Abstract

Machine learning is used to develop predictive models to diagnose different diseases, particularly kidney transplant survival prediction. The paper used the collected dataset of patients’ individual parameters to predict the critical risk factors associated with early graft rejection. Our study shows the high pairwise correlation between a massive subset of the parameters listed in the dataset. Hence the proper feature selection is needed to increase the quality of a prediction model. Several methods are used for feature selection, and results are summarized using hard voting. Modeling the onset of critical events for the elements of a particular set is made based on the Kapplan-Meier method. Four novel ensembles of machine learning models are built on selected features for the classification task. Proposed stacking allows obtaining an accuracy, sensitivity, and specifity of more than 0.9. Further research will include the development of a two-stage predictor.

Highlights

  • Organ transplantation is one of the most outstanding achievements of modern medicine.The use of organ transplants today allows the treatment of many patients who until recently could hope, at best, to continue their painful and limited existence.The urgency of this problem lies in the fact that in Ukraine, legal issues are not yet fully resolved, and there is a lack of donor bodies [1]

  • Outpatient case histories of 164 patients who received human leukocyte antigen (HLA)-compatible renal allografts between 1992 and 2020 were retrospectively analyzed: 152 patients underwent transplantation for the first time—64 (42.1%) women and 88 (57.9%) male patients with a mean age of 32.6 ± 8.7 years at the time of transplantation, and patients (5 (41.7%) women and 7 (58.3%) men), who received a second transplant kidney, who were on an outpatient basis in the Department Hospital Nephrology and Dialysis of the Lviv Regional Clinical Hospital (LRCH)

  • This paper presents feature selection and kidney transplant survival for a month after transplantation prediction using Kapplan-Meier method and ensemble classifier

Read more

Summary

Introduction

Organ transplantation is one of the most outstanding achievements of modern medicine.The use of organ transplants today allows the treatment of many patients who until recently could hope, at best, to continue their painful and limited existence.The urgency of this problem lies in the fact that in Ukraine, legal issues are not yet fully resolved, and there is a lack of donor bodies [1]. Organ transplantation is one of the most outstanding achievements of modern medicine. The use of organ transplants today allows the treatment of many patients who until recently could hope, at best, to continue their painful and limited existence. The urgency of this problem lies in the fact that in Ukraine, legal issues are not yet fully resolved, and there is a lack of donor bodies [1]. In addition to the lack of organs for transplantation, one of the essential problems of Ukrainian transplantology is selecting a donor-recipient pair, which avoids episodes of acute and chronic rejection of the donor organ by the recipient’s immune system [2]

Objectives
Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call