Abstract
Purpose
To develop and validate a machine learning (ML)-based prediction model for acute kidney injury (AKI) in patients with liver cirrhosis.
Methods
Data on liver cirrhosis patients were extracted from the Medical Information Mart for Intensive Care III (MIMIC-III) and MIMIC-IV databases in this retrospective cohort study. ML algorithms, including random forest (RF), extreme gradient boosting (XGB), light gradient boosting machine (LGBM), and gradient boosting decision tree (GBDT) were applied to construct prediction models. Predictors were screened via univariate logistic regression, and then the models were developed with all data of the included patients. A bootstrap resampling method was adopted to validate the models. The predictive abilities of our final model were compared with those of the sequential organ failure assessment score (SOFA), simplified acute physiology score II (SAPS II), Model for End-stage Liver Disease (MELD), and MELD Na.
Results
This study included 950 patients, of which 429 (45.16%) had AKI. Mechanical ventilation, vasopressor, international normalized ratio (INR), bilirubin, Charlson comorbidity index (CCI), prothrombin time (PT), estimated glomerular filtration rate (EGFR), partial thromboplastin time (PTT), and heart rate served as predictors. In the derivation set, the developed RF [area under curve (AUC) = 0.747], XGB (AUC = 0.832), LGBM (AUC = 0.785), and GBDT (AUC = 0.811) models exhibited significantly greater predictive performance than the logistic regression model (AUC = 0.699) (all P < 0.05). Among the ML-based models, the XGB model had the greatest AUC. In internal validation, the predictive capacity of the XGB model (AUC = 0.833) was significantly superior to that of the logistic regression model (AUC = 0.701) (P = 0.045). Hence, the XGB model was selected as the final model for AKI prediction. In contrast to the XGB model (AUC = 0.832), the SOFA (AUC = 0.609), MELD (AUC = 0.690), MELD Na (AUC = 0.690), and SAPS II (AUC = 0.641) had significantly lower predictive abilities in the derivation set (all P < 0.001). The XGB model was internally validated to have an AUC of 0.833, which was significantly higher than the SOFA (AUC = 0.609), MELD (AUC = 0.690), MELD Na (AUC = 0.688), and SAPS II (AUC = 0.641) (all P < 0.05).
Conclusion
The XGB model had a better performance than the logistic regression model, SOFA, MELD, MELD Na, and SAPS II in AKI prediction for cirrhosis patients, which may help identify patients at a risk of AKI, and then provide timely interventions.
Similar content being viewed by others
Data availability
The datasets generated and/or analyzed during the current study are available in the MIMIC database (https://mimic.mit.edu/docs/about/).
References
Gonsalez SR, Cortês AL, Silva RCD, Lowe J, Prieto MC, Silva Lara LD (2019) Acute kidney injury overview: from basic findings to new prevention and therapy strategies. Pharmacol Ther 200:1–12. https://doi.org/10.1016/j.pharmthera.2019.04.001
Realista S (2022) Acute kidney injury in the inpatient and outpatient setting. Crit Care Nurs Clin North Am 34(4):431–441. https://doi.org/10.1016/j.cnc.2022.08.004
Chancharoenthana W, Leelahavanichkul A (2019) Acute kidney injury spectrum in patients with chronic liver disease: Where do we stand? World J Gastroenterol 25(28):3684–3703. https://doi.org/10.3748/wjg.v25.i28.3684
Tariq R, Hadi Y, Chahal K, Reddy S, Salameh H, Singal AK (2020) Incidence, mortality and predictors of acute kidney injury in patients with cirrhosis: a systematic review and meta-analysis. J Clin Transl Hepatol 8(2):135–142. https://doi.org/10.14218/jcth.2019.00060
Mercado MG, Smith DK, Guard EL (2019) Acute kidney injury: diagnosis and management. Am Fam Physician 100(11):687–694
Francoz C, Nadim MK, Durand F (2016) Kidney biomarkers in cirrhosis. J Hepatol 65(4):809–824. https://doi.org/10.1016/j.jhep.2016.05.025
