AUTHOR=Pontes Balanza Beatriz , Castillo Tuñón Juan M. , Mateos García Daniel , Padillo Ruiz Javier , Riquelme Santos José C. , Álamo Martinez José M. , Bernal Bellido Carmen , Suarez Artacho Gonzalo , Cepeda Franco Carmen , Gómez Bravo Miguel A. , Marín Gómez Luis M. 

TITLE=Development of a liver graft assessment expert machine-learning system: when the artificial intelligence helps liver transplant surgeons

JOURNAL=Frontiers in Surgery

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/surgery/articles/10.3389/fsurg.2023.1048451

DOI=10.3389/fsurg.2023.1048451

ISSN=2296-875X

ABSTRACT=ABSTRACT

BACKGROUND.
The complex liver graft assessment process is one point for improvement in Liver Transplantation. This paper’s main objective is to develop a tool that supports the surgeon responsible for liver donation in the decision-making process to accept a graft or not using the initial variables available to it.

MATERIAL AND METHODS.
A donor brain death liver graft sample candidate for liver transplantation was studied. All of them were evaluated "in situ" for transplantation, those discarded after "in situ" evaluation were considered no transplantable liver grafts, while those grafts transplanted after "in situ" evaluation were considered transplantable liver grafts. First, a single-center, retrospective and cohort study identifying risk factors associated with no transplantable group, was performed. Later, a prediction model decision support system based on machine learning, and using a tree ensemble boosting classifier, capable of helping to decide whether to accept or decline a donor liver graft was developed.

RESULTS.
A total of 350 liver grafts evaluated for liver transplantation were studied. Steatosis was the most frequent reason for classifying grafts as no transplantable and the main risk factors identified in the univariant study were age, dyslipidemia, personal medical history, personal surgical history, Bilirubinemia, and the result of previous liver ultrasound (p<0.05).
When studying the developed model, we observe that the best performance reordering in terms of accuracy corresponds to 76.29% with an area under the curve of 0.79. Furthermore, the model provides a classification together with a confidence index of reliability, for most cases in our data, with the probability of success in the prediction being above 0.85.

CONCLUSION.
The tool presented in this paper obtains a high accuracy in predicting whether a liver graft will be transplanted or deemed non-transplantable based on the initial variables assigned to it. 
The inherent capacity for improvement in the system causes the rate of correct predictions to increase as new data is entered. Therefore, we believe it is a tool that can help optimize the graft pool for liver transplantation.