Prediction of Acute Kidney Injury after Liver Transplantation: Machine Learning Approaches vs. Logistic Regression Model

Abstract

Acute kidney injury (AKI) after liver transplantation has been reported to be associated with increased mortality. Recently, machine learning approaches were reported to have better predictive ability than the classic statistical analysis. We compared the performance of machine learning approaches with that of logistic regression analysis to predict AKI after liver transplantation. We reviewed 1211 patients and preoperative and intraoperative anesthesia and surgery-related variables were obtained. The primary outcome was postoperative AKI defined by acute kidney injury network criteria. The following machine learning techniques were used: decision tree, random forest, gradient boosting machine, support vector machine, naïve Bayes, multilayer perceptron, and deep belief networks. These techniques were compared with logistic regression analysis regarding the area under the receiver-operating characteristic curve (AUROC). AKI developed in 365 patients (30.1%). The performance in terms of AUROC was best in gradient boosting machine among all analyses to predict AKI of all stages (0.90, 95% confidence interval [CI] 0.86–0.93) or stage 2 or 3 AKI. The AUROC of logistic regression analysis was 0.61 (95% CI 0.56–0.66). Decision tree and random forest techniques showed moderate performance (AUROC 0.86 and 0.85, respectively). The AUROC of support the vector machine, naïve Bayes, neural network, and deep belief network was smaller than that of the other models. In our comparison of seven machine learning approaches with logistic regression analysis, the gradient boosting machine showed the best performance with the highest AUROC. An internet-based risk estimator was developed based on our model of gradient boosting. However, prospective studies are required to validate our results.

Application of Various Surgical Techniques in Orthotopic Liver Transplantation: a 10-year Experience at a Single Center

“…AKI was another prevalent complication, and its incidence was 4.5% in our study. The incidence of AKI in previous reports ranged from 0-16.7% 37,38 . AKI was mainly caused by hemodynamic instability, IVC blockade, and severe intraoperative blood loss.…”

Applying Machine Learning in Liver Disease and Transplantation: A Comprehensive Review

“…ML tools were used on preoperative and intraoperative anesthesia and surgery-related variables to predict postoperative AKI, which has been associated with increased mortality. (59) Gradient boosting machine performed best among all ML methods to predict AKI of all stages (AUC, 0.90; 95% CI, 0.86-0.93), as compared to AUC for standard logistic regression analysis of 0.61 (95% CI, 0.56-0.66). Posttransplant diabetes mellitus (PTDM) is a major complication associated with a 2-fold higher risk of cardiovascular events, graft loss, and infections in the long term.…”

New trends in the study of post-transplant acute kidney injury after liver transplantation

“…Хотя уровень креатинина в сыворотке крови пока остается «золотым стандартом» оценки функции почек, этот тест имеет низкую специфичность и чувствительность для ранней диагностики ОПП [63]. Поэтому, а также в связи с тем, что современная терапия ОПП оставляет желать лучшего, в настоящее время внимание исследователей акцентируется не на методах лечения, а на профилактике и раннем выявлении ОПП у тяжелых пациентов, в том числе и у больных после ТП [64,65]. Новые биомаркеры для прогнозирования или ранней диагностики ОПП потенциально могут повысить возможности лечения этого осложнения у больных после ТП [66].…”