Dataset Information

Machine Learning Prediction of Liver Allograft Utilization From Deceased Organ Donors Using the National Donor Management Goals Registry.

ABSTRACT: Early prediction of whether a liver allograft will be utilized for transplantation may allow better resource deployment during donor management and improve organ allocation. The national donor management goals (DMG) registry contains critical care data collected during donor management. We developed a machine learning model to predict transplantation of a liver graft based on data from the DMG registry.

Methods

Several machine learning classifiers were trained to predict transplantation of a liver graft. We utilized 127 variables available in the DMG dataset. We included data from potential deceased organ donors between April 2012 and January 2019. The outcome was defined as liver recovery for transplantation in the operating room. The prediction was made based on data available 12-18 h after the time of authorization for transplantation. The data were randomly separated into training (60%), validation (20%), and test sets (20%). We compared the performance of our models to the Liver Discard Risk Index.

Results

Of 13 629 donors in the dataset, 9255 (68%) livers were recovered and transplanted, 1519 recovered but used for research or discarded, 2855 were not recovered. The optimized gradient boosting machine classifier achieved an area under the curve of the receiver operator characteristic of 0.84 on the test set, outperforming all other classifiers.

Conclusions

This model predicts successful liver recovery for transplantation in the operating room, using data available early during donor management. It performs favorably when compared to existing models. It may provide real-time decision support during organ donor management and transplant logistics.

SUBMITTER: Bishara AM

PROVIDER: S-EPMC8478404 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:INTRODUCTION:Research on the management of deceased organ donors aims to improve the number and quality of transplants and recipient outcomes. In Canada, this research is challenged by regionalisation of donation services within provinces and the geographical, clinical and administrative separation of donation from transplantation services. This study aims to build a national platform for future clinical trials in donor management. Objectives are to engage collaborators at donation hospitals and organ donation organisations (ODOs) across Canada, describe current practices, evaluate the effectiveness of donation-specific interventions and assess the feasibility of future clinical trials. METHODS AND ANALYSIS:This ongoing prospective observational study of the medical management of deceased organ donors will enrol more than 650 consented potential donors from adult intensive care units at 33 hospital sites across Canada, each participating for 12 months. ODOs ensure enrolment of consecutive eligible participants. Research staff record detailed data about participants, therapies, organ assessments, death declaration procedures and adverse clinical exposures from the time of donation consent to organ recovery. ODOs provide reasons that organs are declined, dates and places of transplantation, and recipient age and sex.Descriptive analyses will summarise current practices. Effectiveness analyses will examine donation-specific interventions with respect to the number of transplants, using multilevel regression models to account for clustering by donor, hospitals and ODOs. Feasibility analyses will focus on acceptance of the research consent model; participation of academic and community hospitals as well as ODOs; and accessibility of recipient data. ETHICS AND DISSEMINATION:This study uses a waiver of research consent. Hospitals will receive reports on local practices benchmarked to (1) national practices and (2) national donor management guidelines. We will report findings to donation and transplant collaborators (ie, clinicians, researchers, ODOs) and publish in peer-reviewed journals. TRIAL REGISTRATION NUMBER:NCT03114436.