1
|
Behnoush AH, Shariatnia MM, Khalaji A, Asadi M, Yaghoobi A, Rezaee M, Soleimani H, Sheikhy A, Aein A, Yadangi S, Jenab Y, Masoudkabir F, Mehrani M, Iskander M, Hosseini K. Predictive modeling for acute kidney injury after percutaneous coronary intervention in patients with acute coronary syndrome: a machine learning approach. Eur J Med Res 2024; 29:76. [PMID: 38268045 PMCID: PMC10807059 DOI: 10.1186/s40001-024-01675-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/21/2023] [Accepted: 01/15/2024] [Indexed: 01/26/2024] Open
Abstract
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 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 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 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.
Collapse
Affiliation(s)
- Amir Hossein Behnoush
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - M Moein Shariatnia
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
| | - Amirmohammad Khalaji
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Mahsa Asadi
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Alireza Yaghoobi
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Department of Pharmacology, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Malihe Rezaee
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
- Department of Pharmacology, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Hamidreza Soleimani
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Ali Sheikhy
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Afsaneh Aein
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Somayeh Yadangi
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Yaser Jenab
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Farzad Masoudkabir
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Mehdi Mehrani
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Mina Iskander
- Department of Cardiovascular Medicine, Medical College of Wisconsin, Milwaukee, WI, USA
| | - Kaveh Hosseini
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran.
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran.
| |
Collapse
|
2
|
Zhang Y, Wu Z, Wang S, Liu T, Liu J. Clinical Outcome of Paclitaxel-Coated Balloon Angioplasty Versus Drug-Eluting Stent Implantation for the Treatment of Coronary Drug-Eluting Stent In-Stent Chronic Total Occlusion. Cardiovasc Drugs Ther 2023; 37:1155-1166. [PMID: 35930211 PMCID: PMC10721670 DOI: 10.1007/s10557-022-07363-7] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 06/26/2022] [Indexed: 11/25/2022]
Abstract
AIMS In-stent chronic total occlusion (IS-CTO) represents a unique challenge for percutaneous coronary intervention. Whether the optimal treatment for IS-CTO is angioplasty with paclitaxel-coated balloons (PCBs) or repeat stenting with drug-eluting stents (DESs) is unclear. We aimed to evaluate the long-term clinical outcome of PCB angioplasty and DES repeat stenting for DES IS-CTO. METHODS We retrospectively included patients with DES IS-CTO who underwent successful PCB angioplasty or DES repeat stenting from January 2016 to December 2019. The primary endpoints were major adverse cardiac events (MACEs), including cardiac death, myocardial infarction, and target lesion revascularization (TLR). Cox proportional hazards model was performed to compare the risk of MACEs between PCB angioplasty and DES repeat stenting, and to further explore the prognostic factors of patients with DES IS-CTO. RESULTS A total of 214 patients with DES IS-CTO were enrolled: 78 patients (36.4%) treated with PCB and 136 patients (63.6%) treated with DES respectively. The median follow-up was 1160 days, and MACEs were observed in 28.2% of patients with PCB angioplasty versus 26.5% of patients with DES repeat stenting (P = 0.784), mainly driven by TLR (21.8% vs. 19.9%, P = 0.735). There was no significant difference in the risk of MACEs between the PCB group and the DES group (hazard ratio [HR] 1.25, 95% confidence interval [CI] 0.64-2.46, P = 0.512). Multivariate Cox analysis revealed that chronic kidney disease and ≥ 3 stent layers in the lesion were independent predictors of MACEs, while switching to another antiproliferative drug was an independent protective factor (all P < 0.05). CONCLUSIONS PCB angioplasty was an effective alternative treatment strategy for DES IS-CTO, which had similar long-term outcomes to DES repeat stenting in contemporary practice, but both were accompanied by a high rate of long-term MACEs. Improving the poor prognosis of patients with DES IS-CTO remains a challenge.
Collapse
Affiliation(s)
- Yuchao Zhang
- Center for Coronary Artery Disease, Beijing Anzhen Hospital, Capital Medical University, Beijing Institute of Heart Lung and Blood Vessel Diseases, No. 2 Anzhen Road, Chaoyang District, Beijing, 100029, China
| | - Zheng Wu
- Center for Coronary Artery Disease, Beijing Anzhen Hospital, Capital Medical University, Beijing Institute of Heart Lung and Blood Vessel Diseases, No. 2 Anzhen Road, Chaoyang District, Beijing, 100029, China
| | - Shaoping Wang
- Center for Coronary Artery Disease, Beijing Anzhen Hospital, Capital Medical University, Beijing Institute of Heart Lung and Blood Vessel Diseases, No. 2 Anzhen Road, Chaoyang District, Beijing, 100029, China
| | - Tong Liu
- Center for Coronary Artery Disease, Beijing Anzhen Hospital, Capital Medical University, Beijing Institute of Heart Lung and Blood Vessel Diseases, No. 2 Anzhen Road, Chaoyang District, Beijing, 100029, China
| | - Jinghua Liu
- Center for Coronary Artery Disease, Beijing Anzhen Hospital, Capital Medical University, Beijing Institute of Heart Lung and Blood Vessel Diseases, No. 2 Anzhen Road, Chaoyang District, Beijing, 100029, China.
| |
Collapse
|
3
|
Zhu X, Zhang P, Xiong J, Wang N, Yang S, Zhu R, Zhang L, Liu W, Wu L. Effect of glomerular filtration rate in patients undergoing percutaneous coronary intervention: A systematic review and meta-analysis. Medicine (Baltimore) 2022; 101:e31498. [PMID: 36343078 PMCID: PMC9646511 DOI: 10.1097/md.0000000000031498] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/09/2022] Open
Abstract
BACKGROUND Through meta-analysis of the relationship between glomerular filtration rate and major adverse cardiovascular events (MACE) after percutaneous coronary intervention (PCI), we studied the impact of glomerular filtration rate on the prognosis of PCI. METHODS We collected literature on the incidence of MACE in patients with chronic kidney disease (CKD; estimated glomerular filtration rate < 60 mL/minute/1.73 m2) and patients with nonchronic kidney disease undergoing PCI. The search period was from January 1, 2000, to November 1, 2021. The searched databases included CNKI, Chinese Wanfang Data, China Biology Medicine disc, Web of Science, PubMed, and Cochrane Library. We used subgroup analysis and meta-regression to assess heterogeneity. RESULTS Twenty-one eligible studies were included, with 46,255 samples included, 4903 cases of MACE (10.6%), and patients with CKD had a higher risk of MACE after PCI (Risk ratios = 1.67; 95% confidence interval: 1.51-1.85). Multivariate meta regression results show that heterogeneity is related to region. The risk of MACEs in patients with CKD is different in different regions, and North America has the lowest risk, with an risk ratios value of 1.21 (95% confidence interval: 1.08-1.35). CONCLUSION Chronic kidney disease will increase the probability of MACE in patients with myocardial infarction after PCI and affect the prognosis of PCI. Therefore, clinical attention should be given to assessing glomerular filtration rate effects while treating patients with myocardial infarction with the PCI procedure.
Collapse
Affiliation(s)
- Xiang Zhu
- Jiangxi Provincial Key Laboratory of Preventive Medicine, School of Public Health, Nanchang University, Nanchang, People's Republic of China
| | | | | | | | | | | | | | | | | |
Collapse
|