Albert C, Haase M, Albert A, Zapf A, Braun-Dullaeus RC, Haase-Fielitz A (2021) Biomarker-guided risk assessment for acute kidney injury: time for clinical implementation? Ann Lab Med 41(1):1–15. https://doi.org/10.3343/alm.2021.41.1.1
Patidar KR, Xu C, Shamseddeen H, Cheng YW, Ghabril MS, Mukthinuthalapati V, Fricker ZP, Akinyeye S, Nephew LD, Desai AP, Anderson M, El-Achkar TM, Chalasani NP, Orman ES (2019) Development and validation of a model to predict acute kidney injury in hospitalized patients with cirrhosis. Clin Transl Gastroenterol 10(9):e00075. https://doi.org/10.14309/ctg.0000000000000075
Tseng PY, Chen YT, Wang CH, Chiu KM, Peng YS, Hsu SP, Chen KL, Yang CY, Lee OK (2020) Prediction of the development of acute kidney injury following cardiac surgery by machine learning. Critical Care (Lond, Engl) 24(1):478. https://doi.org/10.1186/s13054-020-03179-9
Peng X, Li L, Wang X, Zhang H (2022) A machine learning-based prediction model for acute kidney injury in patients with congestive heart failure. Front Cardiovasc Med 9:842873. https://doi.org/10.3389/fcvm.2022.842873
Yue S, Li S, Huang X, Liu J, Hou X, Zhao Y, Niu D, Wang Y, Tan W, Wu J (2022) Machine learning for the prediction of acute kidney injury in patients with sepsis. J Transl Med 20(1):215. https://doi.org/10.1186/s12967-022-03364-0
Hu C, Tan Q, Zhang Q, Li Y, Wang F, Zou X, Peng Z (2022) Application of interpretable machine learning for early prediction of prognosis in acute kidney injury. Comput Struct Biotechnol J 20:2861–2870. https://doi.org/10.1016/j.csbj.2022.06.003
Xu F, Zhang L, Wang Z, Han D, Li C, Zheng S, Yin H, Lyu J (2021) A new scoring system for predicting in-hospital death in patients having liver cirrhosis with esophageal varices. Front Med 8:678646. https://doi.org/10.3389/fmed.2021.678646
Mehta RL, Kellum JA, Shah SV, Molitoris BA, Ronco C, Warnock DG, Levin A, Network AKI (2007) Acute Kidney Injury Network: report of an initiative to improve outcomes in acute kidney injury. Critical Care (Lond, Engl) 11(2):R31. https://doi.org/10.1186/cc5713
Kamath PS, Wiesner RH, Malinchoc M, Kremers W, Therneau TM, Kosberg CL, D’Amico G, Dickson ER, Kim WR (2001) A model to predict survival in patients with end-stage liver disease. Hepatology (Baltimore, MD) 33(2):464–470. https://doi.org/10.1053/jhep.2001.22172
Dinh A, Miertschin S, Young A, Mohanty SD (2019) A data-driven approach to predicting diabetes and cardiovascular disease with machine learning. BMC Med Inform Decis Mak 19(1):211. https://doi.org/10.1186/s12911-019-0918-5
Guo CY, Chang KH (2022) A novel algorithm to estimate the significance level of a feature interaction using the extreme gradient boosting machine. Int J Environ Res Public Health 19(4):2338. https://doi.org/10.3390/ijerph19042338
Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. Knowl Discov Data Min 785–794
Qi M (2017) LightGBM: a highly efficient gradient boosting decision tree. Neural information processing systems. Curran Associates Inc, Red Hook
Ruf A, Dirchwolf M, Freeman RB (2022) From Child-Pugh to MELD score and beyond: taking a walk down memory lane. Ann Hepatol 27(1):100535. https://doi.org/10.1016/j.aohep.2021.100535
Song X, Liu X, Liu F, Wang C (2021) Comparison of machine learning and logistic regression models in predicting acute kidney injury: a systematic review and meta-analysis. Int J Med Inform 151:104484. https://doi.org/10.1016/j.ijmedinf.2021.104484
Zhang X, Chen S, Lai K, Chen Z, Wan J, Xu Y (2022) Machine learning for the prediction of acute kidney injury in critical care patients with acute cerebrovascular disease. Ren Fail 44(1):43–53. https://doi.org/10.1080/0886022x.2022.2036619
