Cardiac surgery-associated acute kidney injury (CSA-AKI) is related to increased morbidity and mortality. However, limited studies have explored the influence of different feature selection (FS) methods on the predictive performance of CSA-AKI. Therefore, we aimed to compare the impact of different FS methods for CSA-AKI.
Methods
CSA-AKI is defined according to the kidney disease: Improving Global Outcomes (KDIGO) criteria. Both traditional logistic regression and machine learning methods were used to select the potential risk factors for CSA-AKI. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of the models. In addition, the importance matrix plot by random forest was used to rank the features' importance.
Results
A total of 1977 patients undergoing cardiac surgery at Fuwai hospital from December 2018 to April 2021 were enrolled. The incidence of CSA-AKI during the first postoperative week was 27.8%. We concluded that different enrolled numbers of features impact the final selected feature number. The more you input, the more likely its output with all FS methods. In terms of performance, all selected features by various FS methods demonstrated excellent AUCs. Meanwhile, the embedded method demonstrated the highest accuracy compared with the LR method, while the filter method showed the lowest accuracy. Furthermore, NT-proBNP was found to be strongly associated with AKI. Our results confirmed some features that previous studies have reported and found some novel clinical parameters.
Conclusions
In our study, FS was as suitable as LR for predicting CSA-AKI. For FS, the embedded method demonstrated better efficacy than the other methods. Furthermore, NT-proBNP was confirmed to be strongly associated with AKI.
ThongprayoonCHansrivijitPKovvuruK, et al.Diagnostics, risk factors, Treatment and outcomes of acute kidney injury in a New Paradigm. J Clin Med2020; 9: 2–17. DOI: 10.3390/jcm9041104.
2.
LeeHCYoonHKNamK, et al.Derivation and validation of machine learning approaches to predict acute kidney injury after cardiac surgery. J Clin Med2018; 7: 1–05. DOI: 10.3390/jcm7100322.
3.
ThongprayoonCHansrivijitPBathiniT, et al.Predicting acute kidney injury after cardiac surgery by machine learning approaches. J Clin Med2020; 9: 6–11. DOI: 10.3390/jcm9061767.
4.
TsengPYChenYTWangCH, et al.Prediction of the development of acute kidney injury following cardiac surgery by machine learning. Crit Care2020; 24: 478. 2020/08/02. DOI: 10.1186/s13054-020-03179-9.
5.
WuLHuYLiuX, et al.Feature ranking in predictive models for hospital-Acquired acute kidney injury. Sci Rep2018; 8: 17298. 2018/11/25. DOI: 10.1038/s41598-018-35487-0.
6.
AminiSNajafiMNKarrariSP, et al.Risk factors and outcome of acute kidney injury after Isolated CABG surgery: a prospective cohort study. Braz J Cardiovasc Surg2019; 34: 70–75. 2019/02/28. DOI: 10.21470/1678-9741-2017-0209.
7.
ZaouterCPotvinJBatsML, et al.A combined approach for the early recognition of acute kidney injury after adult cardiac surgery. Anaesth Crit Care Pain Med2018; 37: 335–341. 2018/05/20. DOI: 10.1016/j.accpm.2018.05.001.
8.
MalhotraRSiewED. Biomarkers for the early detection and Prognosis of acute kidney injury. Clin J Am Soc Nephrol2017; 12: 149–173. 2016/11/09. DOI: 10.2215/CJN.01300216.
ChertowGMLazarusJMChristiansenCL, et al.Preoperative renal risk stratification. Circulation1997; 95: 878–884.
11.
ThakarCVArrigainSWorleyS, et al.A clinical score to predict acute renal failure after cardiac surgery. J Am Soc Nephrol2005; 16: 162–168.
12.
MehtaRHGrabJDO’BrienSM, et al.Bedside tool for predicting the risk of postoperative dialysis in patients undergoing cardiac surgery. Circulation2006; 114: 2208–2216.
13.
WijeysunderaDNKarkoutiKDupuisJ-Y, et al.Derivation and validation of a simplified predictive index for renal replacement therapy after cardiac surgery. JAMA2007; 297: 1801–1809.
14.
SaeysYInzaILarranagaP. A review of feature selection techniques in bioinformatics. Bioinformatics2007; 23: 2507–2517. 2007/08/28. DOI: 10.1093/bioinformatics/btm344.
15.
GuyonIElisseeffA. An introduction to variable and feature selection. Journal of machine learning research2003; 3: 1157–1182.
16.
LeeCKHoferIGabelE, et al.Development and validation of a deep neural Network model for prediction of postoperative in-hospital mortality. Anesthesiology2018; 129: 649–662. 2018/04/18. DOI: 10.1097/aln.0000000000002186.
