Swipe om te navigeren naar een ander artikel
The online version of this article (https://doi.org/10.1007/s12471-019-1285-7) contains supplementary material, which is available to authorized users.
Transcatheter aortic valve implantation (TAVI) has become a commonly applied procedure for high-risk aortic valve stenosis patients. However, for some patients, this procedure does not result in the expected benefits. Previous studies indicated that it is difficult to predict the beneficial effects for specific patients. We aim to study the accuracy of various traditional machine learning (ML) algorithms in the prediction of TAVI outcomes.
Clinical and laboratory data from 1,478 TAVI patients from a single centre were collected. The outcome measures were improvement of dyspnoea and mortality. Three experiments were performed using (1) screening data, (2) laboratory data, and (3) the combination of both. Five well-established ML techniques were implemented, and the models were evaluated based on the area under the curve (AUC). Random forest classifier achieved the highest AUC (0.70) for predicting mortality. Logistic regression had the highest AUC (0.56) in predicting improvement of dyspnoea.
In our single-centre TAVI population, the tree-based models were slightly more accurate than others in predicting mortality. However, ML models performed poorly in predicting improvement of dyspnoea.
Summarized patient characteristics and hyperparameters used for optimisation.12471_2019_1285_MOESM1_ESM.docx
Khalil A, Faisal A, Lai KW, Ng SC, Liew YM. 2D to 3D fusion of echocardiography and cardiac CT for TAVR and TAVI image guidance. Med Biol Eng Comput. 2017;55:1317–26.
Grbic S, Mansi T, Ionasec R, et al. Image-based computational models for TAVI planning: from CT images to implant deployment. Med Image Comput Comput Interv. IEEE Trans Med Imaging. 2013;395:402.
Swee JKY, Implantation GS. (TAVI) planning from CT with ShapeForest. Med Image Comput Comput Interv—MICCAI. IEEE Trans Med Imaging. 2014;17:24.
Puri R, Iung B, Cohen DJ, Rodés-Cabau J. TAVI or no TAVI: identifying patients unlikely to benefit from transcatheter aortic valve implantation. Eur Heart J. 2016;37:2217–25.
Martin GP, Sperrin M, Ludman PF, et al. Inadequacy of existing clinical prediction models for predicting mortality after transcatheter aortic valve implantation. Am Heart J. 2017;184:97–105.
Van Mourik MS, Vendrik J, Abdelghani M, et al. 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. Open Heart. 2018;5(2):e000879. https://doi.org/10.1136/openhrt-2018-000879.
Lebedev AV, Westman E, Van Westen GJP, et al. Random forest ensembles for detection and prediction of Alzheimer’s disease with a good between-cohort robustness. Neuroimage Clin. 2014;6:115–25.
Nishio M, Nishizawa M, Sugiyama O, et al. Computer-aided diagnosis of lung nodule using gradient tree boosting and Bayesian optimization. PLoS ONE. 2018;13:1–13.
Singal A, Mukherjee A, Elmunzer BJ, et al. Machine learning algorithms outperform conventional regression models in predicting development of hepatocellular carcinoma. Am J Gastroenterol. 2016;42:407–20.
O’Brien SM, Shahian DM, et al. The Society of Thoracic Surgeons 2008 cardiac surgery risk models: part 2—isolated valve surgery. Ann Thorac Surg. 2009;88(1 Suppl):S23–S42. Jul.
Lemeshow S, Gauducheau E, et al. European system for cardiac operative risk evaluation (EuroSCORE). Eur J Cardiothorac Surg. 1999;16:9–13. Jul.
Pilgrim T, Franzone A, Stortecky S, et al. Predicting mortality after transcatheter aortic valve replacement: external validation of the transcatheter valve therapy registry model. Circ Cardiovasc Interv. 2017;10:1–9.
Ludman PF, Moat N, De Belder MA, et al. 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. Circulation. 2015;131:1181–90.
Lantelme P, Eltchaninoff H, Rabilloud M, et al. Development of a risk score based on aortic calcification to predict 1‑year mortality after transcatheter aortic valve replacement. Jacc Cardiovasc Imaging. 2019;12:123–32.
Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: machine learning in Python. J Mach Learn Res. 2012;12:2825–30.
Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20:273–97.
Breiman L. Random forests. Mach Learn. 2001;45:5–32.
Bishop CM. Neural networks for pattern recognition. New York: Oxford University Press; 1995.
Chen T, XGBoost GC. a scalable tree boosting system. Proc 22nd. SIGKDD Int Conf Knowl Discov Data Min. New York: ACM: ACM; 2016. pp. 785–94.
Friedman JH, Meulman JJ. Multiple additive regression trees with application in epidemiology. Stat Med. 2003;22:1365–81.
Memarian N, Kim S, Dewar S, Engel J, Staba RJ. Multimodal data and machine learning for surgery outcome prediction in complicated cases of mesial temporal lobe epilepsy. Comput Biol Med. 2015;64:67–78.
Frizzell JD, Liang L, Schulte PJ, et al. Prediction of 30-day all-cause readmissions in patients hospitalized for heart failure: comparison of machine learning and other statistical approaches. Jama Cardiol. 2017;2:204–9.
Ambale-Venkatesh B, Yang X, Wu CO, et al. Cardiovascular event prediction by machine learning: the multi-ethnic study of atherosclerosis. Circ Res. 2017;121:1092–101.
- Value of machine learning in predicting TAVI outcomes
R. R. Lopes
M. S. van Mourik
E. V. Schaft
L. A. Ramos
J. Baan Jr.
B. A. J. M. de Mol
M. M. Vis
H. A. Marquering
- Bohn Stafleu van Loghum