Development and Validation of a Hybrid Machine Learning Model to Predict Lung Transplant Outcomes

Can an interpretable hybrid machine learning model predict 1-, 5-, and 10-year risk of death or retransplant after a lung transplant?In this prognostic study using a UNOS-OPTN cohort of 51 933 adults undergoing a first lung transplant, a 9-variable AutoScore-Survival model showed moderate discrimination (integrated area under the curve, 0.61; C-index, 0.64), good calibration, and net clinical benefit on decision-curve analysis in the testing cohort across time horizons.These findings suggest that this interpretable, web-accessible risk calculator may support individualized posttransplant risk stratification, patient counseling, and shared decision-making in clinical practice.

Corresponding Authors: Gaurav Sharma, PhD, MBA (gaurav.sharma@utsouthwestern.edu), and Michael E. Jessen, MD (michael.jessen@utsouthwestern.edu), Department of Cardiovascular and Thoracic Surgery, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390.

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.