Development and Validation of an Optimized Prediction of Mortality for Candidates Awaiting Liver Transplantation

Dimitris Bertsimas; Jerry Kung; Nikolaos Trichakis; Yuchen Wang; Ryutaro Hirose; Parsia A. Vagefi

Disclosures

American Journal of Transplantation. 2019;19(4):1109-1118. 

In This Article

Abstract and Introduction

Abstract

Since 2002, the Model for End-Stage Liver Disease (MELD) has been used to rank liver transplant candidates. However, despite numerous revisions, MELD allocation still does not allow for equitable access to all waitlisted candidates. An optimized prediction of mortality (OPOM) was developed (http://www.opom.online) utilizing machine-learning optimal classification tree models trained to predict a candidate's 3-month waitlist mortality or removal utilizing the Standard Transplant Analysis and Research (STAR) dataset. The Liver Simulated Allocation Model (LSAM) was then used to compare OPOM to MELD-based allocation. Out-of-sample area under the curve (AUC) was also calculated for candidate groups of increasing disease severity. OPOM allocation, when compared to MELD, reduced mortality on average by 417.96 (406.8-428.4) deaths every year in LSAM analysis. Improved survival was noted across all candidate demographics, diagnoses, and geographic regions. OPOM delivered a substantially higher AUC across all disease severity groups. OPOM more accurately and objectively prioritizes candidates for liver transplantation based on disease severity, allowing for more equitable allocation of livers with a resultant significant number of additional lives saved every year. These data demonstrate the potential of machine learning technology to help guide clinical practice, and potentially guide national policy.

Introduction

The successful clinical application of liver transplantation has generated a discrepancy between supply and demand, thereby generating a persistent insufficient organ supply that results in thousands of candidate deaths every year while candidates await liver transplantation. Given the scarcity of this resource, one of the most crucial challenges in liver transplantation involves accurately prioritizing a waitlisted candidate's likelihood of death within the near future, so that the limited supply of donated livers can be allocated to maximize the benefit from transplantation.

Since 2002, liver allocation has depended on the Model for End-Stage Liver Disease (MELD) score to rank disease severity and, consequently, priority for receiving a liver transplant.[1] Certain patient populations, however, are at risk of death or of becoming too sick and unsuitable for transplantation based on disease progression that is not captured in their lab-based MELD score calculation. To allow them to contend for liver offers, these candidate populations have been granted "artificial" points (MELD exception points). Although overall the MELD score has allowed for a more objective ranking of candidates awaiting liver transplantation, compared to the pre-MELD era, the process of MELD exception point granting has emerged as a significant weakness in the allocation process, leading to inequitable and undesirable outcomes.[2] In particular, the arbitrary MELD score exception points policy has overly prioritized the subpopulation of liver transplant candidates with hepatocellular carcinoma (HCC).[3] Indeed, since the adoption of the MELD score, there have been multiple policy revisions to reduce the amount of exception points for HCC candidates to more accurately reflect this population's risk of waitlist removal from death or tumor progression. Notwithstanding these revisions, there remains a higher risk of waitlist death/removal for candidates without exception points, when compared to those candidates with exception points.

We sought to utilize a state-of-the-art machine-learning method—termed optimal classification trees (OCTs)—to generate a more accurate prediction of a liver candidate's 3-month waitlist mortality or removal, that would in-return allow for a more appropriate prioritization of candidates awaiting liver transplantation. The following prediction problem was posed: What is the probability that a patient will either die or become unsuitable for liver transplantation within 3 months, given his or her individual characteristics?

Comments

3090D553-9492-4563-8681-AD288FA52ACE

processing....