Prediction of Acute Kidney Injury after Extracorporeal Cardiac Surgery (CSA-AKI) by Machine Learning Algorithms
DOI:
https://doi.org/10.59958/hsf.5673Keywords:
acute kidney injury, extracorporeal cardiac surgery, machine learning, prediction modelsAbstract
Background: Acute renal failure after extracorporeal cardiac surgery under general anesthesia is high and unpredictable, but machine learning algorithms could change this. A feasible approach is to use machine learning models to construct models to predict acute kidney injury after extracorporeal cardiac surgery (CSA-AKI) and screen for the best predictive model. Method: From January 2014 to December 2021, 2187 patients undergoing extracorporeal cardiac surgery at the third hospital of Hebei Medical University and the first medical centre of Chinese PLA General Hospital were collected in this study. After excluding 923 patients who did not meet the inclusion criteria, a dataset of 1264 patients with 125 clinical indexes was constructed. After screening the feature variables using Least absolute shrinkage (LASSO) regression, the dataset was randomly divided into a training set (70%), test set (30%), and six machine learning algorithms, including extreme gradient boosting (XGBoost), logistic regression (LRC), light gradient boosting machine (LGBM), random forest classifier (RFC), adaptive boosting (AdaBoost), and K-nearest neighbor (KNN), were used in training set for predicting the CSA-AKI. The machine learning model with the best predictive performance was selected to complete external validation of the test set. The SHapley Additive exPlanations (SHAP) algorithm was used to interpret the model. Results: Of all 1264 patients, 372 (29.43%) patients presented with CSA-AKI. The LASSO regression eliminated 22 feature variables out of 125 before model development. Among the six prediction models, the RFC prediction model has the best prediction performance, with an Area Under Curve (AUC) value of 0.778 (95% CI: 0.726–0.830) in the test set and the best net benefit compared to the other tools. SHAP explained the impact of different feature variables on the predicted outcome, where the three most influential feature variables were creatinine clearance (CRC), intraoperative urine output (mL/kg/h) and age. Conclusion: We developed an RFC prediction model to predict the CSA-AKI, which has good predictive performance and can explain the factors affecting the prediction results of cases by integrating the SHAP method.
References
Eckardt KU, Kasiske BL. Kidney disease: improving global outcomes. Nature Reviews. Nephrology. 2009; 5: 650–657.
Schurle A, Koyner JL. CSA-AKI: Incidence, Epidemiology, Clinical Outcomes, and Economic Impact. Journal of Clinical Medicine. 2021; 10: 5746.
Wang Y, Bellomo R. Cardiac surgery-associated acute kidney injury: risk factors, pathophysiology and treatment. Nature Reviews. Nephrology. 2017; 13: 697–711.
Cummings JJ, Shaw AD, Shi J, Lopez MG, O'Neal JB, Billings FT 4th. Intraoperative prediction of cardiac surgery-associated acute kidney injury using urinary biomarkers of cell cycle arrest. The Journal of Thoracic and Cardiovascular Surgery. 2019; 157: 1545–1553.e5.
Ortega-Loubon C, Fernández-Molina M, Carrascal-Hinojal Y, Fulquet-Carreras E. Cardiac surgery-associated acute kidney injury. Annals of Cardiac Anaesthesia. 2016; 19: 687–698.
Hobson CE, Yavas S, Segal MS, Schold JD, Tribble CG, Layon AJ, et al. Acute kidney injury is associated with increased long-term mortality after cardiothoracic surgery. Circulation. 2009; 119: 2444–2453.
Bove T, Monaco F, Covello RD, Zangrillo A. Acute renal failure and cardiac surgery. HSR Proceedings in Intensive Care & Cardiovascular Anesthesia. 2009; 1: 13–21.
Nadim MK, Forni LG, Bihorac A, Hobson C, Koyner JL, Shaw A, et al. Cardiac and Vascular Surgery-Associated Acute Kidney Injury: The 20th International Consensus Conference of the ADQI (Acute Disease Quality Initiative) Group. Journal of the American Heart Association. 2018; 7: e008834.
Jordan MI, Mitchell TM. Machine learning: Trends, perspectives, and prospects. Science (New York, N.Y.). 2015; 349: 255–260.
Huang CT, Liu KD. Exciting developments in the field of acute kidney injury. Nature Reviews. Nephrology. 2020; 16: 69–70.
Thongprayoon C, Hansrivijit P, Bathini T, Vallabhajosyula S, Mekraksakit P, Kaewput W, et al. Predicting Acute Kidney Injury after Cardiac Surgery by Machine Learning Approaches. Journal of Clinical Medicine. 2020; 9: 1767.
Lee HC, Yoon HK, Nam K, Cho YJ, Kim TK, Kim WH, et al. Derivation and Validation of Machine Learning Approaches to Predict Acute Kidney Injury after Cardiac Surgery. Journal of Clinical Medicine. 2018; 7: 322.
Li Y, Xu J, Wang Y, Zhang Y, Jiang W, Shen B, et al. A novel machine learning algorithm, Bayesian networks model, to predict the high-risk patients with cardiac surgery-associated acute kidney injury. Clinical Cardiology. 2020; 43: 752–761.