Qu C, Gao L, Yu XQ, Wei M, Fang GQ, He J, Cao LX, Ke L, Tong ZH, Li WQ (2020) Machine learning models of acute kidney injury prediction in acute pancreatitis patients. Gastroenterol Res Pract 2020:3431290. https://doi.org/10.1155/2020/3431290
Lee HC, Yoon HK, Nam K, Cho YJ, Kim TK, Kim WH, Bahk JH (2018) Derivation and validation of machine learning approaches to predict acute kidney injury after cardiac surgery. J Clin Med 7(10):322. https://doi.org/10.3390/jcm7100322
Zhou Y, Feng J, Mei S, Zhong H, Tang R, Xing S, Gao Y, Xu Q, He Z (2023) Machine learning models for predicting acute kidney injury in patients with sepsis-associated acute respiratory distress syndrome. Shock (Augusta, Ga.) 59(3):352–359. https://doi.org/10.1097/SHK.0000000000002065
Liu W, Zhang L, Xin Z, Zhang H, You L, Bai L, Zhou J, Ying B (2022) A promising preoperative prediction model for microvascular invasion in hepatocellular carcinoma based on an extreme gradient boosting algorithm. Front Oncol 12:852736. https://doi.org/10.3389/fonc.2022.852736
Xu Y, Yang X, Huang H, Peng C, Ge Y, Wu H, Wang J, Xiong G, Yi Y (2019) Extreme gradient boosting model has a better performance in predicting the risk of 90-day readmissions in patients with Ischaemic stroke. J Stroke Cerebrovasc Dis 28(12):104441. https://doi.org/10.1016/j.jstrokecerebrovasdis.2019.104441
Rahman MS, Chowdhury AH (2022) A data-driven eXtreme gradient boosting machine learning model to predict COVID-19 transmission with meteorological drivers. PLoS ONE 17(9):e0273319. https://doi.org/10.1371/journal.pone.0273319
Ogunleye A, Wang QG (2020) XGBoost model for chronic kidney disease diagnosis. IEEE/ACM Trans Comput Biol Bioinf 17(6):2131–2140. https://doi.org/10.1109/tcbb.2019.2911071
van den Akker JP, Egal M, Groeneveld AB (2013) Invasive mechanical ventilation as a risk factor for acute kidney injury in the critically ill: a systematic review and meta-analysis. Critical Care (Lond, Engl) 17(3):R98. https://doi.org/10.1186/cc12743
Varrier M, Ostermann M (2014) Novel risk factors for acute kidney injury. Curr Opin Nephrol Hypertens 23(6):560–569. https://doi.org/10.1097/mnh.0000000000000061
Kuiper JW, Vaschetto R, Della Corte F, Plötz FB, Groeneveld AB (2011) Bench-to-bedside review: Ventilation-induced renal injury through systemic mediator release–just theory or a causal relationship? Critical Care (Lond, Engl) 15(4):228. https://doi.org/10.1186/cc10282
Sato R, Luthe SK, Nasu M (2017) Blood pressure and acute kidney injury. Critical Care (Lond, Engl) 21(1):28. https://doi.org/10.1186/s13054-017-1611-7
Yue S, Li S, Huang X, Liu J, Hou X, Wang Y, Wu J (2022) Construction and validation of a risk prediction model for acute kidney injury in patients suffering from septic shock. Dis Markers 2022:9367873. https://doi.org/10.1155/2022/9367873
Wang S, Yang L, Zhou J, Yang J, Wang X, Chen X, Ji L (2022) A prediction model for acute kidney injury in adult patients with hemophagocytic lymphohistiocytosis. Front Immunol 13:987916. https://doi.org/10.3389/fimmu.2022.987916
Lal BB, Alam S, Sood V, Rawat D, Khanna R (2018) Profile, risk factors and outcome of acute kidney injury in paediatric acute-on-chronic liver failure. Liver Int Off J Int Assoc Study Liver 38(10):1777–1784. https://doi.org/10.1111/liv.13693
Yuan L, Liao PP, Song HC, Zhou JH, Chu HC, Lyu L (2019) Hyperbilirubinemia induces pro-apoptotic effects and aggravates renal ischemia reperfusion injury. Nephron 142(1):40–50. https://doi.org/10.1159/000496066
Rafat C, Burbach M, Brochériou I, Zafrani L, Callard P, Rondeau E, Hertig A (2013) Bilirubin-associated acute tubular necrosis in a kidney transplant recipient. Am J Kidney Dis 61(5):782–785. https://doi.org/10.1053/j.ajkd.2012.11.046
Kim JY, Kim KY, Yee J, Gwak HS (2022) Risk scoring system for vancomycin-associated acute kidney injury. Front Pharmacol 13:815188. https://doi.org/10.3389/fphar.2022.815188
