APPLICATION OF MACHINE LEARNING FOR EARLY PREDICTION OF ACUTE KIDNEY INJURY FOLLOWING LIVER TRANSPLANTATION
Main Article Content
Abstract
Objectives: To evaluate the performance of a Random Forest machine-learning model in the early prediction of acute kidney injury (AKI) following liver transplantation. Methods: A single-center, retrospective, descriptive study was conducted on 205 liver transplant recipients at 108 Military Central Hospital from 2021 to 2025. Data were divided into a training set (70%) and a validation set (30%). The Random Forest model was developed using clinical variables associated with AKI risk and evaluated based on the area under the curve (AUC), sensitivity, specificity, Brier score, and calibration. Results: The model achieved an AUC of 0.752 with high specificity (0.804). MELD (model for end-stage liver disease) score, intraoperative transfusion volume, warm ischemia time, and post-operative 6-hour lactate levels were identified as the most important predictors of AKI. Risk stratification based on the model correlated well with actual AKI incidence and ICU length of stay. Conclusion: Random Forest model demonstrated moderate predictive performance and is valuable for early identification of high-risk AKI groups after liver transplantation, thereby supporting timely clinical decision-making.
Keywords
Machine learning, Acute kidney injury, Liver transplantation
Article Details
References
2. He ZL, Zhou JB, Liu ZK, et al. Application of machine learning models for predicting acute kidney injury following donation after cardiac death liver transplantation. Hepatobiliary Pancreat Dis Int. Jun 2021; 20(3):222-231. DOI: 10.1016/j.hbpd.2021.02.001.
3. Lee HC, Yoon SB, Yang SM, et al. Prediction of acute kidney injury after liver transplantation: Machine learning approaches vs. logistic regression model. Journal of Clinical Medicine. Nov 8 2018; 7(11). DOI: 10.3390/jcm7110428.
4. Zhang Y, Yang D, Liu Z, et al. An explainable supervised machine learning predictor of acute kidney injury after adult deceased donor liver transplantation. J Transl Med. Jul 28 2021; 19(1):321. DOI: 10.1186/s12967-021-02990-4.
5. Khwaja A. KDIGO clinical practice guidelines for acute kidney injury. Nephron Clin Pract. 2012; 120(4):c179-84. DOI: 10.1159/000339789.
6. Zongyi Y, Baifeng L, Funian Z, Hao L, Xin W. Risk factors of acute kidney injury after orthotopic liver transplantation in China. Scientific reports. 2017/01/30 2017; 7(1):41555. DOI: 10.1038/srep41555.
7. Romano TG, Schmidtbauer I, Silva FM, Pompilio CE, D'Albuquerque LA, Macedo E. Role of MELD score and serum creatinine as prognostic tools for the development of acute kidney injury after liver transplantation. PLoS One. 2013; 8(5): e64089. DOI: 10.1371/journal.pone.0064089.
8. Barreto AGC, Daher EF, Junior GBS, et al. Risk factors for acute kidney injury and 30-day mortality after liver transplantation. Annals of Hepatology. 2015/09/01/ 2015; 14(5):688-694. DOI: https://doi.org/10.1016/S1665-2681(19)30763-X.
9. Chiofolo C, Chbat N, Ghosh E, Eshelman L, Kashani K. Automated continuous acute kidney injury prediction and surveillance: A Random Forest model. Mayo Clin Proc. May 2019; 94(5):783-792. DOI: 10.1016/j.mayocp.2019.02.009.
10. Song Z, Yang Z, Hou M, Shi X. Machine learning in predicting cardiac surgery-associated acute kidney injury: A systematic review and meta-analysis. Systematic Review. Frontiers in Cardiovascular Medicine. 2022-September-15 2022; 2022; 9. DOI: 10.3389/fcvm.2022.951881.