Date of Award
Honors College Thesis
Chaoyang Zhang, Ph.D.
For years, doctors have utilized the Model for End-stage Liver Disease (MELD) score to aid in the allocation of organs for liver transplants (LT). A major issue with using the MELD score to allocate organs for transplantation is that the MELD score does not accurately predict post-transplant survival. This research project aims to investigate the use of machine learning (ML) methods to predict LT survival using the newer Scientific Registry of Transplant Recipients (SRTR) dataset. For this project, death and nonfatal graft failure were treated equally as both cases result in a loss of a donated organ. The ML algorithms used in this project were provided by both the Weka and Orange software packages. Initial trials investigated a binary classification of patients based on whether they survived for three years post-transplant and primarily utilized a random forest algorithm. Later trials moved to a multi-class classification using both random forest and other classifier algorithms. Initial results from the three-year binary classification seemed promising but performance metrics failed to improve with continued work. All multi-class trials performed similarly using various classifier algorithms. Unexpectedly, the class for 12-year survival showed a promising increase in its area under the receiver operating characteristic curve. The results of this project help to create a baseline for future ML studies utilizing the SRTR dataset and will hopefully spur further research into liver transplant survival prediction.
Copyright for this thesis is owned by the author. It may be freely accessed by all users. However, any reuse or reproduction not covered by the exceptions of the Fair Use or Educational Use clauses of U.S. Copyright Law or without permission of the copyright holder may be a violation of federal law. Contact the administrator if you have additional questions.
Revels, Brandon C., "A Machine Learning Method for Predicting Liver Transplant Survival Outcomes" (2020). Honors Theses. 747.