: e025303.","journal-title":"J Am Heart Assoc"}],"container-title":["BMC Cardiovascular Disorders"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12872-023-03087-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12872-023-03087-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12872-023-03087-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T06:08:54Z","timestamp":1676614134000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmccardiovascdisord.biomedcentral.com\/articles\/10.1186\/s12872-023-03087-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,17]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["3087"],"URL":"https:\/\/doi.org\/10.1186\/s12872-023-03087-0","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2132088\/v1","asserted-by":"object"}]},"ISSN":["1471-2261"],"issn-type":[{"value":"1471-2261","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,17]]},"assertion":[{"value":"4 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study confirmed to Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) statement and was approved by the ethics committee of the First Affiliated Hospital of Air Force Medical University according to the principles of the Declaration of Helsinki. Written informed consent were provided by all patients before procedure.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"91"}}