Predicting Survival of End-Stage Heart Failure patients receiving HeartMate-3: Comparing Machine learning Methods.
Journal
ASAIO journal (American Society for Artificial Internal Organs : 1992)
ISSN: 1538-943X
Titre abrégé: ASAIO J
Pays: United States
ID NLM: 9204109
Informations de publication
Date de publication:
02 Nov 2023
02 Nov 2023
Historique:
medline:
1
11
2023
pubmed:
1
11
2023
entrez:
1
11
2023
Statut:
aheadofprint
Résumé
HeartMate 3 is the only durable left ventricular assist devices (LVAD) currently implanted in the United States. The purpose of this study was to develop a predictive model for 1 year mortality of HeartMate 3 implanted patients, comparing standard statistical techniques and machine learning algorithms. Adult patients registered in the Society of Thoracic Surgeons, Interagency Registry for Mechanically Assisted Circulatory Support (STS-INTERMACS) database, who received primary implant with a HeartMate 3 between January 1, 2017, and December 31, 2019, were included. Epidemiological, clinical, hemodynamic, and echocardiographic characteristics were analyzed. Standard logistic regression and machine learning (elastic net and neural network) were used to predict 1 year survival. A total of 3,853 patients were included. Of these, 493 (12.8%) died within 1 year after implantation. Standard logistic regression identified age, Model End Stage Liver Disease (MELD)-XI score, right arterial (RA) pressure, INTERMACS profile, heart rate, and etiology of heart failure (HF), as important predictor factors for 1 year mortality with an area under the curve (AUC): 0.72 (0.66-0.77). This predictive model was noninferior to the ones developed using the elastic net or neural network. Standard statistical techniques were noninferior to neural networks and elastic net in predicting 1 year survival after HeartMate 3 implantation. The benefit of using machine-learning algorithms in the prediction of outcomes may depend on the type of dataset used for analysis.
Identifiants
pubmed: 37913499
doi: 10.1097/MAT.0000000000002050
pii: 00002480-990000000-00340
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
Copyright © ASAIO 2023.
Déclaration de conflit d'intérêts
M.L. discloses grants and consulting fees for Abbott and Abiomed. S.L. discloses support from Abbott to attend the Heart Failure User’s meetings in May 2022 and October 2019. R.Y.L.-R. discloses support from Abbott to attend an educational meeting in August 2023. The other authors have no conflicts of interest to report.
Références
Molina EJ, Shah P, Kiernan MS, et al.: The society of thoracic surgeons Intermacs 2020 Annual Report. Ann Thorac Surg 111: 778–792, 2021.
Mehra MR, Uriel N, Naka Y, et al.; MOMENTUM 3 Investigators: A fully magnetically levitated left ventricular assist device—Final report. N Engl J Med 380: 1618–1627, 2019.
Mehra MR, Goldstein DJ, Cleveland JC, et al.: Five-year outcomes in patients with fully magnetically levitated vs axial-flow left ventricular assist devices in the MOMENTUM 3 randomized trial. JAMA 328: 1233–1242, 2022.
Miller LW, Guglin M: Patient selection for ventricular assist devices: A moving target. J Am Coll Cardiol 61: 1209–1221, 2013.
Ravichandran AK, Cowger J: Left ventricular assist device patient selection: Do risk scores help? J Thorac Dis 7: 2080–2087, 2015.
Kanwar MK, Lohmueller LC, Kormos RL, et al.: A Bayesian model to predict survival after left ventricular assist device implantation. JACC Heart Failure 6: 771–779, 2018.
Stehlik J, Kirklin JK: The long and winding road to an effective left ventricular assist device: The demise of Medtronic’s HVAD. Circulation 144: 509–511, 2021.
Quer G, Arnaout R, Henne M, Arnaout R: Machine learning and the future of cardiovascular care: JACC state-of-the-art review. J Am Coll Cardiol 77: 300–313, 2021.
Kanwar MK, Kilic A, Mehra MR: Machine learning, artificial intelligence and mechanical circulatory support: A primer for clinicians. J Heart Lung Transplant 40: 414–425, 2021.
Kanwar MK, Lohmueller LC, Kormos RL, et al.: Low accuracy of the HeartMate risk score for predicting mortality using the INTERMACS registry data. ASAIO J 63: 251–256, 2017.
Radhoe SP, Veenis JF, Jakus N, et al.: How does age affect outcomes after left ventricular assist device implantation: Results from the PCHF-VAD registry. ESC Heart Failure 10: 884–894, 2022.
Pagani FD: Is durable left ventricular assist device therapy a viable option for the elderly? J Am Coll Cardiol 78: 895–897, 2021.
Matthews JC, Pagani FD, Haft JW, Koelling TM, Naftel DC, Aaronson KD: Model for end-stage liver disease score predicts left ventricular assist device operative transfusion requirements, morbidity, and mortality. Circulation 121: 214–220, 2010.
Saeed D, Potapov E, Loforte A, et al.: Transition from temporary to durable circulatory support systems. J Am Coll Cardiol 76: 2956–2964, 20202964.
Stevenson LW, Pagani FD, Young JB, et al.: INTERMACS profiles of advanced heart failure: The current picture. J Heart Lung Transplant 28: 535–541, 2009.
Loyaga-Rendon RY, Acharya D, Kirklin JK: LVAD implantation or heart transplantation for ECMO-supported patients. J Am Coll Cardiol 76: 2575–2576, 2020.
Abubakar H, Subahi A, Adegbala O, et al.: Comparison of in-hospital outcomes of patients with-versus-without ischemic cardiomyopathy undergoing left ventricular assist device placement. Am J Cardiol 123: 414–418, 2019.
Rame JE, Pagani FD, Kiernan MS, et al.: Evolution of late right heart failure with left ventricular assist devices and association with outcomes. J Am Coll Cardiol 78: 2294–2308, 2021.
Imamura T, Kinugawa K, Narang N, et al.: Implications of heart rate in patients with left ventricular assist devices. Int Heart J 63: 56–61, 2022.
Krittanawong C, Virk HUH, Bangalore S, et al.: Machine learning prediction in cardiovascular diseases: A meta-analysis. Sci Rep 10: 16057, 2020.
Zou H, Hastie T: Regularization and variable selection via the elastic net. J R Stat Soc B 67: 301–320, 2005.
Hastie T, Tibshirani R, Friedman J: The Elements of Statistical Learning, 2nd ed. New York, NY, Springer, 2008, pp. 43–94.
Samarasinghe S: Neural Networks for Applied Sciences and Engineering. Boca Raton, FL, Auerbach Publications, 2007, pp. 11–67.
Samarasinghe S: Neural Networks for Applied Sciences and Engineering. Boca Raton, FL, Auerbach Publishers, 2007, pp. 69–112.
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 2: 204–209, 2017.
Steyerberg E: Clinical Prediction Models: A Practical Approach to Development, Validation and Updating. New York, NY, Springer, 2009.
Bzdok D, Altman N, Krzywinski M: Statistics versus machine learning. Nat Methods 15: 233–234, 2018.
Mehra M, Morris A, Lanfear DE, et al.: Prediction of survival after implantation of a fully magnetically levitated left ventricular assist device. JACC Heart Failure 10: 948–959, 2022.
Cogswell R, Estep JD, Araujo-Gutierrez R, et al.: Heart failure severity stratification beyond INTERMACS profiles: A step toward optimal left ventricular assist device timing. ASAIO J 67: 554–560, 2021.