Key result
Standard logistic regression matches machine learning in predicting 1-year survival after HeartMate 3 implantation.
Why the study?
HeartMate 3 is the only durable LVAD currently implanted in the United States, prompting the development of a 1-year mortality prediction model comparing standard statistical techniques and machine learning algorithms.
Do machine learning algorithms improve the prediction of 1-year mortality compared to standard logistic regression in end-stage heart failure patients receiving a HeartMate 3 LVAD?
Observational (n=3,853)
Yes
Do machine learning algorithms improve the prediction of 1-year mortality compared to standard logistic regression in end-stage heart failure patients receiving a HeartMate 3 LVAD?
Effect estimate: AUC 0.72 (95% CI 0.66-0.77)
Standard logistic regression is noninferior to complex machine learning algorithms like neural networks and elastic net for predicting 1-year survival after HeartMate 3 implantation.
Simpler logistic regression suffices for post-HeartMate 3 survival prediction; leaves open ML value in prospective or external validation.
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.
No takes yet. Share an insight, caveat, or question.
Loyaga‐Rendon et al. (2023) conducted an observational in End-Stage Heart Failure (n=3,853). Standard logistic regression vs. Machine learning algorithms (elastic net and neural network) was evaluated on Prediction of 1 year mortality (AUC 0.72, 95% CI 0.66-0.77). Standard logistic regression was noninferior to machine learning algorithms in predicting 1-year survival after HeartMate 3 implantation (AUC 0.72; 95% CI 0.66-0.77).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: