loading page

Using Machine Learning to Improve Survival Prediction After Heart Transplantation
  • +2
  • Brian Ayers,
  • Tuomas Sandholm,
  • Igor Gosev,
  • Sunil Prasad,
  • Arman Kilic
Brian Ayers
Massachusetts General Hospital

Corresponding Author:[email protected]

Author Profile
Tuomas Sandholm
Carnegie Mellon University
Author Profile
Igor Gosev
University of Rochester Medical Center
Author Profile
Sunil Prasad
University of Rochester Medical Center
Author Profile
Arman Kilic
Medical University of South Carolina
Author Profile


Background: This study investigates the use of modern machine learning (ML) techniques to improve prediction of survival after orthotopic heart transplantation (OHT). Methods: Retrospective study of adult patients undergoing primary, isolated OHT between 2000-2019 as identified in the United Network for Organ Sharing (UNOS) registry. The primary outcome was one-year post-transplant survival. Patients were randomly divided into training (80%) and validation (20%) sets. Dimensionality reduction and data re-sampling were employed during training. Multiple machine learning algorithms were combined into a final ensemble ML model. Discriminatory capability was assessed using area under receiver-operating-characteristic curve (AUROC), net reclassification index (NRI), and decision curve analysis (DCA). Results: A total of 33,657 OHT patients were evaluated. One-year mortality was 11% (n=3,738). In the validation cohort, the AUROC of singular logistic regression was 0.649 (95% CI 0.628-0.670) compared to 0.691 (95% CI 0.671-0.711) with random forest, 0.691 (95% CI 0.671-0.712) with deep neural network, and 0.653 (95% CI 0.632-0.674) with Adaboost. A final ensemble ML model was created that demonstrated the greatest improvement in AUROC: 0.764 (95% CI 0.745-0.782) (p<0.001). The ensemble ML model improved predictive performance by 72.9% ±3.8% (p<0.001) as assessed by NRI compared to logistic regression. DCA showed the final ensemble method improved risk prediction across the entire spectrum of predicted risk as compared to all other models (p<0.001). Conclusions: Modern ML techniques can improve risk prediction in OHT compared to traditional approaches. This may have important implications in patient selection, programmatic evaluation, allocation policy, and patient counseling and prognostication.
26 Apr 2021Submitted to Journal of Cardiac Surgery
27 Apr 2021Submission Checks Completed
27 Apr 2021Assigned to Editor
28 Apr 2021Reviewer(s) Assigned
23 Jun 2021Review(s) Completed, Editorial Evaluation Pending
23 Jun 2021Editorial Decision: Revise Minor
30 Jun 20211st Revision Received
02 Jul 2021Submission Checks Completed
02 Jul 2021Assigned to Editor
07 Jul 2021Reviewer(s) Assigned
16 Jul 2021Review(s) Completed, Editorial Evaluation Pending
16 Jul 2021Editorial Decision: Accept