{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T21:52:40Z","timestamp":1791237160232,"version":"4.1.0"},"reference-count":38,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T00:00:00Z","timestamp":1622764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100009077","name":"ITEA3","doi-asserted-by":"publisher","award":["16017"],"award-info":[{"award-number":["16017"]}],"id":[{"id":"10.13039\/501100009077","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCDD"],"abstract":"<jats:p>Current prognostic risk scores for transcatheter aortic valve implantation (TAVI) do not benefit yet from modern machine learning techniques, which can improve risk stratification of one-year mortality of patients before TAVI. Despite the advancement of machine learning in healthcare, data sharing regulations are very strict and typically prevent exchanging patient data, without the involvement of ethical committees. A very robust validation approach, including 1300 and 631 patients per center, was performed to validate a machine learning model of one center at the other external center with their data, in a mutual fashion. This was achieved without any data exchange but solely by exchanging the models and the data processing pipelines. A dedicated exchange protocol was designed to evaluate and quantify the model\u2019s robustness on the data of the external center. Models developed with the larger dataset offered similar or higher prediction accuracy on the external validation. Logistic regression, random forest and CatBoost lead to areas under curve of the ROC of 0.65, 0.67 and 0.65 for the internal validation and of 0.62, 0.66, 0.68 for the external validation, respectively. We propose a scalable exchange protocol which can be further extended on other TAVI centers, but more generally to any other clinical scenario, that could benefit from this validation approach.<\/jats:p>","DOI":"10.3390\/jcdd8060065","type":"journal-article","created":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T11:12:13Z","timestamp":1622805133000},"page":"65","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Machine Learning for Predicting Mortality in Transcatheter Aortic Valve Implantation: An Inter-Center Cross Validation Study"],"prefix":"10.3390","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9366-4353","authenticated-orcid":false,"given":"Marco","family":"Mamprin","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Eindhoven University of Technology, 5612 AE Eindhoven, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5515-1488","authenticated-orcid":false,"given":"Ricardo R.","family":"Lopes","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering and Physics, Amsterdam UMC, University of Amsterdam, 1105 AZ Amsterdam, The Netherlands"},{"name":"Department of Radiology and Nuclear Medicine, Amsterdam UMC, University of Amsterdam, 1105 AZ Amsterdam, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2110-4901","authenticated-orcid":false,"given":"Jo M.","family":"Zelis","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Catharina Hospital, 5623 EJ Eindhoven, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pim A. L.","family":"Tonino","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Catharina Hospital, 5623 EJ Eindhoven, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8994-8946","authenticated-orcid":false,"given":"Martijn S.","family":"van Mourik","sequence":"additional","affiliation":[{"name":"Heart Centre, Amsterdam UMC, University of Amsterdam, 1105 AZ Amsterdam, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marije M.","family":"Vis","sequence":"additional","affiliation":[{"name":"Heart Centre, Amsterdam UMC, University of Amsterdam, 1105 AZ Amsterdam, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Svitlana","family":"Zinger","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Eindhoven University of Technology, 5612 AE Eindhoven, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bas A. J. M.","family":"de Mol","sequence":"additional","affiliation":[{"name":"Heart Centre, Amsterdam UMC, University of Amsterdam, 1105 AZ Amsterdam, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter H. N.","family":"de With","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Eindhoven University of Technology, 5612 AE Eindhoven, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2739","DOI":"10.1093\/eurheartj\/ehx391","article-title":"2017 ESC\/EACTS Guidelines for the management of valvular heart disease","volume":"38","author":"Baumgartner","year":"2017","journal-title":"Eur. Heart J."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1007\/s11517-016-1594-6","article-title":"2D to 3D fusion of echocardiography and cardiac CT for TAVR and TAVI image guidance","volume":"55","author":"Khalil","year":"2017","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Grbic, S., Mansi, T., Ionasec, R., Voigt, I., Houle, H., John, M., Schoebinger, M., Navab, N., and Comaniciu, D. (2013). Image-based computational models for TAVI planning: From CT images to implant deployment. Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2013, Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Nagoya, Japan, 22\u201326 September 2013, Springer.","DOI":"10.1007\/978-3-642-40763-5_49"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Swee, J.K.Y., and Grbi\u0107, S. (2014). Advanced transcatheter aortic valve implantation (TAVI) planning from CT with ShapeForest. Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2014, Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Boston, MA, USA, 14\u201318 September 2014, Springer.","DOI":"10.1007\/978-3-319-10470-6_3"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.ahj.2016.10.020","article-title":"Inadequacy of existing clinical prediction models for predicting mortality after transcatheter aortic valve implantation","volume":"184","author":"Martin","year":"2017","journal-title":"Am. Heart J."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"S23","DOI":"10.1016\/j.athoracsur.2009.05.056","article-title":"The Society of Thoracic Surgeons 2008 cardiac surgery risk models: Part 2\u2014Isolated valve surgery","volume":"88","author":"Shahian","year":"2009","journal-title":"Ann. Thorac. Surg."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/S1010-7940(99)00134-7","article-title":"European system for cardiac operative risk evaluation (Euro SCORE)","volume":"16","author":"Nashef","year":"1999","journal-title":"Eur. J. Cardio-Thorac. Surg."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1093\/ejcts\/ezs043","article-title":"Euroscore ii","volume":"41","author":"Nashef","year":"2012","journal-title":"Eur. J. Cardio-Thorac. Surg."},{"key":"ref_9","unstructured":"(2021, March 03). The Society of Thoracic Surgeons (STS) STS Web Risk Calculator v2.9. Available online: http:\/\/riskcalc.sts.org."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1001\/jamacardio.2015.0326","article-title":"Development and validation of a risk prediction model for in-hospital mortality after transcatheter aortic valve replacement","volume":"1","author":"Edwards","year":"2016","journal-title":"JAMA Cardiol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"e005481","DOI":"10.1161\/CIRCINTERVENTIONS.117.005481","article-title":"Predicting mortality after transcatheter aortic valve replacement: External validation of the transcatheter valve therapy registry model","volume":"10","author":"Pilgrim","year":"2017","journal-title":"Circ. Cardiovasc. Interv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1328","DOI":"10.1016\/j.jcin.2019.06.013","article-title":"Machine learning prediction models for in-hospital mortality after transcatheter aortic valve replacement","volume":"12","author":"Kim","year":"2019","journal-title":"JACC Cardiovasc. Interv."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1181","DOI":"10.1161\/CIRCULATIONAHA.114.013947","article-title":"Transcatheter aortic valve implantation in the United Kingdom: Temporal trends, predictors of outcome, and 6-year follow-up: A report from the UK Transcatheter Aortic Valve Implantation (TAVI) Registry, 2007 to 2012","volume":"131","author":"Ludman","year":"2015","journal-title":"Circulation"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1016\/j.amjcard.2014.10.029","article-title":"Value of the \u201cTAVI2-SCORe\u201d versus surgical risk scores for prediction of one year mortality in 511 patients who underwent transcatheter aortic valve implantation","volume":"115","author":"Debonnaire","year":"2015","journal-title":"Am. J. Cardiol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1868","DOI":"10.1016\/j.jacc.2016.07.762","article-title":"Prediction of poor outcome after transcatheter aortic valve replacement","volume":"68","author":"Arnold","year":"2016","journal-title":"J. Am. Coll. Cardiol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e000879","DOI":"10.1136\/openhrt-2018-000879","article-title":"Guideline-defined futility or patient-reported outcomes to assess treatment success after TAVI: What to use? Results from a prospective cohort study with long-term follow-up","volume":"5","author":"Vendrik","year":"2018","journal-title":"Open Heart"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","article-title":"A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models","volume":"110","author":"Jie","year":"2019","journal-title":"J. Clin. Epidemiol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1723","DOI":"10.1038\/ajg.2013.332","article-title":"Machine learning algorithms outperform conventional regression models in predicting development of hepatocellular carcinoma","volume":"108","author":"Singal","year":"2013","journal-title":"Am. J. Gastroenterol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1007\/s12471-019-1285-7","article-title":"Value of machine learning in predicting TAVI outcomes","volume":"27","author":"Lopes","year":"2019","journal-title":"Neth. Heart J."