A Machine Learning Prediction Model for Immediate Graft Function After Deceased Donor Kidney Transplantation

Abstract

Background. After kidney transplantation (KTx), the graft can evolve from excellent immediate graft function (IGF) to total absence of function requiring dialysis. Recipients with IGF do not seem to benefit from using machine perfusion, an expensive procedure, in the long term when compared with cold storage. This study proposes to develop a prediction model for IGF in KTx deceased donor patients using machine learning algorithms. Methods. Unsensitized recipients who received their first KTx deceased donor between January 1, 2010, and December 31, 2019, were classified according to the conduct of renal function after transplantation. Variables related to the donor, recipient, kidney preservation, and immunology were used. The patients were randomly divided into 2 groups: 70% were assigned to the training and 30% to the test group. Popular machine learning algorithms were used: eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine, Gradient Boosting classifier, Logistic Regression, CatBoost classifier, AdaBoost classifier, and Random Forest classifier. Comparative performance analysis on the test dataset was performed using the results of the AUC values, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score. Results. Of the 859 patients, 21.7% (n = 186) had IGF. The best predictive performance resulted from the eXtreme Gradient Boosting model (AUC, 0.78; 95% CI, 0.71–0.84; sensitivity, 0.64; specificity, 0.78). Five variables with the highest predictive value were identified. Conclusions. Our results indicated the possibility of creating a model for the prediction of IGF, enhancing the selection of patients who would benefit from an expensive treatment, as in the case of machine perfusion preservation.

Machine learning algorithms for the prediction of adverse prognosis in patients undergoing peritoneal dialysis

“…Based on the GBDT framework, which has fewer parameters, CatBoost supports categorical variables with high ACC and can efficiently and reasonably process t-algorithms. CatBoost has been extensively studied in the prediction of skin sensitisation [28], depression occurrence [29], pregnancy diabetes management [30], and transplanted kidney function [8], and it exhibits good predictive performance. Owing to numerous factors that affect an adverse PD prognosis and considering the clinical applications, we reconstructed a compression model by extracting 20 key features ranked by the SHAP values.…”

“…An ML algorithm was used to evaluate the accuracy (ACC) of predicting cardiovascular events in asymptomatic populations by comparing random survival forests (an ML technique) with standard cardiovascular risk scores [7]. The prognostic factors affecting kidney transplant surgery cover multiple fields of surgery, immunology, epidemiology, and physiology; the large amount of data that is generated can precisely leverage the computational power of ML [8]. However, studies using ML algorithms for PD-related prognosis are limited.…”

A study of the visualization of artificial intelligence applications in chronic kidney disease in the literature over the last 20 years

“…In the management of CKD-mineral and bone disorder (CKD-MBD) disease, the use of quantitative systems pharmacology (QSP) models combined with reinforcement learning (RL) has been shown to be fast and effective in achieving accurate treatment [34] . Similarly, ML models have been able to predict the occurrence of possible outcomes after renal transplantation and to identify sets of genes associated with graft tolerance to guide immunotherapy by analyzing results from large amounts of data [35,36] .…”

Revolutionizing Kidney Transplantation: Connecting Machine Learning and Artificial Intelligence with Next-Generation Healthcare—From Algorithms to Allografts

“…Konieczny et al [81] used random forest classifiers and a multi-layer perceptron to predict delayed graft function, achieving an accuracy of 0.94 and an AUC of 0.92. Meanwhile, Quinino et al [82] developed a XGBoost model to predict immediate graft function (IGF), which showed good predictive performance.…”