17.
KristovicDHorvaticIHusedzinovicI, et al.Cardiac surgery-associated acute kidney injury: risk factors analysis and comparison of prediction models. Interact Cardiovasc Thorac Surg2015; 21: 366–373. 2015/06/21. DOI: 10.1093/icvts/ivv162.
18.
NeugartenJSandilyaSSinghB, et al.Sex and the risk of AKI following cardio-thoracic surgery: a meta-analysis. Clin J Am Soc Nephrol2016; 11: 2113–2122. 2016/11/01. DOI: 10.2215/CJN.03340316.
19.
YiQLiKJianZ, et al.Risk factors for acute kidney injury after Cardiovascular surgery: evidence from 2,157 Cases and 49,777 Controls - a meta-analysis. Cardiorenal Med2016; 6: 237–250. 2016/06/09. DOI: 10.1159/000444094.
20.
WangJYuWZhouY, et al.Independent risk factors contributing to acute kidney injury according to updated valve academic research consortium-2 criteria after Transcatheter aortic Valve Implantation: a meta-analysis and meta-regression of 13 studies. J Cardiothorac Vasc Anesth2017; 31: 816–826. 2017/04/08. DOI: 10.1053/j.jvca.2016.12.021.
21.
ThomasMEBlaineCDawnayA, et al.The definition of acute kidney injury and its use in practice. Kidney Int2015; 87: 62–73. 2014/10/16. DOI: 10.1038/ki.2014.328.
22.
HoriDKatzNMFineDM, et al.Defining oliguria during cardiopulmonary bypass and its relationship with cardiac surgery-associated acute kidney injury. Br J Anaesth2016; 117: 733–740. 2016/12/14. DOI: 10.1093/bja/aew340.
KoynerJLCareyKAEdelsonDP, et al.The development of a machine learning Inpatient acute kidney injury prediction model. Crit Care Med2018; 46: 1070–1077. 2018/03/30. DOI: 10.1097/ccm.0000000000003123.
25.
Penny-DimriJCBergmeirCReidCM, et al.Machine learning algorithms for predicting and risk Profiling of cardiac surgery-associated acute kidney injury. Semin Thorac Cardiovasc Surg2021; 33: 735–745. 2020/09/27. DOI: 10.1053/j.semtcvs.2020.09.028.
26.
ChristodoulouEMaJCollinsGS, et al.A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J Clin Epidemiol2019; 110: 12–22. 2019/02/15. DOI: 10.1016/j.jclinepi.2019.02.004.
27.
HuPMoZChenY, et al.Derivation and validation of a model to predict acute kidney injury following cardiac surgery in patients with normal renal function. Ren Fail2021; 43: 1205–1213. 2021/08/11. DOI: 10.1080/0886022x.2021.1960563.
28.
KimWHLeeJ-HKimE, et al.Can we really predict postoperative acute kidney injury after aortic surgery? Diagnostic accuracy of risk scores using gray zone approach. Thorac Cardiovasc Surg2016; 64: 281–289.
29.
BrownJRCochranRPLeavittBJ, et al.Multivariable prediction of renal insufficiency developing after cardiac surgery. Circulation2007; 116: I139–I143.
30.
HameedSSPetinrinOOHashiAO, et al.Filter-wrapper combination and embedded feature selection for gene expression data. Int J Advance Soft Compu Appl2018; 10: 90–105.
31.
MariesLManitiuI. Diagnostic and prognostic values of B-type natriuretic peptides (BNP) and N-terminal fragment brain natriuretic peptides (NT-pro-BNP). Cardiovasc J Afr2013; 24: 286–289. 2013/11/13. DOI: 10.5830/cvja-2013-055.
32.
AdhikariLOzrazgat-BaslantiTRuppertM, et al.Improved predictive models for acute kidney injury with IDEA: intraoperative data embedded analytics. PLoS One2019; 14: e0214904.
33.
OstermannMKunstGBakerE, et al.Cardiac surgery associated AKI prevention strategies and medical treatment for CSA-AKI. J Clin Med2021; 10: 5285–6128. DOI: 10.3390/jcm10225285.
AatilaMLachgarMHamidH, et al.Keratoconus severity classification using features selection and machine learning algorithms. Comput Math Methods Med2021; 2021: 9979560. DOI: 10.1155/2021/9979560.
36.
MassothCZarbockAMeerschM. Acute kidney injury in cardiac surgery. Crit Care Clin2021; 37: 267–278. 2021/03/24. DOI: 10.1016/j.ccc.2020.11.009.