Charlson ME, Pompei P, Ales KL, MacKenzie CR (1987) A new method of classifying prognostic comorbidity in longitudinal studies: development and validation. J Chronic Dis 40(5):373–383. https://doi.org/10.1016/0021-9681(87)90171-8
Ganta A, Parola R, Perskin CR, Konda SR, Egol KA (2021) Risk factors and associated outcomes of acute kidney injury in hip fracture patients. J Orthop 26:115–118. https://doi.org/10.1016/j.jor.2021.07.019
Rodríguez E, Soler MJ, Rap O, Barrios C, Orfila MA, Pascual J (2013) Risk factors for acute kidney injury in severe rhabdomyolysis. PLoS ONE 8(12):e82992. https://doi.org/10.1371/journal.pone.0082992
Duan Y, Jin D, Xu Y, Tong W, Hu P (2019) Risk factors and prognosis of acute kidney injury in children with sepsis in pediatric intensive care unit. Zhonghua wei zhong bing ji jiu yi xue 31(8):1004–1007. https://doi.org/10.3760/cma.j.issn.2095-4352.2019.08.018
Huang Y, Cai J, Ha F, Guo B, Xin S, Duan Z, Han T (2022) Characteristics of acute kidney injury and its impact on outcome in patients with acute-on-chronic liver failure. BMC Gastroenterol 22(1):231. https://doi.org/10.1186/s12876-022-02316-8
Hu M, Luo E, Yan G, Tang C, Wang L, Zhang Q, Gong J (2022) Microalbuminuria complicated with low estimated glomerular filtration rate: early risk factors for contrast-induced acute kidney injury after coronary intervention. Med Sci Monitor Int Med J Exp Clin Res 28:e935455. https://doi.org/10.12659/msm.935455
Du ZX, Chang FQ, Wang ZJ, Zhou DM, Li Y, Yang JH (2022) A risk prediction model for acute kidney injury in patients with pulmonary tuberculosis during anti-tuberculosis treatment. Ren Fail 44(1):625–635. https://doi.org/10.1080/0886022x.2022.2058405
Sahinturk H, Ozdemirkan A, Zeyneloglu P, Gedik E, Pirat A, Haberal M (2021) Early postoperative acute kidney injury among pediatric liver transplant recipients. Exp Clin Transplant Off J Middle East Soc Organ Transplant 19(7):659–663. https://doi.org/10.6002/ect.2018.0214
Albuquerque PLMM, Paiva JHHGL, Martins AMC, Meneses GC, da Silva GB, Buckley N, Daher EF (2020) Clinical assessment and pathophysiology of Bothrops venom-related acute kidney injury: a scoping review. J Venomous Animals Toxins Including Trop Dis 26:e20190076. https://doi.org/10.1590/1678-9199-JVATITD-2019-0076
Marzuillo P, Di Sessa A, Iafusco D, Capalbo D, Polito C, Nunziata F, Miraglia Del Giudice E, Montaldo P, Guarino S (2022) Heart rate cut-offs to identify non-febrile children with dehydration and acute kidney injury. Eur J Pediatr 181(5):1967–1977. https://doi.org/10.1007/s00431-022-04381-3
Riley RD, Ensor J, Snell KIE, Harrell FE Jr, Martin GP, Reitsma JB, Moons KGM, Collins G, van Smeden M (2020) Calculating the sample size required for developing a clinical prediction model. BMJ (Clin Res ed) 368:441. https://doi.org/10.1136/bmj.m441
Bland JM, Altman DG (2015) Statistics notes: Bootstrap resampling methods. BMJ (Clin Res ed) 350:h2622. https://doi.org/10.1136/bmj.h2622
Funding
None.
Author information
Authors and Affiliations
Contributions
TZ designed the study. RC, HS and YZ collected and analyzed the data. JT wrote the manuscript. TZ reviewed and edited the manuscript. All the authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors have declared that no conflict of interest exists.
Ethics approval and consent to participate
All patient information in both databases is de-identified, so this study was exempt from the approval of the institutional review board and informed consent from individual patients.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Tian, J., Cui, R., Song, H. et al. Prediction of acute kidney injury in patients with liver cirrhosis using machine learning models: evidence from the MIMIC-III and MIMIC-IV. Int Urol Nephrol 56, 237–247 (2024). https://doi.org/10.1007/s11255-023-03646-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11255-023-03646-6