Data for Decision tree and random forest models for outcome prediction in antibody incompatible kidney transplantation

We explored thepotential of Decision Tree (DT) and Random Forest (RF) classification models, in the context of smalldataset of 80 samples, for outcome prediction in high-risk kidney transplantation. The DT and RF modelsidentified the key risk factors associated with acute rejection: the levels of the donor specific IgG anti-bodies, the levels of IgG4 subclass and the number of human leucocyte antigen mismatches betweenthe donor and recipient.

Furthermore, the DT model determined dangerous levels of donor-specific IgGsubclass antibodies, thus demonstrating the potential of discovering new properties in the data whentraditional statistical tools are unable to capture them. The DT and RF classifiers developed in this workpredicted early transplant rejection with accuracy of 85%, thus offering an accurate decision supporttool for doctors tasked with predicting outcomes of kidney transplantation in advance of the clinicalintervention.<br><br>Due to the ethically sensitive nature of the research and the level of ethical approval which is in place, responsible individuals from regulatory authorities or from the NHS Trust who want access the data could apply directly to the Head of Research, Development & Innovation Team at the University Hospitals Coventry & Warwickshire (NHS Trust).