An Explainable Machine Learning Model to Predict Acute Kidney Injury After Cardiac Surgery: A Retrospective Cohort Study

Overview

Journal Clin Epidemiol

Publisher Dove Medical Press

Specialty Public Health

Date 2023 Dec 11

PMID 38076638

Authors

Yuchen Gao

Chunrong Wang

Wenhao Dong

Bianfang Li

Jianhui Wang

Jun Li

Yu Tian

Jia Liu

Yuefu Wang

Affiliations

Soon will be listed here.

Abstract

Background: To derive and validate a machine learning (ML) prediction model of acute kidney injury (AKI) that could be used for AKI surveillance and management to improve clinical outcomes.

Methods: This retrospective cohort study was conducted in Fuwai Hospital, including patients aged 18 years and above undergoing cardiac surgery admitted between January 1, 2017, and December 31, 2018. Seventy percent of the observations were randomly selected for training and the remaining 30% for testing. The demographics, comorbidities, laboratory examination parameters, and operation details were used to construct a prediction model for AKI by logistic regression and eXtreme gradient boosting (Xgboost). The discrimination of each model was assessed on the test cohort by the area under the receiver operator characteristic (AUROC) curve, while calibration was performed by the calibration plot.

Results: A total of 15,880 patients were enrolled in this study, and 4845 (30.5%) had developed AKI. Xgboost model had the higher discriminative ability compared with logistic regression (AUROC, 0.849 [95% CI, 0.837-0.861] vs 0.803[95% CI 0.790-0.817], <0.001) in the test dataset. The estimated glomerular filtration (eGFR) and creatine on intensive care unit (ICU) arrival are the two most important prediction parameters. A SHAP summary plot was used to illustrate the effects of the top 15 features attributed to the Xgboost model.

Conclusion: ML models can provide clinical decision support to determine which patients should focus on perioperative preventive treatment to preemptively reduce acute kidney injury by predicting which patients are not at risk.

Citing Articles

Low estimated glomerular filtration rate and high body mass index are risk factors for acute kidney injury in systemic lupus erythematosus patients after cardiac surgery.

Zhang X, Wang C, Tian Y, Zhang Y, Miao Q, Wu D Front Cardiovasc Med. 2024; 11:1387612.

PMID: 38911516 PMC: 11190320. DOI: 10.3389/fcvm.2024.1387612.

Explainable Boosting Machine approach identifies risk factors for acute renal failure.

Korner A, Sailer B, Sari-Yavuz S, Haeberle H, Mirakaj V, Bernard A Intensive Care Med Exp. 2024; 12(1):55.

PMID: 38874694 PMC: 11178719. DOI: 10.1186/s40635-024-00639-2.

References

Thakar C, Arrigain S, Worley S, Yared J, Paganini E . A clinical score to predict acute renal failure after cardiac surgery. J Am Soc Nephrol. 2004; 16(1):162-8. DOI: 10.1681/ASN.2004040331. View

Luo X, Kang Y, Duan S, Yan P, Song G, Zhang N . Machine Learning-Based Prediction of Acute Kidney Injury Following Pediatric Cardiac Surgery: Model Development and Validation Study. J Med Internet Res. 2023; 25:e41142. PMC: 9893730. DOI: 10.2196/41142. View

Vagliano I, Chesnaye N, Leopold J, Jager K, Abu-Hanna A, Schut M . Machine learning models for predicting acute kidney injury: a systematic review and critical appraisal. Clin Kidney J. 2022; 15(12):2266-2280. PMC: 9664575. DOI: 10.1093/ckj/sfac181. View

Coulson T, Bailey M, Pilcher D, Reid C, Seevanayagam S, Williams-Spence J . Predicting Acute Kidney Injury After Cardiac Surgery Using a Simpler Model. J Cardiothorac Vasc Anesth. 2020; 35(3):866-873. DOI: 10.1053/j.jvca.2020.06.072. View

Penny-Dimri J, Bergmeir C, Perry L, Hayes L, Bellomo R, Smith J . Machine learning to predict adverse outcomes after cardiac surgery: A systematic review and meta-analysis. J Card Surg. 2022; 37(11):3838-3845. PMC: 9804388. DOI: 10.1111/jocs.16842. View

Rodriguez-Perez R, Bajorath J . Interpretation of Compound Activity Predictions from Complex Machine Learning Models Using Local Approximations and Shapley Values. J Med Chem. 2019; 63(16):8761-8777. DOI: 10.1021/acs.jmedchem.9b01101. View

