Predictive modeling for acute kidney injury after percutaneous coronary intervention in patients with acute coronary syndrome: a machine learning approach.
Acute coronary syndrome
Acute kidney injury
Machine learning
Percutaneous coronary intervention
Prediction
Journal
European journal of medical research
ISSN: 2047-783X
Titre abrégé: Eur J Med Res
Pays: England
ID NLM: 9517857
Informations de publication
Date de publication:
24 Jan 2024
24 Jan 2024
Historique:
received:
21
11
2023
accepted:
15
01
2024
medline:
25
1
2024
pubmed:
25
1
2024
entrez:
24
1
2024
Statut:
epublish
Résumé
Acute kidney injury (AKI) is one of the preventable complications of percutaneous coronary intervention (PCI). This study aimed to develop machine learning (ML) models to predict AKI after PCI in patients with acute coronary syndrome (ACS). This study was conducted at Tehran Heart Center from 2015 to 2020. Several variables were used to design five ML models: Naïve Bayes (NB), Logistic Regression (LR), CatBoost (CB), Multi-layer Perception (MLP), and Random Forest (RF). Feature importance was evaluated with the RF model, CB model, and LR coefficients while SHAP beeswarm plots based on the CB model were also used for deriving the importance of variables in the population using pre-procedural variables and all variables. Sensitivity, specificity, and the area under the receiver operating characteristics curve (ROC-AUC) were used as the evaluation measures. A total of 4592 patients were included, and 646 (14.1%) experienced AKI. The train data consisted of 3672 and the test data included 920 cases. The patient population had a mean age of 65.6 ± 11.2 years and 73.1% male predominance. Notably, left ventricular ejection fraction (LVEF) and fasting plasma glucose (FPG) had the highest feature importance when training the RF model on only pre-procedural features. SHAP plots for all features demonstrated LVEF and age as the top features. With pre-procedural variables only, CB had the highest AUC for the prediction of AKI (AUC 0.755, 95% CI 0.713 to 0.797), while RF had the highest sensitivity (75.9%) and MLP had the highest specificity (64.35%). However, when considering pre-procedural, procedural, and post-procedural features, RF outperformed other models (AUC: 0.775). In this analysis, CB achieved the highest sensitivity (82.95%) and NB had the highest specificity (82.93%). Our analyses showed that ML models can predict AKI with acceptable performance. This has potential clinical utility for assessing the individualized risk of AKI in ACS patients undergoing PCI. Additionally, the identified features in the models may aid in mitigating these risk factors.
Sections du résumé
BACKGROUND
BACKGROUND
Acute kidney injury (AKI) is one of the preventable complications of percutaneous coronary intervention (PCI). This study aimed to develop machine learning (ML) models to predict AKI after PCI in patients with acute coronary syndrome (ACS).
METHODS
METHODS
This study was conducted at Tehran Heart Center from 2015 to 2020. Several variables were used to design five ML models: Naïve Bayes (NB), Logistic Regression (LR), CatBoost (CB), Multi-layer Perception (MLP), and Random Forest (RF). Feature importance was evaluated with the RF model, CB model, and LR coefficients while SHAP beeswarm plots based on the CB model were also used for deriving the importance of variables in the population using pre-procedural variables and all variables. Sensitivity, specificity, and the area under the receiver operating characteristics curve (ROC-AUC) were used as the evaluation measures.
RESULTS
RESULTS
A total of 4592 patients were included, and 646 (14.1%) experienced AKI. The train data consisted of 3672 and the test data included 920 cases. The patient population had a mean age of 65.6 ± 11.2 years and 73.1% male predominance. Notably, left ventricular ejection fraction (LVEF) and fasting plasma glucose (FPG) had the highest feature importance when training the RF model on only pre-procedural features. SHAP plots for all features demonstrated LVEF and age as the top features. With pre-procedural variables only, CB had the highest AUC for the prediction of AKI (AUC 0.755, 95% CI 0.713 to 0.797), while RF had the highest sensitivity (75.9%) and MLP had the highest specificity (64.35%). However, when considering pre-procedural, procedural, and post-procedural features, RF outperformed other models (AUC: 0.775). In this analysis, CB achieved the highest sensitivity (82.95%) and NB had the highest specificity (82.93%).
CONCLUSION
CONCLUSIONS
Our analyses showed that ML models can predict AKI with acceptable performance. This has potential clinical utility for assessing the individualized risk of AKI in ACS patients undergoing PCI. Additionally, the identified features in the models may aid in mitigating these risk factors.
Identifiants
pubmed: 38268045
doi: 10.1186/s40001-024-01675-0
pii: 10.1186/s40001-024-01675-0
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
76Informations de copyright
© 2024. The Author(s).
Références
Sun L, Zhu W, Chen X, Jiang J, Ji Y, Liu N, et al. Machine learning to predict contrast-induced acute kidney injury in patients with acute myocardial infarction. Front Med. 2020;7: 592007.
doi: 10.3389/fmed.2020.592007
Tsai TT, Patel UD, Chang TI, Kennedy KF, Masoudi FA, Matheny ME, et al. Contemporary incidence, predictors, and outcomes of acute kidney injury in patients undergoing percutaneous coronary interventions: insights from the NCDR Cath-PCI registry. JACC Cardiovasc Interventions. 2014;7(1):1–9.
doi: 10.1016/j.jcin.2013.06.016
Chalikias G, Serif L, Kikas P, Thomaidis A, Stakos D, Makrygiannis D, et al. Long-term impact of acute kidney injury on prognosis in patients with acute myocardial infarction. Int J Cardiol. 2019;283:48–54.
doi: 10.1016/j.ijcard.2019.01.070
pubmed: 30711262
Ng AK, Ng PY, Ip A, Lam LT, Ling IW, Wong AS, et al. Impact of contrast-induced acute kidney injury on long-term major adverse cardiovascular events and kidney function after percutaneous coronary intervention: insights from a territory-wide cohort study in Hong Kong. Clin Kidney J. 2022;15(2):338–46.
doi: 10.1093/ckj/sfab212
pubmed: 35145648
Maksimczuk J, Galas A, Krzesiński P. What promotes acute kidney injury in patients with myocardial infarction and multivessel coronary artery disease-contrast media, hydration status or something else? Nutrients. 2022;15(1):21.
doi: 10.3390/nu15010021
pubmed: 36615678
pmcid: 9824824
Huang C, Murugiah K, Mahajan S, Li SX, Dhruva SS, Haimovich JS, et al. Enhancing the prediction of acute kidney injury risk after percutaneous coronary intervention using machine learning techniques: a retrospective cohort study. PLoS Med. 2018;15(11): e1002703.
doi: 10.1371/journal.pmed.1002703
pubmed: 30481186
pmcid: 6258473
Tsai TT, Patel UD, Chang TI, Kennedy KF, Masoudi FA, Matheny ME, et al. Validated contemporary risk model of acute kidney injury in patients undergoing percutaneous coronary interventions: insights from the National Cardiovascular Data Registry Cath-PCI Registry. J Am Heart Assoc. 2014;3(6): e001380.
doi: 10.1161/JAHA.114.001380
pubmed: 25516439
pmcid: 4338731
Kuno T, Mikami T, Sahashi Y, Numasawa Y, Suzuki M, Noma S, et al. Machine learning prediction model of acute kidney injury after percutaneous coronary intervention. Sci Rep. 2022;12(1):749.
doi: 10.1038/s41598-021-04372-8
pubmed: 35031637
pmcid: 8760264
Negassa A, Ahmed S, Zolty R, Patel SR. Prediction model using machine learning for mortality in patients with heart failure. Am J Cardiol. 2021;153:86–93.
doi: 10.1016/j.amjcard.2021.05.044
pubmed: 34246419
Khalaji A, Behnoush AH, Jameie M, Sharifi A, Sheikhy A, Fallahzadeh A, et al. Machine learning algorithms for predicting mortality after coronary artery bypass grafting. Front Cardiovasc Med. 2022;9: 977747.
doi: 10.3389/fcvm.2022.977747
pubmed: 36093147
pmcid: 9448905
de Oliveira Gomes BF, da Silva TMB, Dutra GP, Peres LS, Camisao ND, Junior WSH, et al. Late mortality after myocardial injury in critical care non-cardiac surgery patients using machine learning analysis. Am J Cardiol. 2023;204:70–6.
doi: 10.1016/j.amjcard.2023.07.044
pubmed: 37541150
Mehta RL, Kellum JA, Shah SV, Molitoris BA, Ronco C, Warnock DG, et al. Acute Kidney Injury Network: report of an initiative to improve outcomes in acute kidney injury. Crit Care. 2007;11(2):R31.
doi: 10.1186/cc5713
pubmed: 17331245
pmcid: 2206446
Lundberg SM, Lee S-I. Consistent feature attribution for tree ensembles. arXiv preprint arXiv:170606060. 2017.