Hayward A, Robertson A, Thiruchelvam T, Broadhead M, Tsang VT, Sebire NJ, et al. Oxygen delivery in pediatric cardiac surgery and its association with acute kidney injury using machine learning. The Journal of Thoracic and Cardiovascular Surgery. 2023; 165: 1505–1516.
Parolari A, Pesce LL, Pacini D, Mazzanti V, Salis S, Sciacovelli C, et al. Risk factors for perioperative acute kidney injury after adult cardiac surgery: role of perioperative management. The Annals of Thoracic Surgery. 2012; 93: 584–591.
Shin SR, Kim WH, Kim DJ, Shin IW, Sohn JT. Prediction and Prevention of Acute Kidney Injury after Cardiac Surgery. BioMed Research International. 2016; 2016: 2985148.
Neelamegam S, Ramaraj E. Classification algorithm in data mining: An overview. International Journal of P2P Network Trends and Technology (IJPTT). 2013; 4: 369–374.
Kidney Disease: Improving Global Outcomes (KDIGO) Glomerular Diseases Work Group. KDIGO 2021 Clinical Practice Guideline for the Management of Glomerular Diseases. Kidney International. 2021; 100: S1–S276.
Khwaja A. KDIGO clinical practice guidelines for acute kidney injury. Nephron. Clinical Practice. 2012; 120: c179–c184.
Bradley AP. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognition. 1997; 30: 1145–1159.
Vickers AJ, Elkin EB. Decision curve analysis: a novel method for evaluating prediction models. Medical Decision Making: an International Journal of the Society for Medical Decision Making. 2006; 26: 565–574.
Wang Q, Guo A. An efficient variance estimator of AUC and its applications to binary classification. Statistics in Medicine. 2020; 39: 4281–4300.
Janssens ACJW, Martens FK. Reflection on modern methods: Revisiting the area under the ROC Curve. International Journal of Epidemiology. 2020; 49: 1397–1403.
Park SK, Hur M, Kim E, Kim WH, Park JB, Kim Y, et al. Risk Factors for Acute Kidney Injury after Congenital Cardiac Surgery in Infants and Children: A Retrospective Observational Study. PLoS ONE. 2016; 11: e0166328.
Xue X, Liu Z, Xue T, Chen W, Chen X. Machine learning for the prediction of acute kidney injury in patients after cardiac surgery. Frontiers in Surgery. 2022; 9: 946610.
Petrosyan Y, Mesana TG, Sun LY. Prediction of acute kidney injury risk after cardiac surgery: using a hybrid machine learning algorithm. BMC Medical Informatics and Decision Making. 2022; 22: 137.
Penny-Dimri JC, Bergmeir C, Reid CM, Williams-Spence J, Cochrane AD, Smith JA. Machine Learning Algorithms for Predicting and Risk Profiling of Cardiac Surgery-Associated Acute Kidney Injury. Seminars in Thoracic and Cardiovascular Surgery. 2021; 33: 735–745.
Tseng PY, Chen YT, Wang CH, Chiu KM, Peng YS, Hsu SP, et al. Prediction of the development of acute kidney injury following cardiac surgery by machine learning. Critical Care (London, England). 2020; 24: 478.
Chang HH, Chiang JH, Wang CS, Chiu PF, Abdel-Kader K, Chen H, et al. Predicting Mortality Using Machine Learning Algorithms in Patients Who Require Renal Replacement Therapy in the Critical Care Unit. Journal of Clinical Medicine. 2022; 11: 5289.
Wong WEJ, Chan SP, Yong JK, Tham YYS, Lim JRG, Sim MA, et al. Assessment of acute kidney injury risk using a machine-learning guided generalized structural equation model: a cohort study. BMC Nephrology. 2021; 22: 63.
Alhamzawi R, Ali HTM. The Bayesian adaptive lasso regression. Mathematical Biosciences. 2018; 303: 75–82.
Freijeiro-González L, Febrero-Bande M, González-Manteiga W. A Critical Review of LASSO and Its Derivatives for Variable Selection Under Dependence Among Covariates. International Statistical Review. 2022; 90: 118–145.
Ranstam J, Cook JA. LASSO regression. British Journal of Surgery. 2018; 105: 1348.
Štrumbelj E, Kononenko I. Explaining prediction models and individual predictions with feature contributions. Knowledge and Information Systems. 2014; 41: 647–665.
Meersch M, Zarbock A. Prevention of cardiac surgery-associated acute kidney injury. Current Opinion in Anaesthesiology. 2017; 30: 76–83.
Bai L, Jin Y, Zhang P, Li Y, Gao P, Wang W, et al. Risk factors and outcomes associated with acute kidney injury following extracardiac total cavopulmonary connection: a retrospective observational study. Translational Pediatrics. 2022; 11: 848–858.
Wang M, Xu X, Wu S, Sun H, Chang Y, Li M, et al. Risk factors for ventilator-associated pneumonia due to multi-drug resistant organisms after cardiac surgery in adults. BMC Cardiovascular Disorders. 2022; 22: 465.
Zhang Y, Yang D, Liu Z, Chen C, Ge M, Li X, et al. An explainable supervised machine learning predictor of acute kidney injury after adult deceased donor liver transplantation. Journal of Translational Medicine. 2021; 19: 321.