Huen S, Parikh C . Predicting acute kidney injury after cardiac surgery: a systematic review. Ann Thorac Surg. 2011; 93(1):337-47. PMC: 3286599. DOI: 10.1016/j.athoracsur.2011.09.010. View

Levey A, Stevens L, Schmid C, Zhang Y, Castro 3rd A, Feldman H . A new equation to estimate glomerular filtration rate. Ann Intern Med. 2009; 150(9):604-12. PMC: 2763564. DOI: 10.7326/0003-4819-150-9-200905050-00006. View

Tseng P, Chen Y, Wang C, Chiu K, Peng Y, Hsu S . Prediction of the development of acute kidney injury following cardiac surgery by machine learning. Crit Care. 2020; 24(1):478. PMC: 7395374. DOI: 10.1186/s13054-020-03179-9. View

10.

Xue B, Li D, Lu C, King C, Wildes T, Avidan M . Use of Machine Learning to Develop and Evaluate Models Using Preoperative and Intraoperative Data to Identify Risks of Postoperative Complications. JAMA Netw Open. 2021; 4(3):e212240. PMC: 8010590. DOI: 10.1001/jamanetworkopen.2021.2240. View

11.

Islam M, Nasrin T, Walther B, Wu C, Yang H, Li Y . Prediction of sepsis patients using machine learning approach: A meta-analysis. Comput Methods Programs Biomed. 2019; 170:1-9. DOI: 10.1016/j.cmpb.2018.12.027. View

12.

Lee H, Yoon H, Nam K, Cho Y, Kim T, Kim W . Derivation and Validation of Machine Learning Approaches to Predict Acute Kidney Injury after Cardiac Surgery. J Clin Med. 2018; 7(10). PMC: 6210196. DOI: 10.3390/jcm7100322. View

13.

Guan C, Li C, Xu L, Zhen L, Zhang Y, Zhao L . Risk factors of cardiac surgery-associated acute kidney injury: development and validation of a perioperative predictive nomogram. J Nephrol. 2019; 32(6):937-945. DOI: 10.1007/s40620-019-00624-z. View

14.

Thorsen-Meyer H, Nielsen A, Nielsen A, Kaas-Hansen B, Toft P, Schierbeck J . Dynamic and explainable machine learning prediction of mortality in patients in the intensive care unit: a retrospective study of high-frequency data in electronic patient records. Lancet Digit Health. 2020; 2(4):e179-e191. DOI: 10.1016/S2589-7500(20)30018-2. View

15.

Koyner J, Carey K, Edelson D, Churpek M . The Development of a Machine Learning Inpatient Acute Kidney Injury Prediction Model. Crit Care Med. 2018; 46(7):1070-1077. DOI: 10.1097/CCM.0000000000003123. View

16.

Belley-Cote E, Parikh C, Shortt C, Coca S, Garg A, Eikelboom J . Association of cardiac biomarkers with acute kidney injury after cardiac surgery: A multicenter cohort study. J Thorac Cardiovasc Surg. 2016; 152(1):245-251.e4. PMC: 4921336. DOI: 10.1016/j.jtcvs.2016.02.029. View

17.

Christodoulou E, Ma J, Collins G, Steyerberg E, Verbakel J, Van Calster B . A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J Clin Epidemiol. 2019; 110:12-22. DOI: 10.1016/j.jclinepi.2019.02.004. View

18.

Wen Y, Parikh C . Current concepts and advances in biomarkers of acute kidney injury. Crit Rev Clin Lab Sci. 2021; 58(5):354-368. DOI: 10.1080/10408363.2021.1879000. View

19.

Naruse H, Ishii J, Takahashi H, Kitagawa F, Nishimura H, Kawai H . Predicting acute kidney injury using urinary liver-type fatty-acid binding protein and serum N-terminal pro-B-type natriuretic peptide levels in patients treated at medical cardiac intensive care units. Crit Care. 2018; 22(1):197. PMC: 6098639. DOI: 10.1186/s13054-018-2120-z. View

20.

Verwijmeren L, Bosma M, Vernooij L, Linde E, Dijkstra I, Daeter E . Associations Between Preoperative Biomarkers and Cardiac Surgery-Associated Acute Kidney Injury in Elderly Patients: A Cohort Study. Anesth Analg. 2021; 133(3):570-577. DOI: 10.1213/ANE.0000000000005650. View