Improving Pediatric Donor Heart Utilization with Predictive Analytics

PROJECT SUMMARY/ABSTRACT In the United States, approximately 14% of children with end-stage heart failure or inoperable congenital heart defects die while awaiting heart transplants, yet nearly 40% of donated hearts remain unutilized. When a donor heart becomes available, clinicians have minutes to sort through hundreds of donor and candidate variables to determine whether the organ is a good fit for their patient. However, the nuanced impact of these variables on patient outcomes remains poorly understood, and no data-driven guidelines or evidence- based tools exist to support clinician decision-making. Consequentially, the prevailing uncertainty and associated risk aversion lead to the unnecessary rejection of many suitable hearts. We hypothesize that the integration of evidence-based tools can increase clinicians’ confidence in these critical decisions, thereby optimizing pediatric donor heart utilization and reducing waitlist mortality without negatively affecting post- transplant survival. To answer this need, we are developing the first predictive models to assess, at the time of offer, the given candidate’s post-transplant survival if they received the offered heart; and if refused, projected time to next offer and the associated waitlist survival (Aim 1). To do this, we will use machine learning technology to analyze all 30,000 US-based pediatric heart offers made between 2010–2020, the most complete representation of national pediatric donor information ever compiled; we will validate the models using external data from 2020-2022. We will collaborate with the United Network of Organ Sharing (UNOS), the national organ transplant system, to customize their established simulation platform (Aim 2) to actively run and display Aim 1’s models as well as display the avalanche of data associated with a typical donor offer in a user-friendly, individualizable interface produced from an iterative design process using feedback from a team of experienced pediatric transplant cardiologists (Aim 3). We will measure the success of our models and improved interface by sending simulated donor offers to a large team of pediatric transplant cardiologists from around the country. These realistic offers will use deidentified historic data variably augmented with model outputs and/or the customizable visualizations, allowing us to assess the impact of these interventions on donor acceptance practices. If successful, UNOS will integrate our models and dashboard into its online platform for organ matching, where the technology will support clinical decision-making at the point of care. These aims will support our long-term goal of producing a straightforward, real-time assessment tool for heart transplant decisions. This technology could inform standardized and efficient guidelines for donor heart acceptance, thereby saving lives and reducing the unnecessary refusal of donor hearts. The end result could demonstrate a proof-of-concept for predictive modeling research in transplant medicine, potentially revolutionizing the field of donor acceptance practices across all solid organ systems.