Meacham S, Isaac G, Nauck D, Virginas B, editors. Towards explainable AI: design and development for explanation of machine learning predictions for a patient readmittance medical application. Intelligent Computing. Cham: Springer International Publishing; 2019.
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:2825–30.
Mandrekar JN. Receiver operating characteristic curve in diagnostic test assessment. J Thorac Oncol. 2010;5(9):1315–6.
doi: 10.1097/JTO.0b013e3181ec173d
pubmed: 20736804
Thakker RA, Albaeni A, Alwash H, Gilani S. Prevention and management of AKI in ACS patients undergoing invasive treatments. Curr Cardiol Rep. 2022;24(10):1299–307.
doi: 10.1007/s11886-022-01742-0
pubmed: 35925513
Mehran R, Aymong ED, Nikolsky E, Lasic Z, Iakovou I, Fahy M, et al. A simple risk score for prediction of contrast-induced nephropathy after percutaneous coronary intervention: development and initial validation. J Am Coll Cardiol. 2004;44(7):1393–9.
pubmed: 15464318
Chen YL, Fu NK, Xu J, Yang SC, Li S, Liu YY, et al. A simple preprocedural score for risk of contrast-induced acute kidney injury after percutaneous coronary intervention. Catheter Cardiovasc Interv. 2014;83(1):E8–16.
doi: 10.1002/ccd.25109
pubmed: 23907993
Behnoush AH, Khalaji A, Rezaee M, Momtahen S, Mansourian S, Bagheri J, et al. Machine learning-based prediction of 1-year mortality in hypertensive patients undergoing coronary revascularization surgery. Clin Cardiol. 2023;46(3):269–78.
doi: 10.1002/clc.23963
pubmed: 36588391
pmcid: 10018097
Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2017;2(4):230–43.
doi: 10.1136/svn-2017-000101
pubmed: 29507784
pmcid: 5829945
Mohamadlou H, Lynn-Palevsky A, Barton C, Chettipally U, Shieh L, Calvert J, et al. Prediction of acute kidney injury with a machine learning algorithm using electronic health record data. Can J Kidney Health Dis. 2018;5:2054358118776326.
doi: 10.1177/2054358118776326
pubmed: 30094049
pmcid: 6080076
Li K, Yu N, Li P, Song S, Wu Y, Li Y, et al. Multi-label spacecraft electrical signal classification method based on DBN and random forest. PLoS ONE. 2017;12(5): e0176614.
doi: 10.1371/journal.pone.0176614
pubmed: 28486479
pmcid: 5423585
Amaratunga D, Cabrera J, Lee YS. Enriched random forests. Bioinformatics. 2008;24(18):2010–4.
doi: 10.1093/bioinformatics/btn356
pubmed: 18650208
Speiser JL, Miller ME, Tooze J, Ip E. A comparison of random forest variable selection methods for classification prediction modeling. Expert Syst Appl. 2019;134:93–101.
doi: 10.1016/j.eswa.2019.05.028
pubmed: 32968335
pmcid: 7508310
Chen R-C, Dewi C, Huang S-W, Caraka RE. Selecting critical features for data classification based on machine learning methods. J Big Data. 2020;7(1):52.
doi: 10.1186/s40537-020-00327-4
Niimi N, Shiraishi Y, Sawano M, Ikemura N, Inohara T, Ueda I, et al. Machine learning models for prediction of adverse events after percutaneous coronary intervention. Sci Rep. 2022;12(1):6262.
doi: 10.1038/s41598-022-10346-1
pubmed: 35428765
pmcid: 9012739
Ma X, Mo C, Li Y, Chen X, Gui C. Prediction of the development of contrast-induced nephropathy following percutaneous coronary artery intervention by machine learning. Acta Cardiol. 2023;78:1–10.
