Department of Pediatric Nephrology, Faculty of Medicine, Akdeniz University, Antalya, Turkey.
Department of Computer Engineering, Faculty of Engineering, Akdeniz University, Antalya, Turkey.
Pediatr Nephrol. 2025 Jan;40(1):203-211. doi: 10.1007/s00467-024-06484-5. Epub 2024 Aug 16.
Identification of factors that affect graft survival in kidney transplantation can increase graft survival and reduce mortality. Artificial intelligence modelling enables impartial evaluation of clinician bias. This study aimed to examine factors that affect the survival of grafts in paediatric kidney transplantation through the use of machine learning.
A retrospective review was conducted on records of paediatric patients who underwent kidney transplantation between 1994 and 2021 and had post-transplant follow-up > 12 months. The nearest neighbour method was used to impute missing fields from a total of 48 variables in the dataset. Models including Naive Bayes, logistic regression, support vector machine (SVM), multi-layer perceptron, and XGBoost were trained to predict graft survival. The study used 80% of the patients for training and the remaining 20% for testing. Modelling success was evaluated based on accuracy and F1 score metrics.
The study analysed 465 kidney transplant recipients. Of these, 56.7% were male. The mean age at transplantation was 12.08 ± 5.01 years. Of the kidney transplants, 73.1% (n = 339) were from living donors, 34.5% (n = 160) were pre-emptive transplants, and 2.2% (n = 10) were second-time transplants. The machine learning model identified several features associated with graft survival, including antibody-mediated rejection (+ 0.7), acute cellular rejection (+ 0.66), eGFR at 3 years (+ 0.43), eGFR at 5 years (+ 0.34), pre-transplant peritoneal dialysis (+ 0.2), and cadaveric donor (+ 0.2). The successes of the logistic regression and SVM models were similar. The F1 score was 91.9%, and accuracy was 96.5%.
Machine learning can be used to identify factors that affect graft survival in kidney transplant recipients. By expanding similar studies, risk maps can be created prior to transplantation.
识别影响肾移植移植物存活的因素可以提高移植物存活率并降低死亡率。人工智能建模可以公正地评估临床医生的偏见。本研究旨在通过机器学习来研究影响儿科肾移植移植物存活的因素。
对 1994 年至 2021 年间接受肾移植并进行了 12 个月以上移植后随访的儿科患者的记录进行了回顾性分析。使用最近邻法从数据集中总共 48 个变量中推断出缺失字段。使用朴素贝叶斯、逻辑回归、支持向量机（SVM）、多层感知机和 XGBoost 等模型来预测移植物存活率。该研究使用 80%的患者进行训练，其余 20%用于测试。基于准确性和 F1 评分指标来评估模型的成功。
本研究分析了 465 例肾移植受者。其中，56.7%为男性。移植时的平均年龄为 12.08±5.01 岁。在肾移植中，73.1%（n=339）来自活体供者，34.5%（n=160）为预先移植，2.2%（n=10）为再次移植。机器学习模型确定了与移植物存活相关的几个特征，包括抗体介导的排斥反应（+0.7）、急性细胞排斥反应（+0.66）、3 年时的 eGFR（+0.43）、5 年时的 eGFR（+0.34）、移植前的腹膜透析（+0.2）和尸体供者（+0.2）。逻辑回归和 SVM 模型的成功率相似。F1 评分为 91.9%，准确性为 96.5%。
机器学习可用于识别影响肾移植受者移植物存活的因素。通过扩展类似的研究，可以在移植前创建风险图。