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Mamprin, M., Zelis, J.M., Tonino, P.A.L., Zinger, S., and de With, P.H.N. (2021). Decision Trees for Predicting Mortality in Transcatheter Aortic Valve Implantation. Bioengineering, 8.","DOI":"10.3390\/bioengineering8020022"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2217","DOI":"10.1093\/eurheartj\/ehv756","article-title":"TAVI or No TAVI: Identifying patients unlikely to benefit from transcatheter aortic valve implantation","volume":"37","author":"Puri","year":"2016","journal-title":"Eur. Heart J."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1851","DOI":"10.1016\/j.amjcard.2014.03.014","article-title":"A simple risk tool (the OBSERVANT score) for prediction of 30-day mortality after transcatheter aortic valve replacement","volume":"113","author":"Capodanno","year":"2014","journal-title":"Am. J. Cardiol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1136\/heartjnl-2017-312489","article-title":"Novel United Kingdom prognostic model for 30-day mortality following transcatheter aortic valve implantation","volume":"104","author":"Martin","year":"2018","journal-title":"Heart"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1007\/s12471-018-1129-x","article-title":"Trends in patient characteristics and clinical outcome over 8 years of transcatheter aortic valve implantation","volume":"26","author":"Wiegerinck","year":"2018","journal-title":"Neth. Heart J."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1161\/CIRCULATIONAHA.114.014508","article-title":"Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) the TRIPOD Statement","volume":"131","author":"Collins","year":"2015","journal-title":"Circulation"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"b2393","DOI":"10.1136\/bmj.b2393","article-title":"Multiple imputation for missing data in epidemiological and clinical research: Potential and pitfalls","volume":"338","author":"Sterne","year":"2009","journal-title":"BMJ"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Jakobsen, J.C., Gluud, C., Wetterslev, J., and Winkel, P. (2017). When and how should multiple imputation be used for handling missing data in randomised clinical trials\u2014A practical guide with flowcharts. BMC Med. Res. Methodol., 17.","DOI":"10.1186\/s12874-017-0442-1"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1093\/oxfordjournals.pan.a004868","article-title":"Logistic regression in rare events data","volume":"9","author":"King","year":"2001","journal-title":"Polit. Anal."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_31","first-page":"559","article-title":"Imbalanced-learn: A python toolbox to tackle the curse of imbalanced datasets in machine learning","volume":"18","author":"Nogueira","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_33","first-page":"18","article-title":"Classification and regression by randomForest","volume":"2","author":"Liaw","year":"2002","journal-title":"R News"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_35","unstructured":"Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V., and Gulin, A. (2018, January 2\u20138). CatBoost: Unbiased boosting with categorical features. Proceedings of the Advances in Neural Information Processing Systems, Montr\u00e9al, QC, Canada."},{"key":"ref_36","unstructured":"Dorogush, A.V., Ershov, V., and Gulin, A. (2018). CatBoost: Gradient boosting with categorical features support. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1016","DOI":"10.1136\/heartjnl-2013-305314","article-title":"Predictive factors of early mortality after transcatheter aortic valve implantation: Individual risk assessment using a simple score","volume":"100","author":"Iung","year":"2014","journal-title":"Heart"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Penso, M., Pepi, M., Fusini, L., Muratori, M., Cefal\u00f9, C., Mantegazza, V., Gripari, P., Ali, S.G., Fabbiocchi, F., and Bartorelli, A.L. (2021). Predicting Long-Term Mortality in TAVI Patients Using Machine Learning Techniques. J. Cardiovasc. Dev. Dis., 8.","DOI":"10.3390\/jcdd8040044"}],"container-title":["Journal of Cardiovascular Development and Disease"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2308-3425\/8\/6\/65\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:10:55Z","timestamp":1760163055000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2308-3425\/8\/6\/65"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,4]]},"references-count":38,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["jcdd8060065"],"URL":"https:\/\/doi.org\/10.3390\/jcdd8060065","relation":{},"ISSN":["2308-3425"],"issn-type":[{"value":"2308-3425","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,4]]}}}