doi: 10.1080/00015385.2023.2198937
Khalilia M, Chakraborty S, Popescu M. Predicting disease risks from highly imbalanced data using random forest. BMC Med Inform Decis Mak. 2011;11(1):51.
doi: 10.1186/1472-6947-11-51
pubmed: 21801360
pmcid: 3163175
Wi J, Ko YG, Shin DH, Kim JS, Kim BK, Choi D, et al. Prediction of contrast-induced nephropathy with persistent renal dysfunction and adverse long-term outcomes in patients with acute myocardial infarction using the Mehran Risk Score. Clin Cardiol. 2013;36(1):46–53.
doi: 10.1002/clc.22060
pubmed: 23027701
Helber I, Alves CMR, Grespan SM, Veiga ECA, Moraes PIM, Souza JM, et al. The impact of advanced age on major cardiovascular events and mortality in patients with ST-elevation myocardial infarction undergoing a pharmaco-invasive strategy. Clin Interv Aging. 2020;15:715–22.
doi: 10.2147/CIA.S218827
pubmed: 32546989
pmcid: 7247595
Hosseini K, Khalaji A, Behnoush AH, Soleimani H, Mehrban S, Amirsardari Z, et al. The association between metabolic syndrome and major adverse cardiac and cerebrovascular events in patients with acute coronary syndrome undergoing percutaneous coronary intervention. Sci Rep. 2024;14(1):697.
doi: 10.1038/s41598-024-51157-w
pubmed: 38184738
pmcid: 10771421
Jonas M, Kagan M, Sella G, Haberman D, Chernin G. Cardiovascular outcomes following percutaneous coronary intervention with drug-eluting balloons in chronic kidney disease: a retrospective analysis. BMC Nephrol. 2020;21(1):445.
doi: 10.1186/s12882-020-02089-w
pubmed: 33097001
pmcid: 7583297
Wykrzykowska JJ, Garg S, Onuma Y, de Vries T, Goedhart D, Morel MA, et al. Value of age, creatinine, and ejection fraction (ACEF score) in assessing risk in patients undergoing percutaneous coronary interventions in the ‘all-comers’ leaders trial. Circ Cardiovasc Interventions. 2011;4(1):47–56.
doi: 10.1161/CIRCINTERVENTIONS.110.958389
Capodanno D, Marcantoni C, Ministeri M, Dipasqua F, Zanoli L, Rastelli S, et al. Incorporating Glomerular filtration rate or creatinine clearance by the modification of diet in renal disease equation or the Cockcroft-Gault equations to improve the Global Accuracy of the Age, Creatinine, Ejection Fraction [ACEF] score in patients undergoing percutaneous coronary intervention. Int J Cardiol. 2013;168(1):396–402.
doi: 10.1016/j.ijcard.2012.09.026
pubmed: 23041093
Araujo GN, Pivatto Junior F, Fuhr B, Cassol EP, Machado GP, Valle FH, et al. Simplifying contrast-induced acute kidney injury prediction after primary percutaneous coronary intervention: the age, creatinine and ejection fraction score. Cardiovasc Interv Ther. 2018;33(3):224–31.
doi: 10.1007/s12928-017-0472-y
pubmed: 28540634
Hertzberg D, Sartipy U, Lund LH, Rydén L, Pickering JW, Holzmann MJ. Heart failure and the risk of acute kidney injury in relation to ejection fraction in patients undergoing coronary artery bypass grafting. Int J Cardiol. 2019;274:66–70.
doi: 10.1016/j.ijcard.2018.09.092
pubmed: 30297189
Schöttker B, Brenner H, Koenig W, Müller H, Rothenbacher D. Prognostic association of HbA1c and fasting plasma glucose with reduced kidney function in subjects with and without diabetes mellitus. Results from a population-based cohort study from Germany. Prev Med. 2013;57(5):596–600.
doi: 10.1016/j.ypmed.2013.08.002
pubmed: 23948106
Bartholomew BA, Harjai KJ, Dukkipati S, Boura JA, Yerkey MW, Glazier S, et al. Impact of nephropathy after percutaneous coronary intervention and a method for risk stratification. Am J Cardiol. 2004;93(12):1515–9.
doi: 10.1016/j.amjcard.2004.03.008
pubmed: 15194023