An organ allocation system for liver transplantation based on ordinal regression

• The problem of constructing an organ allocation model via machine learning techniques is assessed.
• The combination of donor, recipient, and surgery characteristics helps the prediction of graft survival after transplantation.
• An ordinal classifier has been proved to perform well for the 4-category classification problem assessed.
• An extended supranational experimental design for liver transplantation allocation could be feasible considering more countries.

Liver transplantation is nowadays a widely-accepted treatment for patients who present a terminal liver disease. Nevertheless, transplantation is greatly hampered by the un-availability of suitable liver donors; several methods have been developed and applied to find a better system to prioritize recipients on the waiting list, although most of them only consider donor or recipient characteristics (but not both). This paper proposes a novel donor–recipient liver allocation system constructed to predict graft survival after transplantation by means of a dataset comprised of donor–recipient pairs from different centres (seven Spanish and one UK hospitals). The best model obtained is used in conjunction with the Model for End-stage Liver Disease score (MELD), one of the current assignation methodology most used globally. This problem is assessed using the ordinal regression learning paradigm due to the natural ordering in the classes of the problem, via a cascade binary decomposition methodology and the Support Vector Machine methodology. The methodology proposed has shown competitiveness in all the metrics selected, when compared to other machine learning techniques and efficiently complements the MELD score based on the principles of efficiency and equity. Finally, a simulation of the proposal is included, in order to visualize its performance in realistic situations. This simulation has shown that there are some determining factors in the characterization of the survival time after transplantation (concerning both donors and recipients) and that the joint use of these sets of information could be, in fact, more useful and beneficial for the survival principle. Nonetheless, the results obtained indicate the true complexity of the problem dealt within this study and the fact that other characteristics that have not been included in the dataset may be of importance for the characterization of the dependent variable (survival time after transplantation), thus starting a promising line of future work.

Figure optionsDownload as PowerPoint slide